Adaptive Computation

Follow this topic Ask about this topic

Momentum

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

Jul 13Week of Sep 28

Latest papers 70

Aug 21, 2026cs.CL

Sparse Token Routing in Efficient Transformers

Efficient-transformer research often motivates token pruning and adaptive computation with the claim that not all tokens require equal computational effort. We test this claim end to end using SEWN, a two-stream Transformer that routes tokens through either lightweight or full-capacity processing using a learned gate. Across our experiments, routing introduces negligible accuracy change relative to parameter-matched baselines, while the gate's token-importance signal depends critically on how it is learned. A static lexicon-seeded prior fails a counterfactual faithfulness test on BoolQ, whereas a fully contextual gate achieves highly significant separation (

p<10^{-10}

) on both evaluated tasks without changing task accuracy.

Sai Krishna Arthanari, JaeHyeong Chang, Chengzhe Sun +1

Transformer Adaptive Computation

Aug 19, 2026cs.NE

Biological-Hybrid Intelligence: A Conceptual Framework for Distributed Biological--Artificial Computation

Biological and artificial systems offer complementary forms of adaptation, learning, and computation, with advances in in-vitro neurotechnology increasingly enabling bidirectional coupling between them. As these systems become more tightly integrated, a key architectural question is how task-relevant computation should be distributed across both substrates. Yet existing biohybrid solutions optimise the biological substrate, the AI model, or their interface without explicitly addressing how such computation is allocated, reassigned, and evaluated. We introduce Biological-Hybrid Intelligence (BHI), a conceptual framework for distributing computation across adaptive biological and artificial substrates coupled through a bioelectronic interface and coordinated by an orchestrator. BHI treats both substrates as computational entities whose computational responsibilities may change during operation. BHI requires reciprocal co-adaptation and differs from systems that merely decode biological activity, stimulate a living substrate, or adapt a single component. BHI further defines three operating modes: adversarial, collaborative, and codependent, distinguished by whether the substrates compete, divide computational labour, or become mutually necessary for task performance. BHI provides a common basis for comparing computational frameworks, defining benchmarks for latency, viability, interface bandwidth, learning efficiency, and reproducibility. It also highlights governance considerations arising from reciprocal stimulation, adaptation, and data exchange. More broadly, BHI invites computer scientists to consider biological substrates as active computational resources and to ask not only how a task should be computed, but where its computation should reside. BHI therefore reframes biological-artificial integration as a system-level problem of computational allocation, coordination, and control.

Michael Taynnan Barros, Sergio Lopez Bernal, Reinhold Scherer

Adaptive Computation Heterogeneous Computing

Aug 13, 2026cs.LG

Reduced Matrix Multiplication: Input-Adaptive Matrix-Product Reduction for LLM Inference

Transformer-based language models achieve strong performance but incur substantial inference cost due to repeated high-dimensional matrix multiplications. We propose Reduced Matrix Multiplication (RMM), a training-free, input-adaptive inference method that reduces Transformer matrix products by selecting informative slices along their contraction dimensions, without modifying model weights. Under a simple retention-ratio control, RMM provides a smooth and predictable accuracy-efficiency trade-off. Across language models ranging from 1B to 70B parameters, we find that reduction tolerance depends on the model family, task, component, and retention ratio, although it often improves with model scale. Under moderate reduction, RMM remains robust across the evaluated discriminative, autoregressive generation, and long-context settings. We further show that the same principle extends to multimodal vision-language inference. Mechanistic ablations reveal a structural asymmetry within Transformers: attention-side computations are substantially more reducible than MLP components. Finally, wall-clock benchmarks with custom kernels on an NVIDIA A100 show that these computational savings can translate into practical runtime gains, especially at longer sequence lengths. Together, these results position RMM as a scalable direction for input-adaptive inference-time optimization.

Zixuan Lan, Yanhong Li, Jiawei Zhou

University of Chicago · Independent Researcher · Stony Brook University

Inference-Time Optimization LLM Inference Acceleration Adaptive Computation

Jul 27, 2026cs.AI

Exploring Budgeted Image Classification with Content-Sensitive Resource Allocation

The ever-growing adoption of Artificial Intelligence (AI) creates the need to deploy Deep Neural Networks in a variety of computational environments. We consider dynamic environments, where computational requirements are subject to change, and we pose the following question: How do we adjust the complexity of an AI classification system, in order to maximize its accuracy, while meeting changing computational constraints? We call this problem Budgeted Image Classification, and we formally formulate it as a resource allocation integer program. Given a computational budget, a batch of images, and a classification system that can make decisions with varying complexity (it has multiple decision points), we explore strategies to allocate images to decision points, in order to maximize accuracy within the available budget. The original integer program is NP-Hard, so, we propose a continuous relaxation, leading to a content-agnostic allocation strategy which assigns images to decision points without considering their particular content. We address this issue by proposing a content-sensitive strategy, that we experimentally show it leads to superior performance. We theoretically study the behavior of our strategies, deriving conditions that must be satisfied by decision points to be suitable for budgeted classification. We analyze fails cases, offering insights for future research directions.

