Efficient Inference

Ask about this topic

Overview

Efficient inference studies how to get useful model outputs with less computation, memory, time, or energy, which matters for large-scale serving and devices with limited resources. Approaches include quantization and distillation, caching and reuse, sparse or low-rank computation, early exits, amortized inference, and adaptive allocation of test-time compute. Systems work complements these methods with batching, scheduling, compilation, and hardware-aware execution, while probabilistic methods seek faster posterior or marginal estimates without losing calibration or exactness. The central tension is reducing cost without undermining accuracy, uncertainty estimates, or robustness, and results can depend strongly on the workload and hardware used for evaluation.

Latest papers

CardsList

109 papers14 papers in the last four weeks, up 17% on the four weeks before. 0.1% of all new papers.

May 15, 2026

TFZ-Tree: An Ultra-Lightweight Waveform Classification Framework for Resource-Constrained Devices

Under the trend of multi-waveform coexistence in 6G IoT, intelligent receivers must first identify physical-layer waveform types before performing correct demodulation and resource scheduling. However, existing signal identification research largely focuses on symbol-level modulation classification. Research directly targeting physical-layer waveform types (e.g., OFDM, OTFS, LoRa) is not only extremely scarce but also heavily reliant on deep neural networks and complex time-frequency transforms, making deployment on resource-constrained terminals difficult. Symbol modulation classification methods themselves cannot circumvent the prerequisite of ``waveform identification first.'' To address this dual gap, we propose an ultra-lightweight waveform classification framework based on time-frequency multidimensional features with a cooperative Z-test tree (ZTree). The framework employs low-complexity time-domain feature extraction, and the classification backend adopts a ZTree optimized by Z-statistical testing, which uses hypothesis testing confidence to automatically control decision tree splitting and size, ensuring efficient execution on resource-limited processors. Tested on ten 6G candidate waveforms including OFDM, OTFS, DSSS, LoRa, and NB-IoT, the method achieves 99.5% average accuracy under AWGN and 87.4% under TDL-C multipath channels, with main confusion between OTFS and LoRa. Implemented in C on an x86 platform, single inference latency is under 4~ms. To the best of our knowledge, this is the first work achieving real-time recognition of ten IoT waveform types. Future work will target deployment acceleration on embedded MCUs. Code and dataset are open-sourced at: https://github.com/Einstein-sworder/IoT-wave.

Hao Wang, Kuang Zhang, Yonggang Chi +3

Efficient InferenceInternet of ThingsWireless CommunicationsDecision Tree LearningPower-Efficient Inference
AskPDF
May 11, 2026

Extending Kernel Trick to Influence Functions

In this paper, we present a dual representation of the influence functions, whose computational complexity scales with dataset size rather than model size. Both analytically and experimentally, we show that this representation can be an efficient alternative to the original influence functions for estimating changes in parameters, model outputs and loss due to data point removal, when model size is large relative to dataset size, or when evaluating the original influence functions in parameter space is infeasible. The dual representation, however, is limited to linearizable models, which are models whose behavior can be approximated by their linearizations throughout training, and requires materializing a matrix, whose size grows with the product of model output dimension and dataset size.

Zhenhuan Sun, Shahrokh Valaee

University of Toronto

Efficient InferenceInfluence Functions
AskPDF
May 11, 2026

Foundations of Reliable Inference: Reliability-Efficiency Co-Design

Reliable inference requires that artificial intelligence (AI) models provide trustworthy uncertainty estimates, not merely accurate predictions. Recent advances in Bayesian learning have made significant progress toward this goal, and growing concerns about computational overhead have jointly shifted the design criterion from reliability alone to the co-design of reliability and efficiency, i.e., reducing computational overhead while preserving trustworthy uncertainty quantification. This thesis develops a unified framework from two perspectives to address the central question: can we efficiently perform reliable inference?

Jiayi Huang

The Department of EngineeringarXiv:2605.10351v1 King’s College London

Efficient InferenceUncertainty QuantificationBayesian Inference
AskPDF
May 11, 2026

PixelFlowCast: Latent-Free Precipitation Nowcasting via Pixel Mean Flows

Precipitation nowcasting aims to forecast short-term radar echo sequences for extreme weather warning, where both prediction fidelity and inference efficiency are critical for real-world deployment. However, diffusion-based models, despite their strong generative capability, suffer from slow inference due to multi-step sampling trajectories, limiting their practical usability. Conditional Flow Matching (CFM) improves efficiency via straightened trajectories, but relies on latent space compression, which inevitably discards high-frequency physical details and degrades fine-grained prediction quality. To address these limitations, we propose PixelFlowCast, a two-stage probabilistic forecasting framework that achieves both high-efficiency and high-fidelity prediction without latent compression. Specifically, in the first stage, a deterministic model first produces coarse forecasts to capture global evolution trends. In the subsequent stage, the proposed KANCondNet extracts deep spatiotemporal evolution features to provide accurate conditional guidance. Based on this, a latent-free, few-step Pixel Mean Flows (PMF) predictor employs an xx-prediction mechanism to generate high-quality predictions, effectively preserving fine-grained structures while maintaining fast inference. Experiments on the publicly available SEVIR dataset demonstrate that PixelFlowCast outperforms existing mainstream methods in both prediction accuracy and inference efficiency, particularly for long sequence forecasting, highlighting its strong potential for real-world operational deployment.

