Efficiency

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, up 133% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 62

Oct 1, 2026cs.AI

AI-assisted mitotic counting improves reproducibility and efficiency across multiple tumour types

Mitotic counting is an important component of tumour grading, diagnosis and prognostic assessment across several tumour types, but manual assessment is time-consuming and subject to inter-pathologist variability. To help address these challenges, we developed MitPro, an AI tool designed to improve consistency and efficiency by directing pathologists towards regions with the highest predicted mitotic activity and highlighting mitotic figures for review, while retaining pathologist control over region selection and the final count. We evaluated its effect on the reproducibility and efficiency of mitotic counting in a retrospective, non-interventional, paired reader study comprising 385 whole-slide images from 3 centres in 3 countries and 7 tumour types using 3 different scanners. 13 pathologists participated, with each slide assessed independently by 3 pathologists without AI assistance and again with AI assistance after a minimum 2 week washout period. Across all slides, AI-assisted counting increased the intraclass correlation coefficient from 0.589 to 0.949. Mean pathologist-level median assessment time decreased from 286.4 to 127.8 seconds, corresponding to an average saving of 151.8 seconds per assessment. Improvements in agreement and efficiency were also observed in supporting analyses using HALO AP and Sectra image management systems and in 2 additional tumour types outside the main study population. AI-assisted assessment was associated with a subtle shift towards higher mitotic counts and scores, consistent with identification of more active mitotic hotspots and fewer missed mitotic figures. The frequency of score change between unassisted and AI-assisted assessment was comparable with inter-pathologist variation during routine counting. These findings support the use of MitPro as an assistive tool for more consistent and efficient mitotic assessment in routine practice.

Simon Graham, Mostafa Jahanifar, Quoc Dang Vu +15

Histofy Ltd, Coventry, United Kingdom · Vilnius University Faculty of Medicine and National Center of Pathology, Affiliate of Vilnius University Hospital Santaros Klinikos, Vilnius, Lithuania · Nottingham University Hospitals NHS Trust, Nottingham, United Kingdom +5

Mitotic Figures Tumor Prognostics Reproducibility Efficiency

Sep 29, 2026cs.SD

Pruning for Efficiency, Paying in Fairness: Demographic Disparities in Pruned Speech-LLMs

Speech-LLMs are expensive to run, making compression important for real-world deployment. However, compressed models are usually selected using aggregate word error rate (WER), which can hide how pruning affects different demographic groups. In this work, we systematically study the effect of audio encoder pruning on SLAM-ASR for different demographic groups. Using the Fair-Speech and Common Voice datasets, we found that the pruning does not affect all demographic groups equally; the gap between best- and worst-performing groups increases in fold. These disparities appear across all three encoder scales, but only the largest model initially hides them behind aggregate WER. LoRA adaptation improves WER for every group, but benefits groups already performing well more strongly and widens for certain groups. On Common Voice English, Danish, and Dutch, accent gaps persist but do not clearly widen, showing that the fairness effects of pruning vary across datasets and must be measured directly. Our findings suggest that for pruned models, deployment decisions should include per-group WER, with the worst-performing group's error rate as an explicit criterion.

Ganesh Pavan Kartikeya Bharadwaj Kolluri, Michael Kampouridis, Ravi Shekhar

School of Computer Science and Electronic Engineering, University of Essex, UK

Character Error Rate Disparities Algorithmic Fairness Sequential Scaling Efficiency Orb-Slam2

Sep 28, 2026cs.AI

CoeF-SFL: Preserving Collaborative Server-Client Learning with Enhanced Communication Efficiency

Split Federated Learning (SFL) enables resource-constrained clients to participate in collaborative training, but vanilla SFL exchanges smashed data and gradients at every batch, which incurs significant communication overhead. Recent methods reduce this overhead with an auxiliary network at the client-side cut layer. However, we identify that this approach makes the client optimize a local objective that differs from the end-to-end objective, which fundamentally limits the collaborative training between the client and the server. We propose Compensated Feedback based SFL (CoeF-SFL), a communication-efficient framework that retains the end-to-end objective without any auxiliary network. In CoeF-SFL, the client and the server exchange the smashed data and the gradients once per round and reuse them during local training. Since this reuse makes the gradients stale on the client side, we compensate them with a curvature-based correction in the activation space and develop two variants. CoeF-D approximates the Hessian with a diagonal gradient outer product, while CoeF-J exploits the tractable Jacobian-based Hessian of a surrogate loss that upper-bounds the true loss. We provide the theoretical background of each method, characterizing its compensation. Across vision and language tasks, model capacities, cut layers, and data distributions, CoeF-SFL significantly outperforms auxiliary-network-based methods under the same communication frequency, and the improvement is most substantial on vision tasks. Code is available at https://anonymous.4open.science/r/CoeF-SFL-2686/README.md

Junwoo Bae, Jin-Hyun Ahn

Myongji University

Feedback Efficiency

Sep 27, 2026cs.LG

No Free Efficiency: Revisiting the Trade-off Between Training Efficiency and Model Vulnerability

Training efficiency has become the central driver of recent progress in foundation models. To overcome the massive computational and data requirements of large-scale training, researchers increasingly adopt strategies such as selective data sampling, efficient pre-training, and simplified reinforcement learning pipelines. While these strategies drastically reduce overhead, they prompt a critical, yet neglected question: Is efficiency achieved at the expense of model robustness and security? To our knowledge, we present the first systematic cross-domain investigation of the efficiency-vulnerability trade-off. Across vision and language models, we show that efficiency-oriented training increases susceptibility to adversarial and privacy attacks. We characterize this vulnerability by analyzing the models' internal geometry and functional representations, demonstrating that the evaluated efficient variants consistently exhibit sharper loss geometry together with systematic changes in representational structure. We further extend our analysis to "zero RL training", finding that models trained using simplified RL recipes exhibit substantially greater susceptibility to catastrophic forgetting and more pronounced overconfidence than those trained through conventional alignment pipelines. Our findings suggest that training efficiency is rarely a "free lunch"; rather, the mechanisms that minimize computation can inadvertently compromise safety. We conclude by calling for a paradigm shift toward multi-objective training that jointly optimizes for performance, cost, and security.

Yiyong Liu, Jun Sakuma, Michael Backes +1

CISPA Helmholtz Center for Information Security · Institute of Science Tokyo

Capability-Speed Trade-Offs Efficiency Trade-Off Representational Capacity

Sep 20, 2026cs.CL

On the Efficiency-Safety Dilemma in Large Reasoning Models

Large reasoning models (LRMs) incur high inference costs, often mitigated by efficiency techniques like quantization and pruning. However, the impact of these techniques on model adversarial robustness remains largely unexplored. This study provides the first comprehensive analysis of the interplay between efficiency, jailbreak vulnerability, and reasoning in LRMs. We find that while efficiency methods seemingly reduce the success rate of jailbreak attacks, this improvement is often superficial. It largely arises from degraded reasoning capabilities leading to "attempted but failed" malicious responses, rather than an increase in genuine alignment. Mechanistic analysis of representational drift confirms this, revealing a strict coupling between reasoning capability loss and the model's inability to maintain malicious semantic trajectories. Additionally, we identify quantization with pruning as the optimal strategy to balance efficiency and robustness. These findings clarify the distinction between true safety alignment and capability-induced failure, providing an empirical foundation for LRM deployment.

Yifei Yang, Zouying Cao, Xingrui Wang +4

AGI Institute, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University · Ant Group +2

Large Reasoning Models Jailbreak Attacks Efficiency

Sep 17, 2026cs.FL

Stringological sequence prediction III: layered ziplines and a tradeoff between efficiency and expressivity

In previous papers, we began the study of sequence prediction algorithms adapted to stringological word complexity measures. In particular, we defined a complexity measure called Arithmetic Repetition Complexity (ARC) which admits a polynomial-time prediction algorithm with a mistake bound quasilinear in the complexity. Here, we show a weaker complexity measure related to ARC that admits an especially efficient prediction algorithm: an algorithm that runs in quasilinear time and polylog space for appropriate highly-structured sequences. The complexity measure is defined via a restricted class of "zipline programs" (a variant of straight-line programs), which we call layered. We thus get a less expressive measure with a more efficient algorithm (compared to our results for ARC), demonstrating a possible tradeoff.

Vanessa Kosoy

Faculty of Mathematics, Technion, Haifa, Israel · Computational Rational Agents Laboratory, Delaware, USA

Sequence Modeling Structural Complexity Expressivity Efficiency Trade-Off

Sep 17, 2026cs.AI

Rethinking Multi-Agent Collaboration: When More Is Less

The rapid advancement of large language models and single-agent harnesses has reshaped the landscape of autonomous systems, raising a critical question of when multi-agent collaboration offers genuine value. As individual agent capabilities continue to scale, multi-agent collaboration faces diminishing returns while incurring growing context overhead. Through systematic analysis, we delineate the capability boundaries of multi-agent collaboration relative to single-agent alternatives, showing that it confers systematic benefits specifically in long-horizon tasks with sparse dependencies, while single-agent harnesses remain superior in tightly coupled, sequential workflows. Building on these insights, we propose SAIGE, a lightweight multi-agent collaboration mechanism based on Semantic-Aware Incremental Graph Evolution. SAIGE models collaboration as a dynamically evolving graph, where nodes are agent instances spawned on demand and edges encode semantic dependencies established through content-based information retrieval. Experiments on long-horizon, complex task benchmarks show that SAIGE achieves a favorable trade-off between context efficiency and task performance, and that scaling the agent pool or deepening the recursion level does not consistently improve outcomes. Our findings suggest that multi-agent superiority is bounded by task structure rather than universal, and that more agents do not necessarily make a system more intelligent.

Yishuo Yuan, Yibo Wu, Yihan Zhang +5

Nanjing University · Shanghai Jiao Tong University

Long-Horizon Task Planning Efficiency

Sep 16, 2026cs.LG

How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents

Scaling laws predict how loss decreases with increases in computation. We show, contrary to conventional wisdom, that architectural interventions can modify scaling exponents in pre-training, leading to power-law improvements in performance as computation increases. As an anchoring point, we consider the architectural formulation of looped transformers. Although not typically used in this way, looping, also known as recursive depth, provides a mechanism for model growth, by increasing the number of loops during training. Model growth, with and without shared weights, provides the biggest changes to the scaling exponents. In particular, a 7.4B model growth architecture matches GPT-3 13B on CORE with roughly

20\times

less compute, and has compute efficiency gains that increase with scale. Moreover, simply using a boundary operator in a vanilla transformer, which normalizes and injects an earlier block, also provides an exponent increase, although to a lesser extent. In the data-constrained, multi-epoch setting, standard looping has a useful regularizing effect, where we find it is compute-optimal to increase the number of loops with scale. These results can be understood through the lens of computational depth: for a given computational budget, we wish to increase the usable depth of the transformer, which can lead to efficiency gains that increase with scale.