Athanasios G. Papadopoulos

Tandon School of Engineering, New York University

Cost-Aware Inference Classification Inference-Time Compute Allocation Image Classification Adaptive Computation

Jul 23, 2026cs.LG

Learning to Access Computation: Accessibility Plasticity as a Principle of Adaptive Intelligence

Modern neural networks primarily adapt through parameter modification within predefined computational structures. While recent methods introduce modularity, conditional computation, and parameter-efficient adaptation, they generally do not distinguish computational capability from computational accessibility as separate adaptive variables. This work introduces Accessibility Plasticity, a principle of adaptive computation in which systems adapt not only by changing what computation exists, but also by reorganizing which existing computations can interact and participate. We formalize Accessibility Plasticity through a relationship-based operational realization and establish a reuse-first hierarchy of adaptation, where accessibility modification precedes more costly capability and structural changes. A proof-of-concept evaluation on sequential learning tasks shows that accessibility adaptation can reduce capability modification while maintaining comparable task performance. These results suggest accessibility as a distinct adaptive dimension and provide a foundation for future dynamic neural systems whose computational relationships evolve with changing environments.

Zhaowen Fan

Department of Computer Science, Sichuan University

Adaptive Computation

Jul 22, 2026cs.CV

Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs

Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across vision-language tasks. However, their high inference cost, arising from both the large number of input visual tokens and the heavy computation of the large language model (LLM), remains a key barrier to practical deployment. Recent work attempts to reduce the cost by adaptively optimizing individual dimensions, e.g., pruning redundant visual tokens or skipping LLM layers and heads. Nonetheless, prior approaches typically treat these dimensions independently and overlook a fundamental coupling: the available compute resources must be dynamically allocated across all dimensions based on the input content. To bridge the gap, we propose SmartVL, a unified adaptive inference framework that jointly controls vision token number and model compute capability in response to varying input contents and compute budgets. SmartVL introduces a vision-side token controller that dynamically selects informative visual tokens and an LLM-side compute controller that adaptively adjusts LLM computation. Importantly, these controllers are trained to coordinate with each other so that the overall inference cost satisfies a target budget. To allow this joint scheduling, we connect the controllers using a shared budget encoding and leverage a differentiable latency estimator for end-to-end training. This design enables SmartVL to learn cross-stage allocation strategies that adapt to both input complexity and runtime compute constraints. Experiments across multiple MLLM benchmarks demonstrate that, with joint scheduling, SmartVL consistently outperforms prior adaptive methods and achieves superior accuracy-efficiency Pareto frontiers. Project page: https://www.schaterji.io/publications/2026/jointtokencompute.

Pengcheng Wang, Zhiquan Wang, Jayoung Lee +5

Purdue University, West Lafayette, IN, USA · University of Wisconsin–Madison, Madison, WI, USA · NVIDIA, Santa Clara, CA, USA

Efficient Multimodal Inference Efficient VLM Inference Multimodal Large Language Models Multimodal Foundation Models Visual Token Pruning Adaptive Computation

Jul 22, 2026cs.CL

SLPO: Scaling Latent Reasoning via a Surrogate Policy

Reinforcement learning with verifiable rewards has become the predominant recipe for eliciting test-time scaling in explicit Chain-of-Thought reasoners. Yet this scaling path remains computationally costly, since every intermediate step must be decoded as a language token. Latent reasoning instead carries intermediate computation as continuous vectors and already matches or surpasses explicit CoT at far shorter horizons. Despite this promise, latent reasoners remain largely imitation-bound, while explicit CoT has already moved past imitation via outcome-reward RL. Latent trajectories lack a tractable per-step likelihood and an adaptive stopping interface under fixed thinking budgets, so outcome rewards cannot elicit latent test-time scaling. We introduce Surrogate Latent Policy Optimization (SLPO) to bring outcome-reward RL to autoregressive latent reasoners: an empirical surrogate policy density over latent transitions for trajectory-level credit assignment, and a correctness-supervised stopping head that outcome-reward optimization refines into a variable-horizon policy. Across continuous and soft thinking settings, SLPO improves Pass@

k

under parallel sampling and allocates longer latent computation to harder instances with higher deterministic accuracy.

Runyang You, Zhiyuan Liu, Yongqi Li +1

The Hong Kong Polytechnic University · Sichuan University · Work done as an intern at PolyU.

Reinforcement Learning RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards Continuous Latent Reasoning Adaptive Computation Latent Reasoning

Jul 19, 2026cs.LG

TAPAS: Throughput-adaptive Perception for Autonomous Systems

Autonomous systems rely on a perception module to navigate through dynamic environments. In real-world scenarios, the perception module's throughput requirements vary at runtime due to changes in scene complexity. However, existing perception strategies assume a fixed FPS and static model-to-cluster mapping, resulting in either over/under provision of throughput requirements or unnecessary energy consumption across diverse scenes. Addressing this challenge requires tightly coupled \textit{scene complexity awareness} to estimate an appropriate FPS target and \textit{dynamic model-to-cluster mapping} to deliver the required throughput at minimum energy. We propose a throughput-adaptive perception strategy for mobile/edge platforms, enabling intelligent runtime resource allocation based on varying FPS targets. We use Reinforcement Learning (RL) with RRM (Reward Reasoning Model) and a GRU (Gated Recurrent Unit) agent to orchestrate perception tasks across heterogeneous mobile/edge platforms. We evaluate TAPAS on Jetson Orin NX across KITTI and unseen nuScenes. On the \textit{KITTI} dataset's test sequences, TAPAS achieves 93-100% throughput met rate while saving energy by 76%. On the unseen \textit{nuScenes} dataset, TAPAS maintains 97% throughput met rate with 64% lower energy compared to \textit{SOTA} approaches, proving its robustness.