Yufeng Zhu, Chunlei Shi, Yongchao Feng +1

Department of Automation, Southeast University, Nanjing 210096, China · State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, China

Precipitation ForecastingEfficient InferenceSpatiotemporal ForecastingPrecipitation NowcastingProbabilistic Time Series Forecasting
AskPDF
May 10, 2026

TileQ: Efficient Low-Rank Quantization of Mixture-of-Experts with 2D Tiling

Mixture-of-Experts (MoE) models achieve remarkable performance by sparsely activating specialized experts, yet their massive parameters in experts pose significant challenges for deployment. While low-rank quantization offers a promising route to compress MoE models, existing methods still incur nonnegligible memory overhead and inference latency. To address these limitations, we propose TileQ, a fine-tuning-free post-training quantization (PTQ) method that employs 2D-tiling structured low-rank quantization to share low-rank factors across both input and output dimensions of MoE experts. Furthermore, we introduce an efficient inference technique for TileQ that fuses multiple low-rank expert computations into a single-pass operation, significantly improving hardware utilization. Experiments show that TileQ cuts down additional memory usage up to 10×\times and reduces inference latency to ∼\sim5% while preserving state-of-the-art accuracy.

Hongyaoxing Gu, Xinzhe Chen, Lijuan Hu +1

Institute of Software Chinese Academy of Sciences · University of Chinese Academy of Sciences

Efficient InferenceMixture-of-Experts InferenceMixture-of-Experts QuantizationMixture-of-Experts ModelsPost-Training QuantizationNeural Network Quantization
AskPDF
May 9, 2026

Latency Analysis and Optimization of Alpamayo 1 via Efficient Trajectory Generation

Reasoning-based end-to-end (E2E) autonomous driving has recently emerged as a promising approach to improving the interpretability of driving decisions as it can generate human-readable reasoning together with predicted trajectories. Such approaches commonly generate multiple trajectories to capture diverse future behaviors, and they fall into two categories: (1) multi-reasoning, where one reasoning sequence is generated per trajectory, and (2) single-reasoning, where a single reasoning is shared across all trajectories. The former offers richer diversity at the cost of redundant computation, while the latter is more efficient but is often assumed to sacrifice diversity. Alpamayo 1, a representative system, adopts the multi-reasoning approach and achieves competitive trajectory prediction performance. However, the efficiency of this design remains largely unexplored, making it a well-motivated subject for investigation. In this paper, we systematically analyze and improve Alpamayo 1 in two ways. First, we reduce inference latency while preserving trajectory diversity by redesigning Alpamayo 1 into a single-reasoning system. Through extensive experiments, we find that replacing multi-reasoning with single-reasoning does not meaningfully degrade trajectory diversity. Second, we accelerate diffusion-based action generation by eliminating inter-block overhead arising from unnecessary copy operations and inefficient kernel execution. Through closed-loop and open-loop experiments, we validate both optimizations, demonstrating a 69.23% reduction in inference latency while maintaining trajectory diversity and prediction quality. These results highlight the importance of jointly analyzing system architecture and runtime execution to improve the efficiency of reasoning-based E2E AD systems.

Yunseong Jeon, Namcheol Lee, Yoonsu Lee +4

Graduate School of Automobile and Mobility, Kookmin University, Seoul, Republic of Korea · Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea

Efficient InferenceEnd-to-End Autonomous DrivingDiffusion-Based PlanningVehicle Trajectory PredictionDiffusion Model Inference Acceleration
AskPDF
May 8, 2026

Exploring and Exploiting Stability in Latent Flow Matching

In this work, we show that Latent Flow-Matching (LFM) models are robust to different types of perturbations, including data reduction and model capacity shrinkage. We characterize this stability by these models' tendency to generate similar outputs under identical noise seeds. We provide a perspective relating this phenomenon to flow matching theory, which indicates that this stability is inherent to the FM objective. We further exploit this stability to derive practical algorithms for more efficient training and inference. Concretely, first, we show that by training LFM models on significantly reduced datasets, performance is preserved, and in compute-constrained regimes, the model converges faster while maintaining quality. This yields multiple advantages, including savings in the training time due to faster convergence, and alleviating annotation effort when training conditional models. Second, LFM stability under architectural shrinkage gives rise to a two-model coarse-to-fine approach, one using a light-weight architecture for the first phase of the FM trajectory, and one with higher capacity for the second, thereby reducing the inference cost substantially. To determine which samples are informative, we introduce three sample-scoring criteria and evaluate them under standard metrics for generative models. Our results are thoroughly evaluated on multiple datasets, demonstrating the practical advantage of this stability, including data savings and a more than two-fold inference speedup while generating comparable outputs.

Rania Briq, Michael Kamp, Ohad Fried +2

Forschungszentrum Jülich · Technical University Dortmund · Lamarr Institute +4

Flow MatchingEfficient InferenceGenerative ModelingFlow-Based Generative Modeling
AskPDF
May 8, 2026

StreamPhy: Streaming Inference of High-Dimensional Physical Dynamics via State Space Models

Inferring the evolution of high-dimensional and multi-modal (e.g., spatio-temporal) physical fields from irregular sparse measurements in real time is a fundamental challenge in science and engineering. Existing approaches, including diffusion-based generative models and functional tensor methods, typically operate in offline settings, depend on full temporal observations, or incur substantial inference cost. We propose StreamPhy, an end-to-end framework that enables efficient and accurate streaming inference of full-field physical dynamics from incoming irregular sparse measurements. The framework integrates a data-adaptive observation encoder that is robust to arbitrary observation patterns, a structured state-space model that supports memory-efficient online updates across irregular time intervals, and an expressive Functional Tensor Feature-wise Linear Modulation (FT-FiLM) decoder for continuous-field generation. We prove that FT-FiLM is more expressive than the functional Tucker model, admitting a richer function class for handling complex dynamics. Experiments on three representative physical systems under challenging sampling patterns show that StreamPhy consistently outperforms state-of-the-art baselines, with at least 48% improvement in accuracy and up to 20--100X faster inference than diffusion-based methods.