Zixi Chen, Akshay Vegesna, Samip Dahal +1

New York University · Q Labs

Scaling Laws Exponents Transformer Architectures Recursive Models Growth Efficiency+1

Sep 12, 2026cs.AI

AI-Powered Flare Combustion Efficiency Estimation

Achieving high combustion efficiency in flare stacks is crucial for adhering to regulatory standards and controlling the release of hydrocarbons into the environment. Traditional instruments like gas analyzers and hyperspectral cameras are expensive, fragile, and require frequent calibration, which makes them impractical for remote or budget constrained industrial sites. We propose an innovative solution that combines a lightweight vision-language encoder with a compact multi-layer perceptron to predict combustion efficiency directly from low-cost thermal video footage. The fully trained model is integrated into an easy-to-deploy graphical user interface. This interface overlays predicted combustion efficiency values on each video frame, displays real-time trends in combustion efficiency, shows the distribution of combustion efficiency across all frames in the video, and allows users to export CSV reports. Over a six-month period, the system achieved 99% uptime and required less than 15 minutes of maintenance per week.

Afeefa Azam, Iyyakutti Iyappan Ganapathi, Fares Ossama Abdelhafez +5

Computer Science Department, Khalifa University of Science and Technology, Abu Dhabi, UAE · Mechanical & Nuclear Engineering, Khalifa University of Science and Technology, Abu Dhabi, UAE · Digital Projects & Innovation Division, ADNOC, Abu Dhabi, UAE

Combustion Control Mobile Gas Sensor Trajectories Govern Hydrogen Leak Detection Wildfire Detection Efficiency

Sep 7, 2026cs.AI

CPR-IE:A Compression-Prediction-Resource Intelligence Efficiency Metric

Comparing intelligent systems under deployment constraints requires more than predictiveaccuracy.This paper develops Compression-Prediction-Resource Intelligence Efficiency (CPR-IE) as a protocol-relative ordering by representational economy, predictive quality, and resourceburden. The analysis separates two questions-how raw resource consumption is represented, andhow the resulting attributes are aggregated. Proportional-increment composition uniquely yieldslogarithmic cumulative burden, and context-independent ratio response yields power responsesto compression, prediction, and burden; with reference normalization the representation is I(C,P,T).We prove Pareto consistency, unit invariance, boundary behavior, trade-off identities, ranking-stability regions, and cross-task aggregation. A translog parent model makes interaction restrictions explicit, and further results establish cardinal and ordinal identification, sub-Gaussianfinite-sample ranking guarantees, robust selection under exponent uncertainty, and deterministicregret bounds. Minimum description length, algorithmic complexity, proper scoring rules, varia-tional inference, and Landauer's principle motivate measurement choices but do not entail theformula. CPR-IE is a constructed efficiency representation, not a universal law or a definition ofintelligence itself.

Xiantao Jiang

College of Information Engineering, Shanghai Maritime University Shanghai 201306, China

Efficiency Prioritization Information-Theoretic Limits Representational Capacity Order Matters

Aug 10, 2026cs.CV

Alpha as an Efficiency Signal: Visibility-Routed RGBA Image-to-Video Generation

RGBA videos combine RGB appearance with an alpha channel, enabling animated assets to be applied across arbitrary backgrounds, which are heavily used in gaming industry. However, generating high-quality RGBA animations for games remains challenging for two reasons. First, most existing RGBA video datasets are dominated by photorealistic content, with limited coverage of game assets. Second, the traditional generate-then-matte pipelines estimate alpha only after RGB synthesis, so semi-transparent regions are often blurred by background, resulting in unstable matting outputs. More recently, many methods have begun to model RGB and alpha jointly, but existing approaches are mostly text-conditioned, and still have unresolved issues in efficiency and quality. To address these challenges, we introduce GameAlpha-2.4K, a 2.4K-clip game-style RGBA video dataset built with matte-friendly synthesis, multi-hypothesis alpha recovery, and compositing-based quality gates. Using this dataset, we train a reference-conditioned RGBA video generator that jointly produces RGB frames and alpha mattes in a single pass. To improve efficiency, we propose a visibility router that identifies transparent tokens in an early stage and bypasses their later DiT updates, while x_0-lock guides them along the original flow-matching schedule toward self-predicted endpoints. Our model obtains lower FVD than traditional two-stage pipelines, and the visibility router skips 35% of token evaluations in the final two DiT denoising steps, providing a 1.2x backbone speedup with negligible quality degradation compared to dense inference.

Zhe Li, Honghao Qiao, Zhixin Xu +3

Peking University · ByteDance · Tsinghua University

Data Generation Pipelines Efficiency

Aug 4, 2026cs.CL

M-GATE: Multilingual Grammar, Accuracy in Translation, and Efficiency Benchmark for Large Language Models

Multilingual language models are deployed across a hundred or more languages, yet most benchmarks test whether a model can perform a task in a language rather than whether it commands the language itself, conflating fluency with proficiency. We introduce M-GATE (Multilingual Grammar, Accuracy in Translation, and Efficiency), a benchmark of linguistic proficiency spanning 30 typologically diverse languages from high- to low-resource. M-GATE comprises three tasks: grammatical error detection on linguist-crafted, adversarially selected sentences that turn on hard, language-specific phenomena; round-trip translation of shared English sources across 29 target languages, scored by a three-provider LLM judge panel validated against professional annotators; and a supplementary tokenizer-efficiency measure. We evaluate over 50 models in more than 80 configurations. Fluency and proficiency come apart sharply: models that translate competently sit near chance on the adversarial grammar items, the best reaching a Matthews correlation coefficient (MCC) of only 0.36, and their errors lean systematically toward under-flagging, accepting ungrammatical text rather than raising false alarms. Translation quality closely tracks a language's share of pretraining data (r = 0.86 against log Common Crawl share), producing a steep low-resource penalty that is nonetheless narrowing with successive model releases. Enabling reasoning reliably improves translation, while its effect on error detection is smaller and for some models negative, so the best configuration is task-dependent. To resist contamination, test items are kept private behind a continuously updated public leaderboard, with illustrative examples released (https://m-gate.ai).

Tomáš Burkert, Angelika Peljak-Łapińska, David Zelený

RWS TrainAI

Multilingual Benchmark Multilingual Language Models Grammatical Error Correction Proficiency Efficiency

Aug 4, 2026cs.MM

Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMs

Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception and rigorous logical deduction. Explicit text-based Chain-of-Thought (CoT) is computationally expensive and prone to visual hallucinations, while existing latent reasoning methods typically require costly training. Furthermore, directly adapting training-free LLM reasoning mechanisms to the multimodal setting yields unstable performance. We identify that this failure stems from their reliance on token-level entropy, which fundamentally conflates perceptual ambiguity (e.g., unclear visual details) with logical uncertainty (e.g., complex reasoning steps). To overcome this bottleneck, we present a novel training-free inference strategy for MLLMs that explicitly decouples perception and reasoning. We propose a novel metric, the vision-to-text attention ratio, to dynamically gauge the model's cognitive focus. Guided by this metric, our proposed framework, Attention-Guided Switching (AGS), adaptively triggers latent reasoning for perceptual tokens to preserve high-fidelity visual information in the continuous space, while enforcing explicit text generation for logical tokens to maintain structural anchoring. Extensive experiments demonstrate that our method achieves state-of-the-art performance, significantly improving both accuracy and inference efficiency by reducing autoregressive steps and latency. Code is released at https://github.com/swordAndSnow/MM26-AGS.

Haoqian Kang, Liupeng Li, Kuofeng Gao +5

Harbin Institute of Technology, Shenzhen Shenzhen, China · Tsinghua Shenzhen International Graduate School, Tsinghua University Shenzhen, China · Peng Cheng Laboratory Shenzhen, China +1

Multimodal Large Language Models LLM Reasoning Strategies Recent Vision-Language Models Latent Thoughts Chain-of-Thought Reasoning Training-Free+2

Jul 29, 2026cs.LG

Simultaneous Coverage and Efficiency Guarantee in Online Conformal Prediction

Adaptive conformal inference (ACI) of Gibbs and Cand{è}s and its variants are the standard approach to online conformal prediction under distribution shift, but they suffer from three fundamental limitations. First, their guarantees control only the \emph{signed} long-run coverage error: persistent miscoverage in one direction can be masked by compensating errors later, so a method can satisfy the theoretical guarantee while being badly wrong for extended periods. Second, existing guarantees say nothing about prediction-set size, so validity can be achieved trivially at the cost of unduly wide prediction sets. Third, the efficiency guarantees that do exist compare against a \emph{fixed} predictor chosen in hindsight, a benchmark that becomes increasingly less meaningful once the data-generating distribution shifts, since the very notion of an optimal threshold then changes over time. We consider a unified online learning framework that simultaneously controls absolute, non-cancelling coverage violation and prediction-set efficiency against a dynamically evolving benchmark for three important models. In the fully adversarial setting, exploiting the fact that the standard ACI update is exactly projected online gradient descent on the pinball loss, we derive simultaneous coverage and efficiency guarantees for arbitrary monotone Lipschitz efficiency objectives, with no distributional or {\it convexity} assumptions. In the stochastic setting with full-score feedback, we propose a sliding-window quantile tracker and establish a matching minimax lower bound showing our algorithm is rate-optimal. In the covariate-dependent stochastic setting, we develop a partitioned ACI algorithm that tracks a function-valued oracle threshold, and derive simultaneous coverage and efficiency guarantees.

Rahul Vaze

Tata Institute of Fundamental Research, Mumbai

Conformal Inference Online Conformal Prediction Long-Run Coverage Guarantees Learning-Augmented Algorithms Efficiency Gradient Descent

Jul 28, 2026cs.LG

Beyond Single-Episode Optimization: Sliding-Window Aware Generative Auto-Bidding for Long-Term Advertising Effectiveness

Auto-bidding systems optimize bids to maximize value under efficiency constraints such as Cost-Per-Action (CPA). Existing methods treat each day as an independent episode. However, many advertisers produce value so sparsely that per-day efficiency ratios become statistically unreliable, undermining advertiser retention. Platforms therefore evaluate window-level efficiency over sliding windows of

W{=}7

days, ensuring fair evaluation and long-term advertising effectiveness. This creates cross-episode coupling: each day's bidding decisions affect up to

W

overlapping windows, so setting daily targets requires anticipating future market conditions. We propose SWAG-Bid (Sliding-Window Aware Generative Auto-Bidding), a hierarchical framework decomposing this challenge into episode-level planning and step-level execution. The planner uses a Masked Trajectory Model to forecast markets and generate candidate plans, scored across all overlapping windows by Multi-Window Model Predictive Control Sampling (MWMS) with exponential confidence decay. The controller adjusts reliance on this guidance through a state-adaptive gate, Per-Step Gated Adaptive Layer Normalization (PSG-AdaLN), complemented by Return-to-Go and Cost-to-Go channels carrying budget and constraint information. Experiments on AuctionNet-Sparse and online A/B tests on AliExpress show that SWAG-Bid achieves competitive constraint satisfaction and value acquisition under sliding-window evaluation.