Aman Vyas, Vasista Kodumagulla, Zain Taufique +2

Department of Computing, University of Turku, Finland

Energy-Efficient ML Edge Computing Autonomous Driving Perception Adaptive Computation

Jul 15, 2026cs.AI

Per-Token Fixed-Point Convergence in Depth-Recurrent Transformers

A depth-recurrent transformer applies a weight-tied core a variable number of times, and prior work has shown that training with a randomized recursion count yields one checkpoint usable across a range of inference depths. We ask what such a model actually computes per token, and measure it directly. On a 135M-class model trained on FineWeb-Edu, the recurrent state converges to a per-token fixed point: mean successive-output KL divergence falls from 3.9e-1 at the second loop to 8.5e-6 by the sixteenth, and per-token state change decays in step. Crucially, this convergence is not uniform across tokens. The median token converges by loop six, while approximately 10 percent of tokens continue to update at the training-mean depth of eight, and mean convergence depth is ordered by token type (whitespace shallowest, content words deepest). This per-token variation is the central object of the paper. We show it is directly readable and that reading it outperforms learning to predict it: a training-free rule that halts each token once its output stabilizes attains uniform depth-8 quality at 4.94 average loops (a 38 percent reduction in average depth) and matches uniform depth across the average-depth range, whereas a linear router trained on convergence labels harvested from the same model requires nearly full depth and yields no reduction. The elasticity that makes this possible reproduces here as background (validation loss decreases monotonically from 3.80 at one loop to 3.20 at eight and remains stable to 32 loops). We report average depth as a FLOP proxy with a three-point wall-clock bracket rather than a realized speedup, make no FLOP-matched parity claim, and note that the allocation results are established at a single scale and seed. The complete study runs on a single RTX 4090 in approximately 100 GPU-hours.

Joe Logan

Independent researcher

Transformer Inference Recurrent Transformers Convergence Analysis Adaptive Computation

Jul 11, 2026cs.AI

CHASE: Cache-Hole-Adapted Skip Exit for Looped State-Space Language Models

Recent work on looped language models suggests that many reasoning problems benefit from greater computational depth rather than from additional independent parameters. Existing studies, however, focus almost exclusively on Transformer backbones, leaving open whether this principle also applies to state-space language models. We investigate Looped Mamba and Looped Hybrid Mamba-Transformer architectures, which repeatedly apply a shared Mamba (or hybrid) block to introduce explicit finite-depth recurrent computation. On two controlled reasoning tasks-Mano (modular-arithmetic manipulation) and p-hop induction-Looped Mamba consistently outperforms parameter-matched non-looped baselines and, in several settings, matches or exceeds non-looped models of equal effective depth. We then extend the study to language model pre-training under matched iso-parameter and iso-FLOPs protocols, which jointly disentangle the effects of parameter sharing and effective depth: looped models remain competitive on downstream benchmarks with substantially fewer distinct parameters, although deeper non-looped models retain an advantage in validation perplexity under strict iso-FLOPs comparisons. Finally, we adapt Ouro's two-stage exit gate to Looped Mamba for threshold-controlled selection among recurrent-step outputs. Executing such exits on a state-space backbone, however, leaves the recurrent state without its deeper updates, and validation perplexity then degrades severely. We therefore introduce a cache-hole adaptation that aligns continued training with skipped-state inference. At the scales studied, the adapted model keeps perplexity close to full computation and matches or exceeds full-compute exit-state selection on downstream benchmarks while executing roughly half of the recurrent steps, which translates into measured inference speedups once the prefill is compute-bound.

Zhenxuan Yu, Takeshi Kojima, Yutaka Matsuo +1

Rikkyo University · The University of Tokyo

Efficient Language Model Inference LLM Reasoning Adaptive Computation State Space Models

Jul 8, 2026cs.CC

Computing with Stochastic Oracles in AI-Augmented Computation

The Stochastic-Oracle Turing Machine (SOTM) framework models AI-augmented computation as the interaction of a probabilistic Turing machine with an oracle whose responses are drawn from context-dependent distributions. This paper studies what an SOTM can achieve under two oracle-response schemes: in a cached-response oracle, each distinct query receives one response that is reused on later calls to the same query, while in a fresh-response oracle, each call returns an independent response. In both schemes, the SOTM first computes from its input and internal random source to generate its first query, then proceeds adaptively, computing from its query-response transcript (the record of queries issued and responses received) to generate each subsequent query or produce a final output. Cached responses impose two transcript-based ceilings on achievable performance: a correct-identification ceiling governed by the total variation distance between the transcript distributions induced by the hidden states of the oracle, and an output quality ceiling equal to the expected score of the best output the SOTM can compute from the transcript. Fresh responses can raise these ceilings by allowing repeated calls to accumulate independent evidence toward correct or high-quality outputs. In the binary single-informative-query case, the error probability decreases exponentially in the number of calls to the same query at the Chernoff rate. For output quality, query-count bounds characterize threshold stopping when the score function is incorporated as part of the SOTM, and majority-based amplification bounds characterize the binary candidate-output model when it is not. Together, the results identify how response reuse, transcript information, and access to the score function determine what an SOTM can compute and at what token cost.

Jie Wang

Richard A. Miner School of Computing and Information Sciences, University of Massachusetts, Lowell, MA 01854, USA.