Panqi Chen, Yifan Sun, Shikai Fang +2

College of Information Science and Electronic Engineering, Zhejiang University · School of EECS,Oregon State University

Efficient InferenceStreaming InferenceState Space ModelsStreaming Algorithms
AskPDF
May 6, 2026

Estimating the expected output of wide random MLPs more efficiently than sampling

By far the most common way to estimate an expected loss in machine learning is to draw samples, compute the loss on each one, and take the empirical average. However, sampling is not necessarily optimal. Given an MLP at initialization, we show how to estimate its expected output over Gaussian inputs without running samples through the network at all. Instead, we produce approximate representations of the distributions of activations at each layer, leveraging tools such as cumulants and Hermite expansions. We show both theoretically and empirically that for sufficiently wide networks, our estimator achieves a target mean squared error using substantially fewer FLOPs than Monte Carlo sampling. We find moreover that our methods perform particularly well at estimating the probabilities of rare events, and additionally demonstrate how they can be used for model training. Together, these findings suggest a path to producing models with a greatly reduced probability of catastrophic tail risks.

Wilson Wu, Victor Lecomte, Michael Winer +3

Alignment Research Center

Multilayer PerceptronsEfficient InferenceRare-Event Estimation
AskPDF
May 6, 2026

GraphPI: Efficient Protein Inference with Graph Neural Networks

The integration of deep learning approaches in biomedical research has been transformative, enabling breakthroughs in various applications. Despite these strides, its application in protein inference is impeded by the scarcity of extensively labeled datasets, a challenge compounded by the high costs and complexities of accurate protein annotation. In this study, we introduce GraphPI, a novel framework that treats protein inference as a node classification problem. We treat proteins as interconnected nodes within a protein-peptide-PSM graph, utilizing a Graph Neural Network-based architecture to elucidate their interrelations. To address label scarcity, we train the model on a set of unlabeled public protein datasets with pseudo-labels derived from an existing protein inference algorithm, enhanced by self-training to iteratively refine labels based on confidence scores. Contrary to prevalent methodologies necessitating dataset-specific training, our research illustrates that GraphPI, due to the well normalized nature of Percolator features, exhibits universal applicability without dataset-specific fine-tuning, a feature that not only mitigates the risk of overfitting but also enhances computational efficiency. Our empirical experiments reveal notable performance on various test datasets and deliver significantly reduced computation times compared to common protein inference algorithms.

Zheng Ma, Jiazhen Chen, Lei Xin +1

Cheriton School of Computer Science, University of Waterloo, Waterloo, ON, Canada, N2L 3G1 · Department of Statistical and Actuarial Science, University of Waterloo, Waterloo, ON, Canada, N2L 3G1 · Bioinformatics Solutions Inc., Waterloo, ON, Canada, N2L 3K8

Efficient Inference
AskPDF
May 5, 2026

A Fast Model Counting Algorithm for Two-Variable Logic with Counting and Modulo Counting Quantifiers

Weighted first-order model counting (WFOMC) is a central task in lifted probabilistic inference: It asks for the weighted sum of all models of a first-order sentence over a finite domain. A long line of work has identified domain-liftable fragments of first-order logic, that is, syntactic classes for which WFOMC can be solved in time polynomial in the domain size. Among them, the two-variable fragment with counting quantifiers, C2\mathbf{C}^2, is one of the most expressive known liftable fragments. Existing algorithms for C2\mathbf{C}^2, however, establish tractability through multi-stage reductions that eliminate counting quantifiers via cardinality constraints, which introduces substantial practical overhead as the domain size grows. In this paper, we introduce IncrementalWFOMC3, a lifted algorithm for WFOMC on C2\mathbf{C}^2 and its modulo counting extension, Cmod2\mathbf{C}^2_{\text{mod}}. Instead of relying on reduction techniques, IncrementalWFOMC3 operates directly on a Scott normal form that retains counting quantifiers throughout inference. This direct treatment yields two main results. First, we derive a tighter data-complexity bound for WFOMC in C2\mathbf{C}^2, reducing the degree of the polynomial from quadratic to linear in the counting parameters. Second, we prove that Cmod2\mathbf{C}^2_{\text{mod}} is domain-liftable, extending tractability from C2\mathbf{C}^2 to a richer fragment with native modulo counting support. Finally, our empirical evaluation shows that IncrementalWFOMC3 delivers orders-of-magnitude runtime improvements and better scalability than both existing WFOMC algorithms and state-of-the-art propositional model counters.