Binglin Wu, Chuan Yue, Yingyi Zhang +4

Dalian University of Technology Dalian, China · Alibaba International Digital Commerce Group Hangzhou, China · Dalian University of Technology & City University of Hong Kong Dalian, China

Ads Efficiency Channel

Jul 27, 2026cs.AI

Efficiency Matters in Autonomous Research

AI-driven autonomous research (AR) systems are becoming increasingly effective across a broad range of tasks. Their performance, however, is still evaluated primarily by the quality of the final outcome. In this paper, we argue that the efficiency of the solution-search process is an equally important but often overlooked dimension of performance. A strong AR system should not only produce high-quality results, but also reach them with as small a budget as possible. Search efficiency will become increasingly important as AR expands from domains with inexpensive verification, such as mathematics and coding, to real-world scientific settings in which solution evaluation may require costly physical experiments. To capture this dimension, we propose evaluating AR systems using the area under the curve (AUC) of the Pareto frontier, alongside final outcome quality. We compare several families of search algorithms, including hill climbing, beam search, tree search, and evolutionary search, across twelve systems-optimization tasks. We find that no single search structure is consistently the most efficient. We also show that search efficiency and final outcome quality are distinct performance dimensions: a method that eventually achieves the best result may nevertheless improve slowly and consume substantially more evaluation budget before reaching that result. Because the most effective search policy is generally unknown in advance, we introduce an adaptive procedure called fluid search, which uses a portfolio bandit to dynamically allocate a fixed evaluation budget across a forest of search processes. Across the evaluated tasks, fluid search achieves the highest overall search efficiency, closely matching the performance of a per-task oracle that is given the best search structure for each task in advance.

Haiqian Yang, Yuan Cao

Research Automation Search Algorithms Efficiency Bandits

Jul 17, 2026cs.RO

A Morphing-Designed Hexarotor Prototype combining Practical Resilience and Efficiency

This work demonstrates experimentally the existence of a hexarotor prototype, termed Opti-Hexa, that simultaneously achieves practical resilience to single-propeller failures and energy efficiency comparable to a standard Star-shaped prototype with the same size, weight, hardware and software. Leveraging a novel open-source morphing platform, we investigate the trade-offs across a continuous range of geometries by varying the angles between adjacent propellers. We study practical efficiency through a data-fitted empirical power model and evaluate practical resilience by comparing the position accuracy and rotational kinetic energy during failure to those observed under nominal hovering conditions. Our experiments confirm the existence of a geometric viability region for this specific morphing platform, where resilience is ensured without the aerodynamic efficiency losses typically associated with practically resilient designs found in the state of the art. The complete hardware and software of the morphing platform are released to support further research.

Murat Bronz, Mahmoud Hamandi, Elgiz Baskaya +2

Ecole Nationale de l’Aviation Civile, Toulouse, France · Center for Artificial Intelligence and Robotics, New York University Abu Dhabi, Saadiyat Island, 129188, Abu Dhabi, UAE · Robotics and Mechatronics lab, Faculty of Electrical Engineering, Mathematics & Computer Science, University of Twente, Enschede, The Netherlands +1

Rotorcraft Aerodynamics Resilience Efficiency Convex Sets

Jul 14, 2026cs.CR

WaterMoE: Expert-Routing-based Watermarking for High Fidelity and Efficiency

Large language models (LLMs) have achieved remarkable success but raise growing concerns about content provenance and misuse, motivating the need for reliable watermarking techniques. However, these techniques have rarely been adopted in practice mainly for two reasons: i) severely degraded model performance, and ii) additional inference overhead. To confirm the problem, we construct a comprehensive benchmark spanning different generation tasks to systematically evaluate 9 representative watermarking methods. We found almost all existing methods are designed for text fluency, but not for restricted and complicated tasks, and their overhead prevents them from deployment in latency-critical systems. To address i) and ii), we propose an LLM watermarking scheme \textit{WaterMoE} for the growingly popular Mixture-of-Experts (MoE) LLMs. WaterMoE embeds watermarking signals through controlled perturbation into the expert selection at each router, which accumulates to token selection shift at the final output. In contrast to watermarking as a post-processing token-sampling approach, WaterMoE embeds watermark within the inference loop incurring negligible quality degradation and computational overhead. Extensive experiments demonstrate that our method achieves a fidelity performance close to the unwatermarked and consistently outperforms state-of-the-art watermarking methods on the benchmark, with up to

4\times

speedup, incurring merely 1% additional inference latency compared to native generation. The results demonstrate the capability of WaterMoE to be deployed in real-world tasks.

Z Sun, Q Jiang, S Sheng +1

Shanghai Jiao Tong University · Shanghai Innovation Institute · Tianjin University

Large Language Model Watermarks Watermarking Watermarks Efficiency High-Fidelity

Jul 13, 2026cs.AI

Enhancing Query Efficiency for d-DNNF Representations Through Preprocessing

In this paper, we investigate preprocessing techniques aimed at improving the efficiency of accessing models of propositional formulas represented in conjunctive normal form (CNF). We focus on three fundamental tasks: uniform sampling, direct model access, and model enumeration. Our analysis reveals that most state-of-the-art preprocessors, when they do not preserve formula equivalence, are generally unsuitable for these tasks. In contrast, we demonstrate that preprocessors which preserve model counts can be effectively leveraged, provided relevant preprocessing information is maintained. To validate our approach, we perform extensive experiments on a diverse suite of benchmarks from multiple domains. The experimental results show that our preprocessing methods are both efficient and robust, yielding significant performance improvements for model access queries when CNF formulas are compiled into d-DNNF representations.

Jean Marie Lagniez, Emmanuel Lonca

CRIL, U. Artois & CNRS, F-62300 Lens, France

Preprocessing Efficient Planning Neural Network Representations Logic Efficiency

Jul 11, 2026cs.RO

On the Efficiency of LoRA Fine-Tuning for Vision-Language-Action Models in Industrial Robotic Manipulation

Deploying billion-parameter Vision-Language-Action (VLA) models on industrial hardware requires fine-tuning to bridge the embodiment gap. Full Fine-Tuning (FFT) provides maximal plasticity but requires data centre-grade GPUs. We present a systematic study of Low-Rank Adaptation (LoRA) for

π_0

, a flow-matching VLA, evaluated on four precision assembly tasks with a UR5e robotic manipulator. Across a sweep of LoRA ranks (r=8 to 256), allocation strategies, and component-freezing ablations, we find no statistically significant advantage of FFT over certain LoRA configurations. Performance saturates at r=32, and uniform allocation across the Vision-Language-Model (VLM) backbone and action expert proves sufficient. Freezing the VLM or restricting the vision encoder to LoRA significantly degrades performance, indicating that embodiment adaptation requires both semantic and visual plasticity. These results suggest that LoRA at r=32 with full vision encoder fine-tuning is a practical approach, reducing static peak VRAM from 36.2 to 10.8 GiB (parameters and optimizer states, activation memory excluded) without detectable performance loss.

Finn Ferchau, Daniel Pommer, Cristian Axenie

Technische Hochschule Nürnberg Georg Simon Ohm, Nürnberg, Germany · Siemens AG, München, Germany · Fraunhofer Institute for Integrated Circuits (IIS), Erlangen, Germany

Diffusion-Based Vision-Language-Actions Flow-Matching Vision-Language-Action Vision Encoders Embodiment Efficiency

Jul 1, 2026cs.LG

The Rollout Infrastructure Tax in Coding-Agent Reinforcement Learning

Coding-agent reinforcement learning treats execution infrastructure as a background implementation detail, despite relying on large numbers of interactive software rollouts. This is a missed opportunity: measuring infrastructure overhead can reveal practical efficiency gains for RL post-training, where small per-rollout savings compound at scale. We present a comparative study of four execution substrates: single containers, hosted sandboxes, Kubernetes-orchestrated containers, and cloud virtual machines. We find up to

110\times

variation in cold-start latency and a

1.8\times

spread in projected worker-hours for one million 150-step trajectories. Our results suggest that future coding-agent RL systems should optimize execution substrates as part of the training system itself, not merely as deployment plumbing.

Daniel Thi Graviet, Lovre Pesut, Ivan Dagelic +2

Daytona United States

Coding Agents Rollout Agentic Inference Offline Reinforcement Learning Reinforcement Learning Post-Training Efficiency+1

Jun 25, 2026cs.CL

CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention

Recurrent delta-rule models keep a fixed-size state matrix S (d_v x d_k) that compresses all past context. The state of the art (GDN-2) gates this update with element-wise matrix erase/write masks. This is powerful but has two defects. First, both gates are computed from the incoming token alone, making the model memory-blind: it decides what to erase without seeing what it has stored. Second, value-axis coupling in the erase gate blocks the WY-form triangular chunk solver that drives efficient training -- the intra-chunk system splits into d_v independent solves, collapsing throughput to serial-recurrence cost. We introduce CARVE (Content-Aware Recurrent with Value Efficiency), which fixes both and, via a single-launch "megakernel" scheduling of the same WY-form math, trains faster than the matrix-gated baseline it replaces. The key idea is architectural: restricting all gating to the key axis makes the intra-chunk coupling independent of the value index, restoring one unmodified WY-form solve. Within this constraint, CARVE conditions both gates on a content signal read once per chunk from the chunk-boundary state and folded algebraically into each gate's low-rank projection (by associativity, U(Sq)=(US)q), giving memory-aware gating at negligible extra traffic. At init the content projections are zero, so CARVE is bit-identical to the baseline; we prove the one-chunk staleness perturbs gates by only O(1/sqrt(L)), matching a measured 0.18% deviation flat up to L=128. At 1.3B parameters / 100B FineWeb-Edu tokens on H100 (three seeds), CARVE improves every axis: WikiText perplexity 15.72 vs 15.90 (hybrid 15.41 vs 15.62), +0.63 pp average common-sense accuracy, and state-of-the-art RULER and real-world recall -- while training +1.4% faster at matched depth and +19.3% at iso-quality depth, at +13% peak memory. Backed by six formal guarantees.