Oracle Complexity Adaptive Computation

Jun 25, 2026cs.CV

Forget, Anticipate and Adapt: Test Time Training for Long Videos

Test Time Training (TTT) is a mechanism in which a model adapts to an incoming test-sample by performing some self-supervised (SSL) task and updating its weights even during inference. This procedure does not require labels at test-time. This paper focuses on TTT for long-videos. A major concern with existing approaches is: 1) they perform TTT updates using a sliding window containing frames in the past, whose compute increases linearly with the size of window. This becomes computationally intractable when the videos are hours long. 2) TTT is performed even when temporally close frames look similar, thereby consuming a lot of compute. We present the Frame Forgetting Network (FFN) that: 1) operates on only three frames within the sliding window, namely the frame that exits, the current frame and the frame after that. The model still manages to retain temporal context and work for hours long-videos; 2) mathematically define a surprise metric: how much new information the incoming frame contains with respect to the past seen frame. This facilitates determining how to modify the effective window size during TTT and constitutes the core mechanism of an adaptive windowing algorithm. Additionally, we curate a dataset EpicTours containing up to 3 hour long videos of walking city-tours, whereas earlier datasets on this problem were only 5 min long. We demonstrate FFNs empirical effectiveness on dense-segmentation, video classification tasks, generalization to depth-estimation, and multi-hour long videos.

Rajat Modi, Sebastian Noel, Xin Liang +1

Institute of Artificial Intelligence, University of Central Florida

Continual Test-Time Adaptation Test-Time Training Long-Video Understanding Adaptive Computation

Jun 24, 2026cs.LG

Finding the Time to Think: Learning Planning Budgets in Real-Time RL

Deliberating takes time. In real-time settings, that time is not free. Standard reinforcement learning (RL) sidesteps this as the environment waits indefinitely for the agent's decision. Instead, we study real-time RL environments where the environment progresses while waiting for the agent's action. Building on prior real-time formalizations, we introduce variable-delay real-time RL, where the agent chooses how long to deliberate at each decision point since the environment progresses. For the planning agents we use, the right delay is state-dependent, and naively planning how long to plan can paralyze the agent. We instead approach this setting by training a lightweight gating policy on top of a planner to select state-dependent planning budgets. Across real-time Pac-Man, Tetris, Snake, Speed Hex, and Speed Go, our gating policy outperforms fixed-budget and heuristic baselines, and transfers to a real-time setup where the environment and agent run on two different GPUs.

Aneesh Muppidi, Firas Darwish, Dylan Cope +2

British Open-ended Learning and Discovery Lab (BOLD), University of Oxford · Department of Statistics, University of Oxford · VGG, University of Oxford

Reinforcement Learning Policy Learning Adaptive Computation

Jun 24, 2026cs.RO

ASSCG: Just-Right Gating over Chattering for Fast-Slow LLM Planning in Autonomous Driving

Large language models (LLMs) can improve autonomous driving planning but are costly to query online, and existing fast-slow planners often rely on hand-designed triggering rules that either over-call the slow system or call it at the wrong times. We formulate slow-system invocation as a resource-aware sequential decision problem and propose the Adaptive Slow-System Control Gate (ASSCG), which makes frame-level Query/Cache/Drop decisions to refresh, reuse, or suppress slow guidance. ASSCG uses an RWKV backbone for efficient long-horizon gating and is trained with supervised fine-tuning followed by GRPO-style compute-aware reinforcement fine-tuning. We apply ASSCG to two different fast-slow architectures: (i) AsyncDriver on nuPlan Hard20 closed-loop evaluation, where ASSCG improves score to 67.28 (+2.28) while reducing average end-to-end inference latency by 60%; and (ii) a RecogDrive-based dual system that we build by replacing its original VLM-2B module with a lightweight ViT-based fast planner and adding an LLM slow planner, evaluated on NAVSIM, where ASSCG achieves 91.4 PDMS (+0.6) and increases average speed by 25%. The project page, including video visualizations and additional results, is available at https://williamxuanyu.github.io/asscg/.

Sining Ang, Yuan Chen, Liu Haiyan +5

Institute for AI Industry Research (AIR), Tsinghua University · Department of Automation, University of Science and Technology of China · Beijing University of Aeronautics and Astronautics +1

LLM Inference Acceleration Autonomous Driving Planning Adaptive Computation

Jun 16, 2026cs.AI

Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers

Looped architectures provide an inductive bias toward learning step-by-step procedures for tasks that require compositional reasoning. The number of effective layers reached by looping determines the quality of the solution these models find. Like deep architectures, looped architectures are prone to a signal propagation problem induced by depth as the halting decision is postponed. In this paper, we address this signal propagation issue using pre-norm layers and residual scaling. Building on these architectural modifications, we propose FPRM, a Transformer-based Fixed-Point Reasoning Model that uses fixed-point convergence as an end-to-end halting mechanism in a looped architecture. We show that fixed-point halting allows FPRM to adapt its compute to task difficulty. FPRM is effective on common reasoning benchmarks, namely Sudoku, Maze, state-tracking, and ARC-AGI.

Sajad Movahedi, Vera Milovanović, Shlomo Libo Feigin +5

ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems, Tübingen AI Center · ETH Zurich · Swiss Institute of Bioinformatics +2

Recurrent Transformers Algorithmic Reasoning Adaptive Computation

Jun 16, 2026cs.LG

Learning to Refine Hidden States for Reliable LLM Reasoning

Large language models show strong reasoning ability, but their internal reasoning process can remain unstable in complex multi-step settings, where early hidden-state errors may propagate to incorrect predictions. We propose ReLAR, a reinforcement-guided latent refinement framework that iteratively updates hidden representations before decoding. ReLAR maintains a compact latent reasoning state and uses learned depth and action controllers to adaptively determine both the number and direction of refinement steps. The controllers are trained with a policy gradient objective based on step-wise likelihood improvement, enabling efficient input-dependent reasoning without explicit chain-of-thought generation. Experiments on medical, mathematical, multi-hop reasoning, and open-ended generation benchmarks show that ReLAR improves accuracy, generation quality, and reasoning stability with substantially lower inference overhead than explicit reasoning baselines.