Shixin Sun, Astrid Klipfel, Ondřej Kuželka +2

School of Artificial Intelligence, Jilin University, Changchun 130012, China · CRIL, Université d’Artois, Lens 62307, France · Czech Technical University, Prague 160 00, Czechia +1

Efficient Inference
AskPDF
May 1, 2026

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

Efficient InferenceCost-Aware Inference
AskPDF
Apr 27, 2026

Spark Policy Toolkit: Semantic Contracts and Scalable Execution for Policy Learning in Spark

Custom policy-learning pipelines in Spark fail for two coupled systems reasons: rowwise Python execution makes inference impractical, and driver-side candidate materialization makes split search fragile at feature scale. We present Spark Policy Toolkit, a semantics-governed systems toolkit for scalable policy learning in Spark. The toolkit provides two Spark-native primitives: partition-initialized vectorized inference through mapInPandas and mapInArrow, and collect-less split search that scores candidates on executors. Both primitives are governed by one fixed-input semantic contract: the same rows, feature order, treatment vocabulary, preprocessing manifest, and split boundaries must preserve per-row score vectors, best-split decisions, and end-to-end learned policy outputs. The evaluation combines practical baseline ladders, backend parity checks, measured split-search scale results, synthetic and Hillstrom end-to-end policy preservation, missingness stress, partition and order perturbation tests, quantile-boundary sensitivity, and a concrete adversarial failure catalog. On a 40-worker Databricks cluster, mapInArrow reaches 4.72M rows/s at 10M matched rows and 7.23M rows/s at 50M rows, while collect-less split search remains valid from F = 10 through F = 1000 with 124000 candidate rows, where the driver-collect baseline is intentionally skipped. Across 24 backend-ablation settings, mapInArrow wins 18 while mapInPandas wins 6, so the paper treats backend choice as workload-dependent rather than universal. Once the fixed-input lock is enforced, all six tested repartition/coalesce/shuffle perturbations preserve identical signatures; before lock, all six drift. The central result is not speed alone: throughput and collect-less execution are the mechanisms that let policy semantics survive at Spark scale.

Zeyu Bai

Efficient InferencePolicy LearningDistributed Inference
AskPDF
Apr 23, 2026

Null-Space Flow Matching for MIMO Channel Estimation in Latency-Constrained Systems

Accurate yet low-latency channel state information (CSI) acquisition is essential for multiple-input multiple-output (MIMO) communication systems. While advanced deep generative models, such as score-based and diffusion models, enable high-fidelity CSI reconstruction from limited pilot observations, they often suffer from high inference latency. To achieve accurate CSI estimation under stringent latency constraints, this paper proposes a null-space flow matching (FM) framework that decomposes pilot-limited MIMO channel estimation into a range-space reconstruction problem and a null-space generation problem. Specifically, the range-space component of the channel is directly recovered from noisy pilot observations, while only the ambiguous null-space component is iteratively refined using an FM-based generative prior. To further improve the robustness of the proposed framework, we introduce a power-law time schedule to better allocate the limited number of refinement steps, along with a noise-aware adaptive correction strategy to suppress channel noise on the refinement trajectory. Experimental results demonstrate that our method achieves a competitive normalized mean square error (NMSE) even under a strict latency budget of around 3 ms, while delivering superior estimation accuracy and faster inference than both model-based and generative baselines.

Junjie Zhao, Guangming Liang, Dongzhu Liu +1

College of Electronic Information and Optical Engineering, Nankai University · School of Computing Science, University of Glasgow · School of Natural and Computing Science, University of Aberdeen

Flow MatchingEfficient InferenceWireless CommunicationsChannel Estimation
AskPDF
Apr 22, 2026

Adaptive Test-Time Compute Allocation with Evolving In-Context Demonstrations

While scaling test-time compute can substantially improve model performance, existing approaches either rely on static compute allocation or sample from fixed generation distributions. In this work, we introduce a test-time compute allocation framework that jointly adapts where computation is spent and how generation is performed. Our method begins with a warm-up phase that identifies easy queries and assembles an initial pool of question-response pairs from the test set itself. An adaptive phase then concentrates further computation on unresolved queries while reshaping their generation distributions through evolving in-context demonstrations -- conditioning each generation on successful responses from semantically related queries rather than resampling from a fixed distribution. Experiments across math, coding, and reasoning benchmarks demonstrate that our approach consistently outperforms existing baselines while consuming substantially less inference-time compute.

Bowen Zuo, Dongruo Zhou, Yinglun Zhu

University of California, Riverside · 2Indiana University Bloomington

Efficient InferenceTest-Time OptimizationTest-Time ScalingIn-Context LearningInference-Time Compute Allocation
AskPDF
Apr 22, 2026

Fast Bayesian equipment condition monitoring via simulation based inference: applications to heat exchanger health

Accurate condition monitoring of industrial equipment requires inferring latent degradation parameters from indirect sensor measurements under uncertainty. While traditional Bayesian methods like Markov Chain Monte Carlo (MCMC) provide rigorous uncertainty quantification, their heavy computational bottlenecks render them impractical for real-time process control. To overcome this limitation, we propose an AI-driven framework utilizing Simulation-Based Inference (SBI) powered by amortized neural posterior estimation to diagnose complex failure modes in heat exchangers. By training neural density estimators on a simulated dataset, our approach learns a direct, likelihood-free mapping from thermal-fluid observations to the full posterior distribution of degradation parameters. We benchmark this framework against an MCMC baseline across various synthetic fouling and leakage scenarios, including challenging low-probability, sparse-event failures. The results show that SBI achieves comparable diagnostic accuracy and reliable uncertainty quantification, while accelerating inference time by a factor of82×\times compared to traditional sampling. The amortized nature of the neural network enables near-instantaneous inference, establishing SBI as a highly scalable, real-time alternative for probabilistic fault diagnosis and digital twin realization in complex engineering systems.