Sayak Dutta

Recurrent Model Kimi Delta Attention Bounded-Memory Factual Recall Gradient Staleness Efficiency

Jun 22, 2026cs.IR

HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions

With the rapid spread of retrieval-augmented generation and semantic search, choosing the right embedding and retrieval configuration is increasingly hard. Large retrieval benchmarks are comprehensive but too heavy to rerun during development, and there is little infrastructure for comparing production settings--dimensionality reduction, quantization, reranking--across many models under identical conditions. We present HAKARI-Bench, a lightweight benchmark that reconstructs existing retrieval suites into small datasets (Nano-sets): 35 benchmarks and 551 tasks across 43 languages in a unified format, enabling same-condition, model-agnostic comparison of five retrieval families (BM25, dense, sparse, late interaction, rerankers) and their efficiency variants. Across 55 models, its overall ranking reproduces the official MTEB retrieval v2, MMTEB v2 retrieval, and English BEIR (full) at Spearman >0.97. HAKARI-Bench does not replace full evaluation; it enables rapid model selection, regression detection, and reading the quality-efficiency Pareto frontier. Code, data, and leaderboard are released under the MIT license.

Yuichi Tateno

Reasoning Benchmark Efficiency

Jun 20, 2026cs.RO

Dynamics, stability, and energy efficiency of an energy-recycling rimless wheel with spring-clutch legs

This paper proposes an energy-recycling rimless wheel with spring-clutch legs. The proposed mechanism uses a lockable clutch to store part of the impact-induced elastic energy after foot contact and reinject it in the next gait cycle. First, we develop a hybrid dynamic model of the energy-recycling rimless wheel. Second, numerical simulations are used to examine the dynamics, local stability of periodic gaits, and the Cost of Transport (CoT) of the proposed mechanism. The simulation results show that the proposed mechanism reduces the CoT by up to 16.13% compared with a benchmark viscoelastic-legged rimless wheel with telescopic spring-damper legs. Compared with the rigid rimless wheel, the viscoelastic-legged and energy-recycling models reduce the CoT by more than 50%. The energy-recycling model also maintains locally stable periodic gaits over the tested slope and stiffness ranges. Finally, prototype experiments on an inclined plane are conducted to examine the feasibility of the proposed mechanism. The experimental results show that the proposed rimless wheel achieves passive walking on a shallow 1° slope, corresponding to a CoT of approximately 0.02. These results suggest that the proposed spring-clutch mechanism can improve the simulated walking efficiency of the energy-recycling rimless wheel, while the prototype experiments support the feasibility of passive walking with the mechanism.

Tongchen Lin, Yanqiu Zheng, Chuhan Zhang +3

Department of Mechanical Engineering and Robotics, Guangdong Technion-Israel Institute of Technology, Shantou, China. · Department of Applied Electronics, Faculty of Advanced Engineering, Tokyo University of Science, Tokyo, Japan. · Tongchen Lin, Chuhan Zhang, Ruigang Chen, Yizhar Or, and Mingyi Liu: Faculty of Mechanical Engineering, Technion-Israel Institute of Technology, Haifa, Israel.

Wheel Claw-Like Agent Efficiency

Jun 19, 2026cs.GT

Simultaneously Efficient Allocation of Indivisible Items Across Multiple Dimensions

Many allocation problems are intrinsically multidimensional, since an item may contribute differently to several criteria, and optimizing a single aggregate objective can hide severe losses in other dimensions. We study how much efficiency can be guaranteed simultaneously when indivisible items have multiple attributes. To this end, we introduce the \emph{multidimensional efficient allocation} (MDEA) model, where each agent has an additive valuation in each dimension, and investigate simultaneous efficiency under utilitarian social welfare (USW) and egalitarian social welfare (ESW). Our results reveal a sharp worst-case frontier. For exact efficiency, maximizing the number of dimensions attaining the USW optimum admits a

c/\ell

-approximation for every fixed constant

c

, and this dependence on the number

\ell

of dimensions is essentially unavoidable; for ESW, even deciding whether two dimensions can be optimized simultaneously is NP-hard with binary valuations. For approximate simultaneous efficiency in every dimension, we identify a tight threshold of order

1/\ell

, showing that such guarantees always exist for both USW and ESW, while any asymptotically better dependence on

\ell

is impossible, even for binary valuations. Finally, we introduce three natural multidimensional Pareto notions and characterize both their relationships and their computational complexity.

Yasushi Kawase, Bodhayan Roy, Mohammad Azharuddin Sanpui

Chuo University, Tokyo, Japan · Indian Institute of Technology Kharagpur, Kharagpur, India

Welfare Pareto Frontier Efficiency Value

Jun 18, 2026cs.RO

Comparative Study on Agility, Efficiency, and Impact Absorption of Bipedal Robots with Active Toes

Human legs exhibit high efficiency, agility, and impact absorption, with toes playing a crucial role in these capabilities. While many attempts have been made to implement human-like toes in robots, they have not fully replicated human characteristics nor rigorously validated their benefits. We propose a 14-DOF biped robot emulating human toes' lightweight, high-torque, robust nature. To quantitatively analyze the effectiveness of the active toes in terms of agility, efficiency, and impact absorption, we developed a high-fidelity simulation training environment that reflects actual actuators with coupled transmissions and accurate power consumption. To ensure a fair comparison between configurations with and without active toes, we designed a minimal RL reward function and applied an identical training procedure to both. The simulation results indicate that, at 1.33 m/s walking, the toe-equipped robot reduced CoT by 17.5% and heel-strike GRF by 5.0% compared with the toe-ablation configuration. On the agility test, average and maximum path deviation decreased by 25.0% and 34.0%, respectively.

Joong-Gil Kim, Wontae Ye, Geunwoo Cho +3

School of Electrical, Electronics and Communication Engineering, Korea University of Technology and Education, Cheonan, 31253, Korea · Artificial Intelligence and Robotics Institute, Korea Institute of Science and Technology, Seoul, 02792, South Korea · Robot Innovation Hub, WIRobotics Inc., Cheonan, 31253, Korea

Legged Robots Feet Efficiency

Jun 17, 2026cs.RO

DF-ExpEnse: Diffusion Filtered Exploration for Sample Efficient Finetuning

A natural recipe for intelligent robotic decision-making is initializing from pretrained generative control policies, which have summarized offline experience, and adapting them to self-collected online experience. We present DF-ExpEnse, an exploration technique that improves the quality of online experience collection, thus increasing finetuning sample-efficiency. DF-ExpEnse leverages the multimodal modeling capabilities of the generative control policy to create an expressive and tractably evaluatable candidate set. It then utilizes an ensemble of critics to identify the action that best balances quality with high exploration interest. In fleet settings, DF-ExpEnse further enables cross-agent communication to facilitate collaborative exploration as a group. DF-ExpEnse can be seamlessly integrated with existing strategies that finetune pretrained generative control policies via reinforcement learning. We experimentally validate consistent sample-efficiency benefits through DF-ExpEnse across a variety of manipulation and locomotion tasks, compared to default finetuning and alternative action selection schemes. Project can be found at https://df-expense.github.io.

Calvin Luo, Chen Sun, Shuran Song

1Stanford University · 2Brown University.

Stochastic Exploration Generative Control Policies Exploration Model Fine-Tuning Efficiency Token Budget Allocation

Jun 17, 2026cs.CV

Dyna-DINO: Efficient ViT Distillation Via Adaptive Representation Anchoring

Vision Foundation Models (VFMs) with Vision Transformer (ViT) backbones, such as DINOv2, have become essential for downstream tasks like object recognition and semantic segmentation. The immense computational requirements of backbones often necessitate distillation into smaller architectures for edge deployment. Feature-based knowledge distillation (KD) often suffers from the teacher-student gap; the student struggles to imitate teacher's complex feature map due to its limited capacity. To mitigate this bottleneck, we propose Dyna-DINO: Efficient ViT Distillation Via Adaptive Representation Anchoring, a training curriculum for ViT feature-based knowledge distillation. By utilizing the teacher's intermediate feature maps as a sequence of progressively more difficult targets, our curriculum allows the student to build a foundational representation before tackling higher-level abstractions. Our results demonstrate that this paradigm significantly accelerates convergence through adaptive difficulty selection across various student model sizes and dataset scales. With our curriculum, the Dyna-DINO distilled ViT-S achieves 90.1% accuracy on ImageNet-100, a +12.24% improvement compared with baseline. On ImageNet-1K, Dyna-DINO achieves +3.9% and +6.09% improvement for the instance retrieval task on the Oxford and Paris datasets, +1.93% improvements on semantic segmentation task, as well as meaningful performance gain on classification task. Furthermore, the curriculum enables 25.1% savings in training FLOPs and 21% savings in training time on ImageNet-100 by implementing early-stopping for teacher inference during the initial stages of training. Code is available at https://github.com/KevinZ0217/Dyna-DINO

Jiaqi Zhang, Ashton Lee, Anthony Wong +3

Brown University · Rice University

Knowledge Distillation Dataset Distillation Vision Transformer Imagenet Teacher Efficiency

Jun 17, 2026cs.LG

Compute Efficiency and Serial Runtime Tradeoffs for Stochastic Momentum Methods

Stochastic momentum methods such as heavy ball (HB), Nesterov momentum, and variants of Accelerated SGD (ASGD) [Kidambi et al., 2018] are widely used in modern training, but their stochastic benefits depend on two distinct quantities: serial runtime, the number of iterations needed to reach a target accuracy, and compute efficiency (CE), the inverse total gradient-query or FLOP cost. Larger batches reduce serial runtime without hurting CE only when the contraction gap grows linearly with batch size. We study stochastic HB and ASGD for consistent linear regression with Gaussian covariates and prove finite-dimensional, discrete-time lower bounds on their batch-size tradeoffs. Our first result shows that HB does not improve the CE frontier over SGD for arbitrary spectra; rather, it preserves SGD-level CE over a larger batch-size window, allowing larger batches to reduce serial runtime until HB reaches its deterministic accelerated scale. This window can be a factor

\sqrtκ

larger than the SGD critical batch size. For ASGD, the picture is more spectrum-dependent: for rapidly decaying power-law spectra, ASGD improves small-batch CE over HB/SGD, but as batch size grows it trades this CE advantage for improved serial runtime. Synthetic linear-regression experiments verify these qualitative regimes, including near-overlap of ASGD and HB for slowly decaying spectra and the predicted CE--serial tradeoff for rapidly decaying spectra.

Depen Morwani, Alexandru Meterez, Pranav Nair +1

1Harvard University · 2Kempner Institute at Harvard University · †: Work done while at Harvard.