Chia-Hsuan Hsu, Jui-Ming Yao

RL for Language Model Reasoning Efficient Language Model Reasoning LLM Reliability Implicit Reasoning in Language Models Adaptive Computation Latent Reasoning

Jun 15, 2026cs.CL

Tyler: Typed Latent Reasoning for Language Models -- When to Think, What to Compute, and How Much to Allocate

Chain-of-thought (CoT) prompting improves reasoning in large language models (LLMs) by externalizing intermediate computation as discrete text tokens, but this textual interface also introduces redundancy and inference overhead. Latent reasoning offers a promising alternative by carrying part of the computation in continuous representations. However, existing methods typically predefine when latent computation is invoked and how it is allocated during decoding, leaving a key problem unresolved: when to invoke latent computation, what type of computation to perform, and how much budget to allocate. We propose \textbf{Ty}ped \textbf{L}at\textbf{e}nt \textbf{R}easoning (Tyler), a typed and budget-aware framework for latent reasoning during autoregressive decoding. Tyler learns a policy that, at each decoding step, chooses between emitting a text token and switching to a latent computation module specialized for a particular reasoning function. Once invoked, an operator maps the current reasoning state into latent tokens that support global planning, local state updates, or reusable procedural abstraction. Across extensive experiments on three backbone LLMs, Tyler improves accuracy by up to 14.49 points over CoT and by up to 4.30 points over the strongest competing baseline. It further generalizes across diverse reasoning domains and achieves the best final-stage performance with the lowest forgetting.

Hanyu Lin, Min Cai, Jiawei Wen +1

1Shenzhen University · University of Alberta

Language Model Decoding Efficient Language Model Reasoning Continuous Latent Reasoning LLM Reasoning Adaptive Computation Latent Reasoning

Jun 5, 2026cs.AI

DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling

Recent advances in Large Reasoning Models (LRMs) demonstrate remarkable performance improvements by iteratively reflecting, exploring, and executing complex tasks, yet suffer from inefficiencies due to redundant reasoning, known as "overthinking". Existing methods to mitigate this issue either rely on static difficulty estimates or require task-specific training, and thus fail to adapt to the dynamic complexity during reasoning. In this work, we empirically show that the problem difficulty evolves dynamically throughout the reasoning process and is linearly encoded in the LRM's step-level embeddings. Building on this insight, we propose DyCon, a training-free framework that leverages latent step-level representations to explicitly model the evolving task difficulty, enabling the dynamic control of reasoning depth to mitigate the overthinking issue. Extensive experiments conducted on four models ranging from 4B to 32B, and across twelve benchmarks in math reasoning, general question answering, and coding tasks demonstrate that DyCon significantly enhances reasoning efficiency by reducing redundant steps without sacrificing accuracy or generalization. Code is available at https://github.com/yu-lin-li/DyCon.

Tengyao Tu, Yulin Li, Hui-Ling Zhen +6

Harbin Institute of Technology, Shenzhen · Zhongguancun Academy · Huawei Noah’s Ark Lab +2

Overthinking in Language Models Efficient Language Model Reasoning Efficient Language Model Inference LLM Reasoning Adaptive Computation Large Reasoning Models

May 28, 2026cs.CL

A Dual-Path Architecture for Scaling Compute and Capacity in LLMs

Looped transformers apply a shared block multiple times and have emerged as a parameter-efficient route to scaling compute in language models. However, at fixed FLOPs a looped model has strictly less capacity than a baseline transformer. We propose a novel dual-path block that can flexibly scale compute, the number of sequential operations applied to a hidden state, and capacity, the parameters available at a single step. For this we expose both axes as parallel pathways within a single layer: a deep sublayer re-applied K times with shared parameters, and a wide sublayer with an enlarged feed-forward network applied once. Independent per-token gates combine both axes and allow detailed per-token routing analyses. We show that across two FLOP budgets, our dual-path model surpasses iso-FLOP matched models on language modeling and downstream evaluations, while using fewer parameters than the baseline at matched FLOPs. The learned gates are directly interpretable and show systematic per-token allocation with function words and lexical content trend wide, while punctuation, symbols, and arithmetic tokens trend deep.