Peter Collett, Alexander Johannes Stasik, Simone Casolo +1

Cognite AS, Oslo, Norway · Department of Data Science, Norwegian University of Life Sciences, Ås, Norway · Department for Mathematics and Cybernetics, SINTEF Digital, Oslo, Norway

Simulation-Based InferenceEfficient InferenceAmortized InferenceBayesian InferencePredictive MaintenanceIndustrial Fault Diagnosis
AskPDF
Apr 22, 2026

Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees

Self-consistency boosts inference-time performance by sampling multiple reasoning traces in parallel and voting. However, in constrained domains like math and code, this strategy is compute-inefficient because it samples with replacement, repeatedly revisiting the same high-probability prefixes and duplicate completions. We propose Distinct Leaf Enumeration (DLE), a deterministic decoding method that treats truncated sampling as traversal of a pruned decoding tree and systematically enumerates distinct leaves instead of sampling with replacement. This strategy improves inference efficiency in two ways. Algorithmically, it increases coverage of the truncated search space under a fixed budget by exploring previously unvisited high-probability branches. Systemically, it reuses shared prefixes and reduces redundant token generation. Empirically, DLE explores higher-quality reasoning traces than stochastic self-consistency, yielding better performance on math, coding, and general reasoning tasks.

Xueyan Li, Johannes Zenn, Ekaterina Fadeeva +3

Max Planck Institute for Intelligent Systems · ETH Zurich · AI Center Tübingen +3

Language Model DecodingInference-Time SearchEfficient InferenceSelf-Consistency DecodingTest-Time OptimizationAlgorithmic Reasoning
AskPDF
Apr 22, 2026

Scalable AI Inference: Performance Analysis and Optimization of AI Model Serving

AI research often emphasizes model design and algorithmic performance, while deployment and inference remain comparatively underexplored despite being critical for real-world use. This study addresses that gap by investigating the performance and optimization of a BentoML-based AI inference system for scalable model serving developed in collaboration with graphworks.ai. The evaluation first establishes baseline performance under three realistic workload scenarios. To ensure a fair and reproducible assessment, a pre-trained RoBERTa sentiment analysis model is used throughout the experiments. The system is subjected to traffic patterns following gamma and exponential distributions in order to emulate real-world usage conditions, including steady, bursty, and high-intensity workloads. Key performance metrics, such as latency percentiles and throughput, are collected and analyzed to identify bottlenecks in the inference pipeline. Based on the baseline results, optimization strategies are introduced at multiple levels of the serving stack to improve efficiency and scalability. The optimized system is then reevaluated under the same workload conditions, and the results are compared with the baseline using statistical analysis to quantify the impact of the applied improvements. The findings demonstrate practical strategies for achieving efficient and scalable AI inference with BentoML. The study examines how latency and throughput scale under varying workloads, how optimizations at the runtime, service, and deployment levels affect response time, and how deployment in a single-node K3s cluster influences resilience during disruptions.

Hung Cuong Pham, Fatih Gedikli

Institute of Computer Science University of Applied Sciences Ruhr West Mülheim an der Ruhr, Germany

Efficient Inference
AskPDF
Apr 21, 2026

SAGE: Training-Free Semantic Evidence Composition for Edge-Cloud Inference under Hard Uplink Budgets

Edge-cloud hybrid inference offloads difficult inputs to a powerful remote model, but the uplink channel imposes hard per-request constraints on the number of bits that can be transmitted. We show that selecting transmitted content based solely on attention-based importance, the standard approach in collaborative inference, is inherently limited under hard budgets. Two findings support this claim. First, replacing high-importance units with low-importance but complementary ones improves server accuracy. This shows that what matters is not individual importance but how well the transmitted set covers diverse aspects of the input. Second, spatially uniform selection without any content information achieves competitive accuracy at moderate budgets. This confirms that spatial coverage alone carries independent value. Based on this analysis, we propose SAGE (Semantic Attention-Guided Evidence), a principled, training-free method that combines importance filtering with embedding-diversity sampling. SAGE achieves 93% of the server ceiling in offloaded accuracy while transmitting fewer than half of the available evidence units on ImageNet-1K, substantially outperforming importance-only composition.

Inhyeok Choi, Hyuncheol Park

School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea

Efficient InferenceEdge-Cloud ComputingImage ClassificationEdge-Cloud Collaborative Inference
AskPDF
Apr 21, 2026

EX-FIQA: Leveraging Intermediate Early eXit Representations from Vision Transformers for Face Image Quality Assessment

Face Image Quality Assessment is crucial for reliable face recognition systems, yet existing Vision Transformer-based approaches rely exclusively on final-layer representations, ignoring quality-relevant information captured at intermediate network depths. This paper presents the first comprehensive investigation of how intermediate representations within ViTs contribute to face quality assessment through early exit mechanisms and score fusion strategies. We systematically analyze all twelve transformer blocks of ViT-FIQA architectures, demonstrating that different depths capture distinct and complementary quality-relevant information, as evidenced by varying attention patterns and performance characteristics across network layers. We propose a score fusion framework that combines quality predictions from multiple transformer blocks without architectural modifications or additional training. Our early exit analysis reveals optimal performance-efficiency trade-offs, enabling significant computational savings while maintaining competitive performance. Through extensive evaluation across eight benchmark datasets using four FR models, we demonstrate that our fusion strategy improves upon single-exit approaches. Our proposed quality fusion approach employs depth-weighted averaging that assigns progressively higher importance to deeper transformer blocks, achieving the best quality assessment performance by effectively leveraging the hierarchical nature of feature learning in ViTs. Our work challenges the conventional wisdom that only deep features matter for face analysis, revealing that intermediate representations contain valuable information for quality assessment. The proposed framework offers practical benefits for real-world biometric systems by enabling adaptive computation based on resource constraints while maintaining competitive quality assessment capabilities.