Stochastic Gradient Descent Momentum Stochastic Gradient Descent Batch Efficiency Trade-Off

Jun 15, 2026cs.CL

Surpassing Scale by Efficiency: A Compact 135M Parameter Foundational LLM Natively Adapted for the Bangla Language

While the NLP landscape is dominated by multi-billion parameter architectures, their deployment in low-resource, non-Latin scripts remains computationally prohibitive for edge configurations, mobile systems, and decentralized local hardware. This paper presents bangla-smollm-135m, a highly compact 135-million parameter decoder-only foundational model engineered explicitly for high-efficiency language modeling in the Bangla script. By leveraging a deterministic intersect-and-append token merging strategy between TituLLMs and SmolLM2-135M, the model overcomes subword script fragmentation without destabilizing early pretrained parameter states. In zero-shot multi-task benchmark evaluations (PIQA_bn, OpenBookQA_bn, CommonsenseQA_bn, and Bangla_MMLU), bangla-smollm-135m matches or outperforms models twice its size (Gemma-3-270m) and achieves parity with models in the 1B parameter tier. The model is available at rnnandi/bangla-smollm-135m

Rabindra Nath Nandi

Independent Researcher

Bangla Small Large Language Models Subword Tokenization Efficiency

Jun 12, 2026cs.SD

Efficiency-Performance Trade-offs in Neural Speaker Diarization via Structured Pruning and Low-Bit Quantization

Streaming speaker diarization is crucial for time-critical medical dispatch, but deploying it on resource-constrained hardware requires smaller, faster models. Using SIMSAMU, a dataset of simulated medical-dispatch conversations, we evaluate streaming behavior before compressing the segmentation model with pruning and low-bit quantization. We characterize performance across a range of streaming latency budgets and find that additional buffering is not consistently beneficial, while very low-latency operating points can substantially degrade performance. Our study shows that model compression trades performance for memory footprint, and we highlight an operating point where FP16 reduces model size by half with essentially unchanged real-time factor, at a cost of a 40% relative DER increase against the baseline. This work characterizes the trade-offs for real-time deployment and contributes to speech technology that can enable reliable human communication in time-critical contexts.

Rishit Chatterjee, Tahiya Chowdhury

Department of Computer Science, Colby College, Waterville, Maine, United States

Speaker Diarization Neural Speech Codecs Streaming Structured Pruning Trade-Off Emergency Departments+1

Jun 9, 2026cs.LG

Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey

Resource constraints increasingly determine what can be trained, fine-tuned, and deployed in large language models (LLMs), yet efficiency is often studied through isolated techniques rather than as an interacting system of limits. This survey adopts a constraint-centric perspective and organizes recent progress around three coupled bottlenecks: data efficiency (what to train on), memory efficiency (how to fit training), and compute budget awareness (when and where to spend FLOPs). On the data axis, we review selection and pruning methods that maximize learning per token, ranging from scalable proxy signals based on learning dynamics to gradient- and influence-based scoring, as well as difficulty-aware and curriculum-style strategies. We highlight emerging evidence that different notions of good data dominate in different regimes, implying that optimal subsets depend on the task objective and resource budget rather than being universal. On the systems side, we show that GPU memory, not raw compute, is often the dominant bottleneck in fine-tuning, and that effective scaling requires jointly reducing weight storage, optimizer states, and activation memory rather than optimizing any single component in isolation. Beyond memory, we frame training and inference as compute-governed processes in which optimization, data selection, and decoding must explicitly account for finite FLOP budgets. We review evidence for compute-optimal allocation and stopping rules, where computation should be halted or reallocated once marginal performance gains fall below a budget-dependent threshold. Together, these results unify compute-aware data selection, scaling laws, and adaptive inference under a common principle of resource-conditioned decision-making.

Vanessa Schmidt, Huy Hoang Nguyen, Cédric Jung +2

Chair of Information Theory and Data Analytics (INDA), RWTH Aachen University, 52074 Aachen, Germany · AIT Austrian Institute of Technology GmbH, 1210 Vienna, Austria · Automation and Control Institute, Technische Universität Wien (TUW), 1040 Vienna, Austria

Alignment-Aware Selection Large Language Model Training Bounded-Memory Peak Memory Efficiency

Jun 7, 2026cs.LG

Deep Active Re-Labeling: Toward Noise-Resilient Annotation Efficiency

While Deep Active Learning (DAL) effectively reduces human annotation costs, its efficacy is constrained by human annotation errors. This is because the data sampled for active learning is assumed to be highly informative for training. When human annotators introduce errors into this informative data at a certain rate, the active learning performance drops significantly and, in some cases, even exhibits worse outcomes than passive learning. In this paper, we first analyze the impact of human annotation errors in the DAL setting. Then we propose a framework to address the human annotation noise problem for DAL. Informed by human learning patterns, the core idea of our proposed solution involves allocating a portion of the human annotation budget to re-annotate data that has already been labeled. Previous theoretical work suggests that when the model possesses a certain level of ability to identify potentially noisy data, even re-labeling a small fraction of the data can effectively remove noise from the active training set. To achieve this, we implement two active noise sampling strategies to detect noise under different circumstances and allocate a part of the annotation budget to re-annotate these instances. Our approach imbues active learning with a revisiting and introspective behavior. Our experiments demonstrate that, under the same annotation budget, our method is more data-efficient and yields a relatively noise-free annotation dataset in the end.

Md Abdullah Al Forhad, Weishi Shi

Active Machine Learning Lab · Learning · Language · Vision (LLaVi) Lab · Department of Computer Science and Engineering +1

Noisy Labels Human Annotations Efficiency Introspection Adapters

May 29, 2026cs.LG

A Context-Aware Middleware for Medical Image Based Reports: An approach based on image feature extraction and association rules

This work proposes a context-aware middleware for medical workflow organization and efficiency improvement. In hospitals, laboratories and teleradiology companies, each physician or technician is specialized in a specific kind of diagnosis or analysis. Therefore, certain types of medical images are often forwarded to a certain physician or a certain group. This forwarding is time consuming. That is, repeatedly deciding who would be the best physician, whether he is available at a certain moment given a certain context is exhaustive and may be very inefficient. Thus, the proposed middleware has the ability to process and collect data from images analyzed by each medical staff. Based on the collected data and current clinical context, the middleware is able to infer who would be the best fit staff to receive a certain incoming medical image.

Erick O. Rodrigues, Jose Viterbo, Aura Conci +1

Department of Computer Science Universidade Federal Fluminense Niter6i, Rio de Janeiro · Departament of Mathematics & Statistics, York University Keele St 4700, Toronto, ON M3J IP3, Canada

Real-World Clinical Workflows Medical Images Context-Awareness Medical Imaging Datasets Radiology Report Generation Efficiency

May 22, 2026cs.RO

Balancing Accuracy and Efficiency: Adaptive Dynamics Orchestration for Model Predictive Control

Model Predictive Control (MPC) for autonomous navigation faces a fundamental trade-off between model accuracy and real-time efficiency. High-fidelity dynamics models can accurately predict complex vehicle-terrain interactions during trajectory rollouts, but incur significant computational cost, increasing inference latency and reducing control frequency. Conversely, lightweight models enable fast updates and dense sampling, yet may produce erroneous predictions under safety-critical conditions, potentially leading to catastrophic failures such as vehicle rollover. To address this trade-off, we propose Adaptive Dynamics Orchestration (ADO), a framework that dynamically selects the most appropriate dynamics model for the current navigation context. ADO maintains a library of models spanning diverse accuracy-efficiency profiles and continuously refines terrain-conditioned performance estimates using residual errors from online counterfactual rollouts, where executed control actions are replayed across the model library to assess predictive discrepancy. These estimates guide model selection in real time, balancing computational efficiency and predictive accuracy. Real-world experiments on an off-road ground robot demonstrate that ADO significantly reduces modeling error compared to a fixed low-latency baseline, while approaching the accuracy of the highest-fidelity model without incurring its computational cost, resulting in more reliable and effective navigation in challenging terrain.

Francesco Cancelliere, Aniket Datar, Giovanni Muscato +1

Department of Electrical, Electronic and Computer Engineering (DIEEI), University of Catania, Italy · Department of Computer Science, George Mason University, USA

Model Predictive Control Autonomous Navigation Robust Trajectory Trajectory Generation Efficiency

May 21, 2026cs.AI

CLORE: Content-Level Optimization for Reasoning Efficiency

Reinforcement learning post-training has improved the reasoning ability of large language models, but often produces unnecessarily long, repetitive, or semantically opaque reasoning traces. Existing efficient reasoning methods mainly regulate response length through explicit budgets or length-aware rewards, leaving intermediate reasoning content weakly supervised. We propose CLORE, a content-level optimization framework that improves reasoning efficiency by editing correct on-policy rollouts. CLORE uses an external augmentation model to delete repetitive segments, illegible or task-irrelevant content, and superfluous reasoning after the solution is established, while preserving the final answer. The resulting augmented--original pairs are optimized with an auxiliary reference-free DPO objective alongside standard policy-gradient training. By restricting augmentation to correct trajectories and performing local deletion, CLORE keeps edited rollouts close to the policy distribution and mitigates off-policy mismatch. Experiments on DeepSeek-R1-Distill-Qwen-7B and Qwen2.5-Math-7B across five mathematical reasoning benchmarks show that CLORE improves the accuracy--efficiency trade-off and remains compatible with GRPO, DAPO, Training Efficient, and ThinkPrune. Content-level analyses further show that CLORE reduces repetitive reasoning, illegible content, and post-answer exploration, supporting content-level supervision as a complementary direction to length-level control.

Yuyang Wu, Qiyao Xue, Guanxing Lu +4

Carnegie Mellon University · University of North Carolina, Chapel Hill · University of Pittsburgh +1

Reasoning Skills Efficiency

May 21, 2026cs.AI

Planning in the LLM Era: Building for Reliability and Efficiency

Growing attention to intelligent agents has put a spotlight on one of their central capabilities: planning. Early attempts to leverage large language models (LLMs) for planning relied on single-shot plan generation, followed by hybrid approaches that coupled LLMs with limited external search. These methods, unsound and incomplete by their very nature, often require substantial resources without yielding better solutions on unseen problems. As the limitations of LLMs become clearer, recent work has shifted toward using them at solution construction time -- generating symbolic solvers for a family of problems that can be verified and then used efficiently at inference time. This trend reflects the growing need for agents that are both reliable and resource-efficient. It also offers a path towards generating maintainable planners with minimal dependence on language models at inference time. In this paper, we argue that this shift reflects a broader realignment of the planning field in the LLM era. We examine three major categories of planner-generation methods, discuss their current limitations, and outline research steps towards a more reliable and efficient LLM-based generation of planners.