Markus Frey, Behzad Shomali, Joachim Koehler +1

Lamarr Institute · Fraunhofer IAIS · University of Bonn

Recurrent Transformers Language Model Scaling LLM Routing Adaptive Computation

May 28, 2026cs.RO

ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models

Vision-Language-Action (VLA) models are a powerful paradigm for generalist robotic control. However, their high computational cost and limited control frequency hinder real-time robotic manipulation, especially when large vision-language backbones and iterative action heads run at every control step. Existing VLA acceleration methods often optimize individual components or rely on fixed acceleration rules, treating different control steps with largely fixed computation and overlooking the non-uniform reasoning demands of sequential embodied control. Inspired by human motor control, where cognitive and feedback resources concentrate on goal-sensitive stages, we argue that VLA models should learn when to invest full computation and when to reuse prior computation. We propose ElegantVLA, a plug-in phase-adaptive inference framework that accelerates VLA models through intra-model dynamic compute scheduling. ElegantVLA introduces a lightweight scheduler that observes temporal representation similarity, robot-motion cues, and episode progress to jointly allocate computation across the vision encoder, LLM, and action head. For perception-language reasoning, the scheduler selects a five-level Vision-LLM compute mode, from full recomputation to multi-step temporal reuse, based on visual-language representation stability. For action generation, it selects a three-level denoising mode, reusing intermediate denoising states during stable motion while preserving full refinement for goal-sensitive stages. By coordinating these decisions, ElegantVLA offers a general acceleration framework for modern VLA pipelines with explicit action-generation modules, without modifying or retraining the base model. Experiments on GR00T and CogACT achieve up to 2.55x and 3.77x speedup, and on six real-world GR00T tasks ElegantVLA cuts computation by 2.18x while raising control frequency from 13.8 Hz to 26.3 Hz.

Ye Li, Huanan Liu, Kangye Ji +7

Tsinghua University · University of Illinois at Urbana-Champaign

Efficient VLM Inference Efficient VLA Model Inference Efficient VLA Models Vision-Language-Action Models VLMs for Robotics Reasoning for VLA Models+1

May 27, 2026cs.LG

LoRe: Adaptive Interaction-Evaluation Routing with Per-Step Interaction Budgets for Iterative Graph Solvers

Diffusion-based neural solvers for combinatorial optimization repeatedly re-evaluate dense edge/factor interactions, making inference expensive in wall-clock time and often memory-bound at scale. Inspired by the computational methodologies of many-body physics, we introduce LoRe, a training-free, inference-time drop-in wrapper that enforces per-step interaction-evaluation budgeting: at each iteration, it evaluates only a fixed fraction of interactions by dynamically routing computation to high-conflict or high-uncertainty interactions, instead of using a fixed sparsification (e.g., static kNN graphs or static masks). Under fully inclusive end-to-end wall-clock accounting, LoRe substantially improves scalability on the Maximum Independent Set (MIS) problem, extending feasible inference more than

3\times

beyond the baseline's out-of-memory limit, delivering a

\sim 8\times

speedup and a

\sim 12\times

peak-memory reduction, with solution quality preserved in this regime. Demonstrating cross-task generality on the large-scale Traveling Salesperson Problem (TSP) and zero-shot robustness to topology shifts, LoRe achieves a

\sim 15\times

speedup at

n=1000

with a

44\times

memory reduction and competitive tour quality.

Jintao Li, Yong-Yi Wang, Zheng-An Wang +1

Beijing Key Laboratory of Fault-Tolerant Quantum Computing, Beijing Academy of Quantum Information Sciences, Beijing, China · Beijing National Laboratory for Condensed Matter Physics, Institute of Physics, CAS, Beijing, China · Beijing Key Laboratory of Advanced Quantum Technology, Beijing, China +1

Efficient Inference Inference-Time Optimization Memory-Efficient Optimization Combinatorial Optimization Neural Combinatorial Optimization Diffusion Model Inference Acceleration+1

May 27, 2026cs.LG

CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models

Large language models have achieved strong reasoning capabilities, though often at the cost of massive parameter counts and expensive inference. In this work, we explore a different direction: adaptive reasoning depth in compact language models. We present CosmicFish-HRM, a compact language model built around a Hierarchical Reasoning Module (HRM) that dynamically allocates computational effort during inference. Instead of applying fixed computation to every input, the model iterates through high-level and low-level reasoning cycles and learns when to halt based on input complexity. CosmicFish-HRM combines this adaptive reasoning core with modern transformer components including Grouped Query Attention, RoPE, and SwiGLU activations. While the additional reasoning infrastructure introduces overhead at small scale, we hypothesize that this tradeoff becomes increasingly favorable as model size grows and the relative cost of the HRM core diminishes. Our results show that the model learns non-uniform reasoning behavior, allocating different numbers of reasoning steps across tasks and inputs. These findings suggest that adaptive reasoning depth may offer a promising alternative to relying solely on parameter scale for reasoning capability.

Venkat Akhil Lakkapragada

Mistyoz AI Hyderabad, India

Small Language Models LLM Reasoning Adaptive Computation Large Reasoning Models

May 27, 2026cs.AI

Do Agents Think Deeper? A Mechanistic Investigation of Layer-Wise Dynamics in Sequential Planning

Recent mechanistic studies suggest that large language models (LLMs) may utilize their depth inefficiently in standard single-turn tasks. Whether this still holds in autonomous agent settings, where models must perform multi-turn planning, tool use, and iterative state updates, remains unclear. We study this question through a systematic layer-wise analysis of complete user-agent trajectories spanning three domains: Deep Research, Code Generation, and Tabular Processing. Using residual stream probes, causal layer-skipping interventions, and effective-depth measurements, we show that agentic reasoning exhibits a distinct depth profile from static tasks. As trajectories unfold, models progressively recruit more and deeper layers, with stronger long-range inter-layer dependencies emerging in later turns. At the same time, residual updates become increasingly correction-dominant, indicating a shift from stable feature accumulation toward repeated recalibration. Effective-depth analysis further reveals a substantial construction-refinement gap: semantic direction often forms relatively early, while deep layers remain necessary for stabilizing final outputs. Across model families, this gap is pronounced in Qwen and Minimax, whereas GLM shows a more domain-dependent depth allocation pattern. These results provide mechanistic evidence that autonomous LLM agents allocate depth adaptively as reasoning complexity grows.