Guray Ozgur, Tahar Chettaoui, Eduarda Caldeira +4

Fraunhofer Institute for Computer Graphics Research IGD, Darmstadt, Germany · Department of Computer Science, TU Darmstadt, Germany

Efficient Transformer InferenceEfficient InferenceVision TransformerImage Quality AssessmentEarly-Exit Neural Networks
AskPDF
Apr 21, 2026

FlowForge: A Staged Local Rollout Engine for Flow-Field Prediction

Deep learning surrogates for CFD flow-field prediction often rely on large, complex models, which can be slow and fragile when data are noisy or incomplete. We introduce FlowForge, a staged local rollout engine that predicts future flow fields by compiling a locality-preserving update schedule and executing it with a shared lightweight local predictor. Rather than producing the next frame in a single global pass, FlowForge rewrites spatial sites stage by stage so that each update conditions only on bounded local context exposed by earlier stages. This compile-execute design aligns inference with short-range physical dependence, keeps latency predictable, and limits error amplification from global mixing. Across PDEBench, CFDBench, and BubbleML, FlowForge matches or improves upon strong baselines in pointwise accuracy, delivers consistently better robustness to noise and missing observations, and maintains stable multi-step rollout behavior while reducing per-step latency.

Xiaowen Zhang, Ziming Zhou, Fengnian Zhao +1

Shanghai Jiao Tong University · University of Michigan

Efficient InferencePDE Surrogate ModelingSpatiotemporal ForecastingComputational Fluid Dynamics
AskPDF
Apr 20, 2026

Streaming Structured Inference with Flash-SemiCRF

Semi-Markov Conditional Random Fields (semi-CRFs) assign labels to segments of a sequence rather than to individual positions, enabling exact inference over segment-level features and principled uncertainty estimates at their boundaries. However, existing implementations must materialize a large edge potential tensor whose size grows with sequence length, maximum segment length, and label count, becoming prohibitive for speech-scale state spaces and intractable at genomic scales where sequences can exceed 100,000 positions. This memory bottleneck has limited the adoption of exact segment-level inference for long sequences and large label sets. We identify that the core inefficiency is materializing edge potentials that can instead be evaluated on-the-fly from a compact prefix-sum array, and make several improvements. First, replacing the stored edge tensor with prefix-sum lookup reduces the memory footprint by a factor proportional to the product of segment length and label count. Second, a streaming forward-backward pass with checkpoint-boundary normalization keeps working memory sublinear in sequence length while preserving exact gradients. Third, zero-centered cumulative scores control numerical drift and induce an adaptive duration prior under label imbalance. We integrate these ideas into Flash-SemiCRF, a fused Triton kernel that enables exact semi-CRF inference on previously intractable problem sizes. Available at https://github.com/biobenkj/flash-semicrf.

Benjamin K. Johnson, Thomas Goralski, Ayush Semwal +2

Department of Epigenetics, Van Andel Institute, 333 Bostwick Ave. NE, Grand Rapids, 49503, MI, USA. · Department of Cell Biology, Van Andel Institute, 333 Bostwick Ave. NE, Grand Rapids, 49503, MI, USA.

Efficient InferenceConditional Random FieldsMemory-Efficient InferenceSequence Modeling
AskPDF
Apr 20, 2026

FlashFPS: Efficient Farthest Point Sampling for Large-Scale Point Clouds via Pruning and Caching

Point-based Neural Networks (PNNs) have become a key approach for point cloud processing. However, a core operation in these models, Farthest Point Sampling (FPS), often introduces significant inference latency, especially for large-scale processing. Despite existing CUDA- and hardware-level optimizations, FPS remains a major bottleneck due to exhaustive computations across multiple network layers in PNNs, which hinders scalability. Through systematic analysis, we identify three substantial redundancies in FPS, including unnecessary full-cloud computations, redundant late-stage iterations, and predictable inter-layer outputs that make later FPS computations avoidable. To address these, we propose FlashFPS, a hardware-agnostic, plug-and-play framework for FPS acceleration, composed of FPS-Prune and FPS-Cache. FPS-Prune introduces candidate pruning and iteration pruning to reduce redundant computations in FPS while preserving sampling quality, and FPS-Cache eliminates layer-wise redundancy via cache-and-reuse. Integrated into existing CUDA libraries and state-of-the-art PNN accelerators, FlashFPS achieves 5.16×\times speedup over the standard CUDA baseline on GPU and 2.69×\times on PNN accelerators, with negligible accuracy loss, enabling efficient and scalable PNN inference. Codes are released at https://github.com/Yuzhe-Fu/FlashFPS.