Michael Katz, Harsha Kokel, Kavitha Srinivas +1

IBM Research

Large Language Model Planning Classical Planning Planning Artificial Intelligence Agents Efficiency

May 20, 2026cs.DC

Instant GPU Efficiency Visibility at Fleet Scale

We present Overall FLOP Utilization (OFU), a hardware-level, precision-agnostic GPU efficiency metric for AI workloads on HPC systems, derived from two on-chip performance counters: Tensor Pipe Activity and SM clock frequency. OFU requires no application instrumentation and works across GPU generations and numeric precisions. We characterize five properties of the OFU approximation -- tile quantization, floating-point precision scaling, clock sampling noise, Tensor Core clock domains, and non-tensor undercounting -- through controlled GEMM experiments on H100 and GB200 across FP16, TF32, FP8, and NVFP4. After tile-quantization correction, OFU predicts application-level MFU to within <=2 percentage points. Against 608 production training jobs, OFU achieves r = 0.78 correlation with application-level MFU and surfaces two framework-level FLOPs miscalculations. Deployed across large-scale GPU fleets, OFU has detected a 2.5x efficiency regression and tracked precision-dependent utilization changes in mixed-precision pretraining. Our evaluation and operational experience suggest OFU is a practical, deployment-ready complement to application-level MFU for continuous fleet-wide efficiency monitoring.

Connor Pedersen, Dong H. Ahn, Michel Migdal +2

NVIDIA

Graphics Processing Unit Resources High-Performance Computing Floating-Point Efficiency

May 17, 2026cs.CR

LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails

Guardrails are a critical safety layer for modern AI systems, but their operating regime is changing. As LLMs are deployed as customized assistants, safety policies are increasingly specified at inference time by users, organizations, or regulatory contexts. This makes safety enforcement fundamentally dynamic: the guardrail should adapt to changing safety policies without retraining. Yet this requirement creates a fundamental tension: faithfully judging complex policy contexts demands reasoning capability, while practical deployment requires low-latency responses. We introduce Latent Policy Guardrail (LPG), a guardrail framework that learnssemantic latent deliberation over dynamic policies. LPG compresses the internal deliberation needed for intent interpretation and policy grounding into continuous states supervised by decision-relevant semantics. At inference time, it generates only a compact verdict anchored to the violated policy clauses, preserving auditability while avoiding the latency of explicit reasoning. Across policy guardrail benchmarks, LPG-4B reaches 84.5% average safety accuracy and 77.9% F1 by compressing deliberation into just 10 latent tokens, outperforming the strongest dynamic baseline while running roughly 11 times faster than Qwen3-4B-Thinking under the single-sample evaluation setup. Code and data are available at https://github.com/SaFo-Lab/Latent_Policy_Guard.

Nanxi Li, Zhengyue Zhao, Chaowei Xiao

Johns Hopkins University

Streaming Guardrails Large Language Model Policy Optimization Deliberation Efficiency

May 14, 2026cs.LG

Enjoy Your Layer Normalization with the Computational Efficiency of RMSNorm

Layer normalization (LN) is a fundamental component in modern deep learning, but its per-sample centering and scaling introduce non-negligible inference overhead. RMSNorm improves efficiency by removing the centering operation, yet this may discard benefits associated with centering. This paper propose a framework to determine whether an LN in an arbitrary DNN can be replaced by RMSNorm without changing the model function. The key idea is to fold LN's centering operation into upstream general linear layers by enforcing zero-mean outputs through the column-centered constraint (CCC) and column-based weight centering (CBWC). We extend the analysis to arbitrary DNNs, define such LNs as foldable LNs, and develop a graph-based detection algorithm. Our analysis shows that many LNs in widely used architectures are foldable, enabling exact inference-time conversion and end-to-end acceleration of 2% to 12% without changing model predictions. Experiments across multiple task families further show that, when exact equivalence is partially broken in practical training settings, our method remains competitive with vanilla LN while improving efficiency.

Yuxin Guo, Yihao Yue, Yunhao Ni +4

State Key Laboratory of Complex and Critical Software Environment (SKLCCSE), Beihang University, Beijing, China · Hangzhou International Innovation Institute, Beihang University, Hangzhou, China

Batch Normalization Neural Network Inference Layer-Wise Modern Deep Networks Efficiency Structural Constraints

May 13, 2026cs.SE

CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing

Code agents must both reason over long-horizon repository state and obey strict tool-use protocols. In paired Instruct/Thinking checkpoints, these capabilities are complementary but misaligned. The Instruct model is concise and tool-disciplined, whereas the Thinking model offers stronger planning and recovery behavior but often over-deliberates and degrades agent performance. We present CRANE (Constrained Reasoning Injection for Code Agents via Nullspace Editing), a training-free parameter-editing method that treats the Thinking-Instruct delta as a directional pool of candidate reasoning edits for the Instruct backbone. CRANE combines magnitude thresholding to denoise the delta, a Conservative Taylor Gate to retain edits that are jointly beneficial for reasoning transfer and tool-use preservation, and Graduated Sigmoidal Projection to suppress format-critical update directions. By merging paired Instruct and Thinking checkpoints, CRANE delivers strong gains over either individual model while preserving Instruct-level efficiency: on Roo-Eval it achieves pass1 of 66.2% (+19.5%) for Qwen3-30B-A3B and 81.5% (+8.7%) for Qwen3-Next-80B-A3B; on SWE-bench-Verified it resolves up to 14 additional instances at both scales (122/500 and 180/500); and on Terminal-Bench v2 it improves pass1/pass5 by up to 2.3%/7.8%, reaching 7.6%/17.9% and 14.8%/30.3%, respectively, consistently outperforming alternative merging strategies across all three benchmarks.

Mingzhi Zhu, Michele Merler, Raju Pavuluri +1

Rensselaer Polytechnic Institute Troy, NY 12180 · IBM Research Yorktown Heights, NY 10598

Coding Agents Efficiency

May 13, 2026cs.LG

The Efficiency Gap in Byte Modeling

Modern language models have historically relied on two dominant design choices: subword tokenization and autoregressive (AR) ordering. These design decisions bake in priors that dictate a model's learning. Recently, two alternative paradigms have challenged this: byte-level modeling, which bypasses static statistically-derived token vocabularies, and masked diffusion modeling (MDM), which conducts parallel, non-sequential generation. Their intersection represents a fully end-to-end modality-agnostic generative prototype; however, removing these structural priors incurs a significant computational cost. In this work, we investigate this cost through a compute-matched scaling study. Our results reveal that the performance penalty of byte modeling is not uniform; across scale, the scaling overhead of byte modeling is worse for MDM than for AR. We hypothesize that this disparity stems from context fragility: while AR's stable causal history allows models to naturally rediscover subword patterns, the MDM objective destroys the local contiguity required to efficiently resolve semantics from raw bytes. Our findings from controlled permutation experiments suggest that future modality-agnostic designs must incorporate alternative structural biases to maintain viable scaling trajectories in the byte regime.

Celine Lee, Jing Nathan Yan, Chen Liang +9

1Google DeepMind · 2Work done while at Google DeepMind · Department of Computer Science, Cornell University.

Model Size Downstream Fine-Tuning Diffusion Models Efficiency

May 12, 2026stat.ML

Keeping Score: Efficiency Improvements in Neural Likelihood Surrogate Training via Score-Augmented Loss Functions

For stochastic process models, parameter inference is often severely bottlenecked by computationally expensive likelihood functions. Simulation-based inference (SBI) bypasses this restriction by constructing amortized surrogate likelihoods, but most SBI methods assume a black-box data generating process. While these surrogates are exact in the limit of infinite training data, practical scenarios force a strict tradeoff between model quality and simulation cost. In this work, we loosen the black-box assumption of SBI to improve this tradeoff for structured stochastic process models. Specifically, for neural network likelihood surrogates trained via probabilistic classification, we propose to augment the standard binary cross-entropy loss with exact score information

\nabla_θ\log p(x \mid θ)

and adaptive weighting based on loss gradients. We evaluate our approach on case studies involving network dynamics and spatial processes, demonstrating that our method improves surrogate quality at a drastically lower computational cost than generating more training data. Notably, in some cases, our approach achieves downstream inference performance equivalent to a 10x increase in training data with less than a 1.1x increase in training time.

Alexander Shen, Mikael Kuusela

Department of Statistics and Data Science Carnegie Mellon University Pittsburgh, PA 15213

Surrogates Uncertainty Score Loss Function Cross-Entropy Losses Stochastic Processes Scores+1

May 12, 2026cs.LG

Understanding Sample Efficiency in Predictive Coding

Predictive Coding (PC) is an influential account of cortical learning. Much of recent work has focused on comparing PC to Backpropagation (BP) to find whether PC offers any advantages. Small scale experiments show that PC enables learning that is more sample efficient and effective in many contexts, though a thorough theoretical understanding of the phenomena remains elusive. To address this, we quantify the efficiency of learning in BP and PC through a metric called ``target alignment'', which measures how closely the change in the output of the network is aligned to the output prediction error. We then derive and empirically validate analytical expressions for target alignment in Deep Linear Networks. We show that learning in PC is more efficient than BP, which is especially pronounced in deep, narrow and pre-trained networks. We also derive exact conditions for guaranteed optimal target alignment in PC and validate our findings through experiments. We study full training trajectories of linear and non-linear models, and find the predicted benefits of PC persist in practice even when some assumptions are violated. Overall, this work provides a mechanistic understanding of the higher learning efficiency observed for PC over BP in previous works, and can guide how PC should be parametrised to learn most effectively.

Gaspard Oliviers, Elene Lominadze, Rafal Bogacz

Nuffield Department of Clinical Neurosciences, University of Oxford, United Kingdom · MRC Centre of Research Excellence in Restorative Neural Dynamics, United Kingdom

Predictive Coding Deep Network Human Visual Cortex Efficiency

May 11, 2026cs.CV

Increasing the Efficiency of DETR for Maritime High-Resolution Images

Maritime object detection is critical for the safe navigation of unmanned surface vessels (USVs), requiring accurate recognition of obstacles from small buoys to large vessels. Real-time detection is challenging due to long distances, small object sizes, large-scale variations, edge computing limitations, and the high memory demands of high-resolution imagery. Existing solutions, such as downsampling or image splitting, often reduce accuracy or require additional processing, while memory-efficient models typically handle only limited resolutions. To overcome these limitations, we leverage Vision Mamba (ViM) backbones, which build on State Space Models (SSMs) to capture long-range dependencies while scaling linearly with sequence length. Images are tokenized into sequences for efficient high-resolution processing. For further computational efficiency, we design a tailored Feature Pyramid Network with successive downsampling and SSM layers, as well as token pruning to reduce unnecessary computation on background regions. Compared to state-of-the-art methods like RT-DETR with ResNet50 backbone, our approach achieves a better balance between performance and computational efficiency in maritime object detection.