Zhenyu Cui, Xiangzhong Luo

LLM Interpretability Mechanistic Interpretability Long-Horizon LLM Agents Adaptive Computation

May 24, 2026q-bio.NC

Growing a Neural Network in Breadth, Depth, and Time

Spatial and temporal resource constraints are critical for both biological and artificial intelligent systems. Here we define differentiable cost terms for breadth, depth, and time within a recurrent convolutional neural network conceived as a finite subset of an infinite lattice. We optimize these costs jointly with task errors via backpropagation. We set different pressures on breadth, depth, and time, which leads to diverse computational graphs emerging organically through training. We find that all three resources can be traded off against each other to achieve a given level of accuracy. Networks grow in all three dimensions with task complexity and spontaneously take more recurrent steps when inputs are occluded. Surprisingly, time used by the model correlates with human reaction times in an object recognition task. Our framework provides a normative account of how resource constraints shape neural architectures, connecting to questions about brain design in neuroscience, and may help illuminate the diversity of neural solutions found in nature.

Eivinas Butkus, Kedar Garzón Gupta, Nikolaus Kriegeskorte

1Columbia University · 2NSF AI Institute for Artificial and Natural Intelligence

Convolutional RNNs Dynamic Neural Networks Neural Network Optimization Recurrent Neural Networks Convolutional Neural Networks Adaptive Computation

May 15, 2026cs.CL

Process Rewards with Learned Reliability

Process Reward Models (PRMs) provide step-level feedback for reasoning, but current PRMs usually output only a single reward score for each step. Downstream methods must therefore treat imperfect step-level reward predictions as reliable decision signals, with no indication of when these predictions should be trusted. We propose BetaPRM, a distributional PRM that predicts both a step-level success probability and the reliability of that prediction. Given step-success supervision from Monte Carlo continuations, BetaPRM learns a Beta belief that explains the observed number of successful continuations through a Beta-Binomial likelihood, rather than regressing to the finite-sample success ratio as a point target. This learned reliability signal indicates when a step reward should be trusted, enabling downstream applications to distinguish reliable rewards from uncertain ones. As one application, we introduce Adaptive Computation Allocation (ACA) for PRM-guided Best-of-N reasoning. ACA uses the learned reliability signal to stop when a high-reward solution is reliable and to spend additional computation on uncertain candidate prefixes. Experiments across four backbones and four reasoning benchmarks show that BetaPRM improves PRM-guided Best-of-N selection while preserving standard step-level error detection. Built on this signal, ACA improves the accuracy--token tradeoff over fixed-budget Best-of-16, reducing token usage by up to 33.57% while improving final-answer accuracy.

Jinyuan Li, Langlin Huang, Chengsong Huang +5

Washington University in St. Louis · Singapore University of Technology and Design

Reward Modeling Process Reward Models Algorithmic Reasoning Adaptive Computation

May 11, 2026cs.CV

GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs

Long-video understanding in VLMs is bottlenecked by a single monolithic forward pass over thousands of frames at quadratic attention cost. A common mitigation is to first select a small subset of informative frames before the forward pass; common for training-free selectors via auxiliary encoder-space similarities. Such signals are capped by contrastive pretraining, which usually fails on reasoning-heavy queries (negation, cross-frame counting, holistic summarization). We propose GridProbe, an efficient training-free posterior-probing inference paradigm that scores evidence in answer space using a frozen VLM's own reasoning and then selects question-relevant frames adaptively, resulting in sub-quadratic attention cost with little to no accuracy loss. We arrange frames on a

K{\times}K

grid and run lightweight row R and column C probes, where each probe reads its peak posterior as a query-conditioned confidence. The outer product of R and C yields an interpretable importance map whose skewness and kurtosis drive Shape-Adaptive Selection, a closed-form rule that reliably replaces the fixed frame budget

M

with a per-question

M_{\mathrm{eff}}

. We show empirically that

M_{\mathrm{eff}}

tracks intrinsic question difficulty without ever seeing the answer, a sign of test-time adaptive compute. On Video-MME-v2, GridProbe matches the monolithic baseline within

1.6

pp Avg Acc at

3.36\times

TFLOPs reduction, while on LongVideoBench it Pareto-dominates the baseline (

+0.9

pp at

0.35\times

compute). Because the selector and QA models can be decoupled, pairing a small 2B selector with a stronger 4B or 8B QA is strictly Pareto-dominant over the 2B monolithic baseline (up to

+4.0

pp at

0.52\times

compute, on average), with no retraining. Finally, the interpretability of the importance maps opens future avenues for behavioral diagnostics, grounding, and frame-selection distillation.