Yuzhe Fu, Hancheng Ye, Cong Guo +7

Helen · Duke University Durham, North Carolina, USA

Efficient InferenceGPU AccelerationPoint Cloud Learning
AskPDF
Apr 17, 2026

KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving

Power has become a central bottleneck for AI inference. This problem is becoming more urgent as agentic AI emerges as a major workload class, yet prior power-management techniques focus almost entirely on single-turn LLM serving. Our analysis shows that agentic serving behaves fundamentally differently: each request carries long-lived context that evolves across tool-interleaved turns, and lowering GPU frequency can push the system into a thrashing regime where memory pressure sharply worsens both performance and power efficiency. These observations show that power optimization for agentic serving requires rethinking. We present KAIROS, a context-aware power optimization system for agentic AI serving. KAIROS uses agent context as a first-class control signal to jointly manage GPU frequency, per-instance concurrency, and multi-instance request placement. This enables KAIROS to save power when memory headroom exists while avoiding thrashing and preserving performance targets. At a high level, KAIROS tracks requests at agent granularity, adapts local control to context growth and agent progress, and routes agents across instances to jointly improve power efficiency and memory stability. Evaluated across diverse software and data engineering agentic tasks, KAIROS achieves an average of 27% (up to 39.8%) power reduction while meeting the performance targets.

Yichao Yuan, Mosharaf Chowdhury, Nishil Talati

University of Illinois, Urbana Champaign Urbana, IL, USA · University of Michigan Ann Arbor, MI, USA

Efficient InferenceLLM Inference ServingAgentic AIPower-Efficient Inference
AskPDF
Apr 16, 2026

A Comparative Study of CNN Optimization Methods for Edge AI: Exploring the Role of Early Exits

Deploying deep neural networks on edge devices requires balancing accuracy, latency, and resource constraints under realistic execution conditions. To fit models within these constraints, two broad strategies have emerged: static compression techniques such as pruning and quantization, which permanently reduce model size, and dynamic approaches such as early-exit mechanisms, which adapt computational cost at runtime. While both families are widely studied in isolation, they are rarely compared under identical conditions on physical hardware. This paper presents a unified deployment-oriented comparison of static compression and dynamic early-exit mechanisms, evaluated on real edge devices using ONNX based inference pipelines. Our results show that static and dynamic techniques offer fundamentally different trade-offs for edge deployment. While pruning and quantization deliver consistent memory footprint reduction, early-exit mechanisms enable input-adaptive computation savings that static methods cannot match. Their combination proves highly effective, simultaneously reducing inference latency and memory usage with minimal accuracy loss, expanding what is achievable at the edge.

Nekane Fernandez, Ivan Valdes, Steven Van Vaerenbergh +2

Nekane Fernandez, Ivan Valdes, Idoia de la Iglesia and Julen Arratibel are with the Dept. of Connected and Distributed Intelligence, Ikerlan Technology Research Centre, Arrasate, Spain · Nekane Fernandez and Steven Van Vaerenbergh are with the Dept. of Mathematics, Statistics and Computation, Universidad de Cantabria, Santander, Spain

Efficient InferenceEdge InferenceNeural Network QuantizationNeural Network CompressionEarly-Exit Neural NetworksNeural Network Pruning
AskPDF
Apr 15, 2026

Rethinking AI Hardware: A Three-Layer Cognitive Architecture for Autonomous Agents

The next generation of autonomous AI systems will be constrained not only by model capability, but by how intelligence is structured across heterogeneous hardware. Current paradigms -- cloud-centric AI, on-device inference, and edge-cloud pipelines -- treat planning, reasoning, and execution as a monolithic process, leading to unnecessary latency, energy consumption, and fragmented behavioral continuity. We introduce the Tri-Spirit Architecture, a three-layer cognitive framework that decomposes intelligence into planning (Super Layer), reasoning (Agent Layer), and execution (Reflex Layer), each mapped to distinct compute substrates and coordinated via an asynchronous message bus. We formalize the system with a parameterized routing policy, a habit-compilation mechanism that promotes repeated reasoning paths into zero-inference execution policies, a convergent memory model, and explicit safety constraints. We evaluate the architecture in a reproducible simulation of 2000 synthetic tasks against cloud-centric and edge-only baselines. Tri-Spirit reduces mean task latency by 75.6 percent and energy consumption by 71.1 percent, while decreasing LLM invocations by 30 percent and enabling 77.6 percent offline task completion. These results suggest that cognitive decomposition, rather than model scaling alone, is a primary driver of system-level efficiency in AI hardware.

Li Chen

Edge-Cloud Collaborative InferenceCognitive Architectures for AI AgentsEfficient InferenceHeterogeneous ComputingEdge-Cloud Computing
AskPDF
Apr 12, 2026

LAWS: Learning from Actual Workloads Symbolically -- A Self-Certifying Parametrized Cache Architecture for Neural Inference, Robotics, and Edge Deployment

We introduce LAWS (Learning from Actual Workloads Symbolically), a self-certifying inference caching architecture that builds a growing library of certified expert functions from deployment observations. Each expert covers a region of input space defined by a node in the Probabilistic Language Trie (PLT) of the base model and carries a formal error bound holding uniformly over all inputs. The central result is a self-certification theorem: for any input x, the LAWS approximation error is bounded by epsilon_fit + 2*Lambda(W)*C_E, where Lambda(W) is the model Lipschitz constant, C_E is the maximum embedding diameter, and epsilon_fit is the expert training error -- all checkable at deployment time without ground truth. We prove that LAWS generalizes both Mixture-of-Experts and KV prefix caching as special cases and is strictly more expressive than any fixed-K MoE or finite cache. Further results include a monotone hit rate theorem (any-match routing ensures coverage only increases), an expert library growth rate of O(2^H log N) where H is workload entropy, a fleet learning convergence theorem with Omega(K) speedup for K-unit fleets, and an over-the-air update bandwidth bound. We conjecture that LAWS is acquisition-optimal among stationary online caching algorithms and that the effective Lipschitz constant on the training distribution grows polynomially rather than exponentially in depth. Applications are developed for LLM inference, robotic control, and multi-agent edge deployment.