Tinsae Yehuala, Hao Cheng, Ville Lehtola

Dept. of Earth Observation Science, ITC Faculty, University of Twente, Enschede, The Netherlands.

Ship Detection Detection Transformer Efficiency

May 11, 2026cs.LG

Balancing Efficiency and Fairness in Traffic Light Control through Deep Reinforcement Learning

Urban traffic congestion presents a significant challenge for modern cities, which impacts mobility and sustainability. Traditional traffic light control systems often fail to adapt to dynamic conditions, leading to inefficiencies. This paper proposes a novel deep reinforcement learning agent for traffic light control that addresses this limitation by explicitly integrating fairness considerations for both vehicular and pedestrian traffic. Unlike prior work, our approach dynamically balances these flows based on real-time demand, moving beyond systems focused solely on vehicles. Experimental results demonstrate that our agent effectively reduces congestion while ensuring equitable service for both the categories of road users. This research contributes to a practical and adaptable solution for intelligent traffic management within the framework of smart cities, paving the way for more efficient and inclusive urban mobility.

Matteo Cederle, Giacomo Scatto, Gian Antonio Susto

University of Padova, Italy

Traffic Signal Control Intelligent Transportation Urban Mobility Algorithmic Fairness Efficiency

May 10, 2026cs.LG

Efficient LLM Reasoning via Variational Posterior Guidance with Efficiency Awareness

Although large language models rely on chain-of-thought for complex reasoning, the overthinking phenomenon severely degrades inference efficiency. Existing reinforcement learning methods compress reasoning chains by designing elaborate reward functions, which renders high-quality samples extremely sparse in the exploration space and creates a sampling bottleneck for the prior policy. Inspired by cognitive science, we theoretically prove that a posterior distribution guided by reference answers achieves higher expected utility than the prior distribution, thus capable of breaking through the sampling bottleneck of high-quality samples. However, the posterior distribution is unavailable during inference. To this end, we formalize efficient reasoning as a variational inference problem and introduce an efficiency-aware evidence lower bound as the theoretical foundation. Based on this, we propose the VPG-EA framework. It adopts a parameter-shared dual-stream architecture to instantiate both the posterior distribution and the prior policy; after filtering out pseudo-efficient paths via cross-view evaluation, it unidirectionally transfers the posterior's efficient patterns to the prior policy through variational distillation. Experiments on DeepSeek-R1-Distill-Qwen-1.5B and 7B scales demonstrate that VPG-EA improves the comprehensive efficiency metric epsilon cubed by 8.73% and 12.37% over the strongest baselines on each model size, respectively.

Zizhao Chen, Yuying Li, Siting Lin +1

Guangdong University of Foreign Studies, Guangzhou, China.

LLM Reasoning Strategies Efficient Inference Chain-of-Thought Reasoning Efficiency Distribution Matching Distillation

May 7, 2026cs.LG

Multi-Objective Multi-Agent Bandits: From Learning Efficiency to Fairness Optimization

We study multi-objective multi-agent multi-armed bandits (MO-MA-MAB) under stochastic rewards, where agents observe heterogeneous reward vectors and communicate over time-varying graphs. We formulate this emerging problem setting to address \emph{efficient learning}, measured by Pareto regret, and incorporate \emph{fair learning} as an additional goal, captured via social welfare. To measure efficiency, we formulate Pareto regret and develop \textsc{Pareto UCB1 Gossip}, whose novel exploration radius explicitly separates statistical uncertainty in Pareto-based inference from consensus error. To express the fairness constraint, we formulate a Nash Social Welfare objective over preference-scalarized rewards and propose \textsc{Simulated NSW UCB Gossip}, which integrates preference-based reward simulation, gossip-based utility estimation, and UCB-style exploration. We prove that \textsc{Pareto UCB1 Gossip} achieves

\mathcal{O}(\log T)

regret and an instance-independent rate of

\mathcal{O}(\sqrt{T})

, while \textsc{Simulated NSW UCB Gossip} achieves an instance-independent regret bound of

\mathcal{O}(T^{3/4})

. This separation reveals the cost of imposing the fairness constraint to our efficiency objective: fairness limits information aggregation and slows convergence. Experiments show that our methods consistently outperform baselines, improving performance by approximately

100\%

and

50\%

in the efficiency and fairness settings, respectively.

John Wang, Mengfan Xu

University of Massachusetts Amherst

Stochastic Multi-Armed Bandits Game Theory Algorithmic Fairness Gossip Efficiency

May 7, 2026cs.MA

Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs

Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes. Highly structured methods rely on fixed roles, pipelines, or task decompositions assigned a priori. In contrast, fully unstructured teams enable adaptability and exploration but suffer from inefficiencies such as error propagation, inter-agent conflicts, and wasted resources (measured in time, tokens, or file operations). We introduce Language Agent Teams for Task Evolution (LATTE), a framework for coordinating LLM teams inspired by distributed systems, where processors must operate under partial observability and communication constraints. In LATTE, a team of agents collaboratively construct and maintain a shared, evolving coordination graph which encodes sub-task dependencies, individual agent assignment, and the current state of sub-task progress. This protocol maintains consistency while empowering agents to dynamically allocate work, adapt coordination, and discover new tasks. Across multiple collaborative tasks and a variety of base models, we demonstrate how LATTE reduces token usage, wall-clock time, communication, and coordination failures (e.g. file conflicts and redundant outputs) while matching or exceeding the accuracy of standard designs including MetaGPT, decentralized teams, top-down Leader-Worker hierarchies, and static decompositions.

Elizabeth Mieczkowski, Alexander Ku, Tiwalayo Eisape +5

Princeton University · University of Cambridge · MIT +1

Multi-Agent Coordination Efficiency

May 4, 2026cs.AI

First-Order Efficiency for Probabilistic Value Estimation via A Statistical Viewpoint

Probabilistic values, including Shapley values and semivalues, provide a model-agnostic framework to attribute the behavior of a black-box model to data points or features, with a wide range of applications including explainable artificial intelligence and data valuation. However, their exact computation requires utility evaluations over exponentially many coalitions, making Monte Carlo approximation essential in modern machine learning applications. Existing estimators are often developed through different representation strategies, including weighted averages, self-normalized weighting, regression adjustment, and weighted least squares. Our key observation is that these seemingly distinct constructions share a common first-order expansion, in which the leading term is determined by the sampling law and a working surrogate function. This first-order representation yields an explicit expression for the leading mean squared error (MSE), which characterizes how the sampling law and the surrogate jointly determine statistical efficiency. Guided by this criterion, we propose an Efficiency-Aware Surrogate-adjusted Estimator (EASE) that directly chooses the sampling law and surrogate to minimize the first-order MSE. We demonstrate that EASE consistently outperforms existing estimators for various probabilistic values.

Ziqi Liu, Kiljae Lee, Yuan Zhang +1

Department of Statistics & Data Science, Carnegie Mellon University. · Department of Statistics, The Ohio State University.

Probabilistic Model Machine Learning Surrogates Empirical Bayes Statistical Inference Value Monte Carlo+2

May 2, 2026cs.AI

Multi-Agent Reasoning Improves Compute Efficiency: Pareto-Optimal Test-Time Scaling

Advances in inference methods have enabled language models to improve their predictions without additional training. These methods often prioritize raw performance over cost-effective compute usage. However, computational efficiency is key for real-world applications with resource constraints. We provide a systematic analysis of the inference scaling strategies self-consistency, self-refinement, multi-agent debate, and mixture-of-agents, to study their computational performance tradeoffs. We evaluate methods on two reasoning benchmarks (MMLU-Pro, BBH) and include extensive parameter configurations (e.g., scaling the number of parallel predictions, agents, and debate rounds) across different model sizes. Across 34 configurations and over 100 evaluations, we compute the Pareto-optimal front to select methods that achieve the best accuracy with the lowest computational budget. Notably, inference scaling improves accuracy by up to +7.1% points over chain-of-thought at the highest evaluated budgets (20x the CoT compute budget) on MMLU-Pro. With an equal computing budget, debate and mixture-of-agents outperform self-consistency by 1.3% and 2.7% points, respectively. While self-consistency saturates earlier, multi-agent gains persist, particularly on more complicated tasks. We identify a simple multi-agent design guideline: mixture-of-agents is most efficient when the number of parallel generations exceeds the number of sequential aggregations.

Florian Valentin Wunderlich, Lars Benedikt Kaesberg, Jan Philip Wahle +2

University of Göttingen, Germany

Test-Time Scaling Multi-Agent Reasoning Reasoning Benchmark Multi-Agent Debate Efficiency Self-Consistency

May 1, 2026cs.IR

Intelligent Elastic Feature Fading: Enabling Model Retrain-Free Feature Efficiency Rollouts at Scale

Large-scale ranking systems depend on thousands of features derived from user behavior across multiple time horizons. Typically requires model retraining -- resulting in long iteration cycles (3--6 months), substantial GPU resource consumption, and limited rollout throughput. We introduce Intelligent Elastic Feature Fading (IEFF), a production infrastructure system that enables retrain-free feature efficiency rollouts by elastically controlling feature coverage and distribution at serving time. IEFF supports incremental feature coverage adjustments while models adapt through recurring training, eliminating dependencies on explicit retraining cycles. The system incorporates strict safety guardrails, reversibility mechanisms, and comprehensive monitoring to ensure stability at scale. Across multiple production use cases, IEFF accelerates efficiency-related rollouts by 5

\times

, eliminates retraining-related GPU overhead, and enables faster capacity recycling. Extensive offline and online experiments demonstrate that gradual feature fading prevents 50--55% of online performance degradation compared to abrupt feature removal, while maintaining stable model behavior. These results establish elastic, system-level feature fading as a practical and scalable approach for managing feature efficiency in modern industrial ranking systems.