Mohamed Eltahir, Lama Ayash, Ali Habibullah +2

King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia · Department of Computer Science, Edge Hill University, Ormskirk, England

Efficient VLM Inference Long-Video Understanding Video Frame Selection Adaptive Computation Query-Aware Video Frame Selection

May 11, 2026cs.LG

Consolidation-Expansion Operator Mechanics:A Unified Framework for Adaptive Learning

Every adaptive learning system must alternate between two operations: consolidating what it already knows and expanding into new evidence. We propose \emph{Consolidation-Expansion Operator Mechanics} (OpMech), a framework that makes this structure precise. The central object is the \emph{order-gap}

\Ogap(θ; e)

, the degree to which a consolidation operator~

Q

and an expansion operator~

P_e

fail to commute at a given knowledge state. Because the order-gap is computable from the system's own trajectory, it serves as a real-time control signal: large values indicate that the system is still sensitive to the ordering of consolidation and expansion; once the order-gap falls and stays small, further processing is unlikely to change the outcome. Three results give the signal precise meaning: the order-gap decays along convergent trajectories; a persistently large order-gap implies the system is far from its settled state; and an order-gap-based stopping rule terminates with provable guarantees in both noiseless and bounded-noise settings. The framework applies across five domains: bandits, reinforcement learning, stochastic optimization, continual learning, and recursive language models. We give conditions under which the order-gap reliably tracks convergence in three representative cases. We develop the recursive language model application in detail, showing how OpMech replaces heuristic stopping rules and fixed recursion budgets with principled, evidence-driven alternatives.

Debashis Guha

S P Jain School of Global Management

Adaptive Learning Adaptive Computation Recursive Language Models

May 10, 2026cs.CL

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models

Tokenizer-free language models eliminate the tokenizer step of the language modeling pipeline by operating directly on bytes; patch-based variants further aggregate contiguous byte spans into patches for efficiency. However, the average patch size chosen at the model design stage governs a tight trade-off: larger patches reduce compute and KV-cache footprint, but degrade modeling quality. We trace this trade-off to patch lag: until a patch is fully observed, byte predictions within it must rely on a stale representation from the previous patch to preserve causality; this lag widens as patches grow larger. We introduce Scratchpad Patching (SP), which inserts transient scratchpads inside each patch to aggregate the bytes seen so far and refresh patch-level context for subsequent predictions. SP triggers scratchpads using next-byte prediction entropy, selectively allocating compute to information-dense regions and enabling post-hoc adjustment of inference-time compute. Across experiments on natural language and code, SP improves model quality at the same patch size; for example, even at

16

bytes per patch, SP-augmented models match or closely approach the byte-level baseline on downstream evaluations while using a

16\times

smaller KV cache over patches and

3

-

4\times

less inference compute.

Lin Zheng, Vasilisa Bashlovkina, Timothy Dozat +3

1Google DeepMind · 2The University of Hong Kong

Byte-Level Language Model Language Modeling Efficient Language Model Inference Adaptive Computation

May 10, 2026cs.LG

LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models

Looped computation shows promise in improving the reasoning-oriented performance of LLMs by scaling test-time compute. However, existing approaches typically require either training recurrent models from scratch or applying disruptive retrofits, which involve substantial computational costs and may compromise pretrained capabilities. To address these limitations, we introduce \textbf{Looped Depth Up-Scaling} (LoopUS), a post-training framework that converts a standard pretrained LLM into a looped architecture. As a key technical contribution, LoopUS recasts the pretrained LLM into an encoder, a looped reasoning block, and a decoder. It operationalizes this latent-refinement architecture through four core components: (1) block decomposition, guided by staged representation dynamics; (2) an input-dependent selective gate to mitigate hidden-state drift; (3) random deep supervision for memory-efficient learning over long recursive horizons; and (4) a confidence head for adaptive early exiting. Collectively, these mechanisms transform a standard non-looped model into a looped form while stabilizing it against both computational bottlenecks and representation collapse. Through stable latent looping, LoopUS improves reasoning-oriented performance without extending the generated traces or requiring recurrent training from scratch. For more details, see https://thrillcrazyer.github.io/LoopUS

Taekhyun Park, Yongjae Lee, Dohee Kim +1

Department of Data Science Pusan National University Busan, Republic of Korea · Department of Industrial Engineering Pusan National University Busan, Republic of Korea · Department of Artificial Intelligence Engineering Changwon National University Changwon, Republic of Korea

Recurrent Transformers LLM Post-Training LLM Reasoning Adaptive Computation

May 7, 2026cs.CV

Dynamic Pondering Sparsity-aware Mixture-of-Experts Transformer for Event Stream based Visual Object Tracking

Despite significant progress, RGB-based trackers remain vulnerable to challenging imaging conditions, such as low illumination and fast motion. Event cameras offer a promising alternative by asynchronously capturing pixel-wise brightness changes, providing high dynamic range and high temporal resolution. However, existing event-based trackers often neglect the intrinsic spatial sparsity and temporal density of event data, while relying on a single fixed temporal-window sampling strategy that is suboptimal under varying motion dynamics. In this paper, we propose an event sparsity-aware tracking framework that explicitly models event-density variations across multiple temporal scales. Specifically, the proposed framework progressively injects sparse, medium-density, and dense event search regions into a three-stage Vision Transformer backbone, enabling hierarchical multi-density feature learning. Furthermore, we introduce a sparsity-aware Mixture-of-Experts module to encourage expert specialization under different sparsity patterns, and design a dynamic pondering strategy to adaptively adjust the inference depth according to tracking difficulty. Extensive experiments on FE240hz, COESOT, and EventVOT demonstrate that the proposed approach achieves a favorable trade-off between tracking accuracy and computational efficiency. The source code will be released on https://github.com/Event-AHU/OpenEvTracking.

Shiao Wang, Xiao Wang, Duoqing Yang +5

School of Computer Science and Technology, Anhui University, Hefei 230601, China · Beijing Institute of Technology, Beijing, China · Peng Cheng Laboratory, Shenzhen, China +2

Event-Based Vision Mixture of Experts Visual Object Tracking Vision Transformer Adaptive Computation