Gregory Magarshak

Efficient InferenceLLM Inference AccelerationOn-Device Inference
AskPDF
Apr 12, 2026

One-Step Score-Based Density Ratio Estimation

Density ratio estimation (DRE) is a useful tool for quantifying discrepancies between probability distributions, but existing approaches often involve a trade-off between estimation quality and computational efficiency. Classical direct DRE methods are usually efficient at inference time, yet their performance can seriously deteriorate when the discrepancy between distributions is large. In contrast, score-based DRE methods often yield more accurate estimates in such settings, but they typically require considerable repeated function evaluations and numerical integration. We propose One-step Score-based Density Ratio Estimation (OS-DRE), a partly analytic and solver-free framework designed to combine these complementary advantages. OS-DRE decomposes the time score into spatial and temporal components, representing the latter with an analytic radial basis function (RBF) frame. This formulation converts the otherwise intractable temporal integral into a closed-form weighted sum, thereby removing the need for numerical solvers and enabling DRE with only one function evaluation. We further analyze approximation conditions for the analytic frame, and establish approximation error bounds for both finitely and infinitely smooth temporal kernels, grounding the framework in existing approximation theory. Experiments across density estimation, continual Kullback-Leibler and mutual information estimation, and near out-of-distribution detection demonstrate that OS-DRE offers a favorable balance between estimation quality and inference efficiency.

Wei Chen, Qibin Zhao, John Paisley +2

School of Mathematics, South China University of Technology, Guangzhou 510006, China · Tensor Learning Team, RIKEN Center for Advanced Intelligence Project, Tokyo 103-0027, Japan · Department of Electrical Engineering, Columbia University, New York, NY 10027, USA +1

Density Ratio EstimationEfficient Inference
AskPDF
Apr 9, 2026

Joint Task Offloading, Inference Optimization and UAV Trajectory Planning for Generative AI Empowered Intelligent Transportation Digital Twin

To implement the intelligent transportation digital twin (ITDT), unmanned aerial vehicles (UAVs) are scheduled to process the sensing data from the roadside sensors. At this time, generative artificial intelligence (GAI) technologies such as diffusion models are deployed on the UAVs to transform the raw sensing data into the high-quality and valuable. Therefore, we propose the GAI-empowered ITDT. The dynamic processing of a set of diffusion model inference (DMI) tasks on the UAVs with dynamic mobility simultaneously influences the DT updating fidelity and delay. In this paper, we investigate a joint optimization problem of DMI task offloading, inference optimization and UAV trajectory planning as the system utility maximization (SUM) problem to address the fidelity-delay tradeoff for the GAI-empowered ITDT. To seek a solution to the problem under the network dynamics, we model the SUM problem as the heterogeneous-agent Markov decision process, and propose the sequential update-based heterogeneous-agent twin delayed deep deterministic policy gradient (SU-HATD3) algorithm, which can quickly learn a near-optimal solution. Numerical results demonstrate that compared with several baseline algorithms, the proposed algorithm has great advantages in improving the system utility and convergence rate.

Xiaohuan Li, Junchuan Fan, Bingqi Zhang +3

Guangxi University Key Laboratory of Intelligent Networking and Scenario System (School of Information and Communication, Guilin University of Electronic Technology), Guilin 541004, China · Research Institute of Highway Ministry of Transport, Beijing 100000, China · School of Automation, Guangdong University of Technology, Guangzhou 510006, China +1

Intelligent Transportation SystemsDigital TwinsUAV Trajectory OptimizationEfficient InferenceMulti-Agent Reinforcement Learning
AskPDF
Apr 7, 2026

A Tensor-Train Framework for Bayesian Inference in High-Dimensional Systems: Applications to MIMO Detection and Channel Decoding

Bayesian inference in high-dimensional discrete-input additive noise models is a fundamental challenge in communication systems, as the support of the required joint a posteriori probability (APP) mass function grows exponentially with the number of unknown variables. In this work, we propose a tensor-train (TT) framework for tractable, near-optimal Bayesian inference in discrete-input additive noise models. The central insight is that the joint log-APP mass function admits an exact low-rank representation in the TT format, enabling compact storage and efficient computations. To recover symbol-wise APP marginals, we develop a practical inference procedure that approximates the exponential of the log-posterior using a TT-cross algorithm initialized with a truncated Taylor-series. To demonstrate the generality of the approach, we derive explicit low-rank TT constructions for two canonical communication problems: the linear observation model under additive white Gaussian noise (AWGN), applied to multiple-input multiple-output (MIMO) detection, and soft-decision decoding of binary linear block error correcting codes over the binary-input AWGN channel. Numerical results show near-optimal error-rate performance across a wide range of signal-to-noise ratios while requiring only modest TT ranks. These results highlight the potential of tensor-network methods for efficient Bayesian inference in communication systems.

Luca Schmid, Dominik Sulz, Shrinivas Chimmalgi +1

Communications Engineering Lab (CEL), Karlsruhe Institute of Technology (KIT), Hertzstr. 16, 76187 Karlsruhe, Germany · Technical University of Munich (TUM), Boltzmannstr. 3, 85748 Garching b. München, Germany · Qoherent, Toronto, ON, Canada

Bayesian InferenceEfficient InferenceTT Decomposition
AskPDF