Jieming Di, Xiaoyu Chen, Ying She +21

Meta · USA

Retraining Parallel Rollouts Real-World Content Recommendation Problem Efficiency Autoregressive Rollout

Apr 18, 2026cs.CV

Vision-Based Human Awareness Estimation for Enhanced Safety and Efficiency of AMRs in Industrial Warehouses

Ensuring human safety is of paramount importance in warehouse environments that feature mixed traffic of human workers and autonomous mobile robots (AMRs). Current approaches often treat humans as generic dynamic obstacles, leading to conservative AMR behaviors like slowing down or detouring, even when workers are fully aware and capable of safely sharing space. This paper presents a real-time vision-based method to estimate human awareness of an AMR using a single RGB camera. We integrate state-of-the-art 3D human pose lifting with head orientation estimation to ascertain a human's position relative to the AMR and their viewing cone, thereby determining if the human is aware of the AMR. The entire pipeline is validated using synthetically generated data within NVIDIA Isaac Sim, a robust physics-accurate robotics simulation environment. Experimental results confirm that our system reliably detects human positions and their attention in real time, enabling AMRs to safely adapt their motion based on human awareness. This enhancement is crucial for improving both safety and operational efficiency in industrial and factory automation settings.

Maximilian Haug, Christian Stippel, Lukas Pscherer +5

Fraunhofer Austria Research GmbH, Vienna, Austria · Fraunhofer Austria Research GmbH, 1040 Vienna, Austria · Computer Vision Lab, TU Wien, Vienna, Austria +4

Human-Robot Collaboration Warehouse Automation Safety Claims Efficiency

Mar 26, 2026cs.CL

Do LLMs Know What They Know? Measuring Metacognitive Efficiency with Signal Detection Theory

Standard evaluation of LLM confidence relies on calibration metrics (ECE, Brier score) that conflate how much a model knows (Type-1 accuracy) with how well its confidence signal tracks that knowledge (Type-2 metacognitive sensitivity). We apply Signal Detection Theory (SDT) to decompose these capacities, treating token-level normalised log-probability as a graded confidence variable and answer correctness as the state to be discriminated. We characterise the Type-2 ROC of this signal, including its unequal-variance structure via z-ROC analysis, and -- because the meta-d' efficiency ratio is not well defined for open-ended QA, which lacks a two-alternative Type-1 decision -- quantify metacognitive efficiency with a model-free information measure, normalised metacognitive information (meta-I_2r). Applied to four LLMs (Llama-3-8B-Instruct, Mistral-7B-Instruct-v0.3, Llama-3-8B-Base, Gemma-2-9B-Instruct) across 224,000 factual QA trials, we find: (1) metacognitive information varies more than two-fold across models and co-varies inversely with accuracy -- the least accurate model has the most informative confidence -- though with four models this ordering cannot be separated from an error-difficulty confound, so we report it as coupling, not decoupling; (2) the confidence signal has model-specific unequal-variance structure (z-ROC slopes 0.81 to 1.18) invisible to calibration metrics; (3) metacognitive information is domain-specific, strongest in Arts & Literature for every model; (4) temperature dissociates Type-1 accuracy from metacognitive information, which stays stable while accuracy shifts. All estimates carry permutation nulls and bootstrap confidence intervals. Pre-registered; code and data public.

Jon-Paul Cacioli

Independent Researcher Melbourne, Australia

Metacognition Theory Efficiency

Mar 12, 2026cs.CL

A technology-oriented mapping of the language and translation industry: Analysing stakeholder values and their potential implication for translation pedagogy

This paper examines how value is constructed and negotiated in today's increasingly automated language and translation industry. Drawing on interview data from twenty-nine industry stakeholders collected within the LT-LiDER project, the study analyses how human value, technological value, efficiency, and adaptability are articulated across different professional roles. Using Chesterman's framework of translation ethics and associated values as an analytical lens, the paper shows that efficiency-oriented technological values aligned with the ethics of service have become baseline expectations in automated production environments, where speed, scalability, and deliverability dominate evaluation criteria. At the same time, human value is not displaced but repositioned, emerging primarily through expertise, oversight, accountability, and contextual judgment embedded within technology-mediated workflows. A central finding is the prominence of adaptability as a mediating value linking human and technological domains. Adaptability is constructed as a core professional requirement, reflecting expectations that translators continuously adjust their skills, roles, and identities in response to evolving tools and organisational demands. The paper argues that automation reshapes rather than replaces translation value, creating an interdependent configuration in which technological efficiency enables human communicative work.

María Isabel Rivas Ginel, Janiça Hackenbuchner, Alina Secară +2

Dublin City University · Ghent University · University of Vienna +2

Human Values Translation Quality Stakeholders Efficiency Pedagogical Frameworks

Jan 20, 2026cs.AI

Toward Efficient Agents: Memory, Tool learning, and Planning

Recent years have witnessed increasing interest in extending large language models into agentic systems. While the effectiveness of agents has continued to improve, efficiency, which is crucial for real-world deployment, has often been overlooked. This paper therefore investigates efficiency from three core components of agents: memory, tool learning, and planning, considering costs such as latency, tokens, steps, etc. Aimed at conducting comprehensive research addressing the efficiency of the agentic system itself, we review a broad range of recent approaches that differ in implementation yet frequently converge on shared high-level principles including but not limited to bounding context via compression and management, designing reinforcement learning rewards to minimize tool invocation, and employing controlled search mechanisms to enhance efficiency, which we discuss in detail. Accordingly, we characterize efficiency in two complementary ways: comparing effectiveness under a fixed cost budget, and comparing cost at a comparable level of effectiveness. This trade-off can also be viewed through the Pareto frontier between effectiveness and cost. From this perspective, we also examine efficiency oriented benchmarks by summarizing evaluation protocols for these components and consolidating commonly reported efficiency metrics from both benchmark and methodological studies. Moreover, we discuss the key challenges and future directions, with the goal of providing promising insights.

Xiaofang Yang, Lijun Li, Heng Zhou +12

Shanghai Artificial Intelligence Laboratory · Fudan University · University of Science and Technology of China +5

Production Agentic Systems Efficiency Learn Planning Evaluation Protocols

Nov 11, 2025cs.DC

Intelligence per Watt: Measuring Intelligence Efficiency of Local AI

Large language model (LLM) queries are predominantly processed by frontier models in centralized cloud infrastructure. Demand growth strains this paradigm faster than providers can scale. Two advances create an opportunity to rethink it: small, local LMs (<=20B active parameters) now achieve competitive performance to frontier models on many tasks, and local accelerators (e.g., Apple M4 Max) can host these models at interactive latencies. This raises the question: can local inference viably redistribute demand from centralized infrastructure? This requires measuring both whether local LMs can accurately answer real-world queries and whether they can do so efficiently on power-constrained devices (e.g., laptops). We propose intelligence per watt (IPW), task accuracy per unit of power, as a unified metric for the capability and efficiency of local inference across model-accelerator configurations. We evaluate 20+ state-of-the-art local LMs, 8 hardware accelerators (local and cloud), and 1M real-world single-turn chat and reasoning queries. For each query, we measure accuracy (local LM win rate against frontier models), energy, latency, and power. We find three key results. First, local LMs successfully answer 88.7% of these queries, with accuracy varying by domain. Second, longitudinal analysis from 2023-2025 shows IPW improved 5.3x, driven by both algorithmic and accelerator advances, with locally-serviceable query coverage rising from 23.2% to 71.3%. Third, local accelerators achieve at least 1.4x lower IPW than cloud accelerators running identical models, revealing significant headroom for local accelerator optimization. These findings demonstrate that local inference can meaningfully redistribute demand from centralized infrastructure for a substantial subset of queries, with IPW serving as the critical metric for tracking this transition.

Jon Saad-Falcon, Avanika Narayan, Hakki Orhun Akengin +12

Stanford University · Together AI

LLM Inference Optimization Efficiency Intelligence Frontier Models Interactive Learning

Oct 30, 2025cs.LG

Can machines think efficiently?

The Turing Test is no longer adequate for distinguishing human and machine intelligence. With advanced artificial intelligence systems already passing the original Turing Test and contributing to serious ethical and environmental concerns, we urgently need to update the test. This work expands upon the original imitation game by accounting for an additional factor: the energy spent answering the questions. By adding the constraint of energy, the new test forces us to evaluate intelligence through the lens of efficiency, connecting the abstract problem of thinking to the concrete reality of finite resources. Further, this proposed new test ensures the evaluation of intelligence has a measurable, practical finish line that the original test lacks. This additional constraint compels society to weigh the time savings of using artificial intelligence against its total resource cost.

Adam Winchell

Counter Turing Test Efficiency Imitation

Jul 13, 2025cs.GT

Efficiency, Feasibility, and Incentive-Awareness in Constrained Online Resource Allocation

We study the dynamic allocation of indivisible resources to strategic agents under long-term constraints, where the planner aims to maximize social welfare, satisfy multiple constraints, and elicit near-truthful reports. We find standard primal-dual methods fragile in this setting: agents easily manipulate their reports to distort dual variables, sacrificing social efficiency for individual utility. To address this, we propose the Incentive-Aware Primal-Dual (IAPD) framework. On the primal side, we integrate three components to suppress manipulation: a VCG-based payment neutralizes immediate misreporting benefits, while epoch-based lazy updates and random exploration together ensure potential future gains are outweighed by immediate penalties. On the dual side, to overcome a learning barrier due to lazy updates -- which we call the "price of incentives" -- we design a novel optimistic online learning algorithm, O-FTRL-FP. It utilizes a fixed-point oracle to resolve the circular dependency between optimistic dual variables and the resulting allocations. Ultimately, our mechanism attains

\tilde{\mathcal O}(\sqrt T)

social welfare regret, satisfies all long-term constraints, and induces a near-truthful equilibrium. It also smoothly generalizes to multi-unit multi-demand allocation problems. Notably, this

\tilde{\mathcal O}(\sqrt T)

regret near-matches the non-strategic

Ω(\sqrt T)

lower bound, demonstrating that incentive-awareness can be accommodated at nearly no cost.

Yan Dai, Negin Golrezaei, Patrick Jaillet

Operations Research Center, MIT. · Sloan School of Management, MIT. · Department of EECS, MIT.

Incentives Primal-Dual Methods Equilibrium Feasibility Efficiency

May 28, 2025cs.LG

Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders

Sparse Autoencoders (SAEs) decompose language-model activations into sparse, interpretable features, but standard encoders usually treat the latent dictionary as a flat set of independent coordinates, leaving hierarchy and feature interactions to emerge only implicitly. We propose KronSAE, a design that factorizes the latent space into heads and forms post-latent features as pairwise compositions of lower-dimensional pre-latents using mAND, a differentiable AND-like interaction. This imposes a compositional co-activation prior while remaining compatible with standard SAE objectives and variants such as TopK, Matryoshka, and Switch SAEs. KronSAE matches strong baselines on the EV-FLOPs frontier, improves interpretability of the latents, better captures the underlying correlated feature structure, and reduces encoder computational cost as an additional benefit. Code is available at https://github.com/corl-team/kronsae.

Vadim Kurochkin, Yaroslav Aksenov, Daniil Laptev +2

T-Tech

Model Activations Interpretability Efficiency