Early-Exit Neural Networks

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 31

Oct 8, 2026cs.AR

DEX: Digit-Level Early Exit for Energy-Efficient MSDF Neural Network Inference

U-Net inference for brain-tumor segmentation requires billions of multiply-accumulate operations, motivating hardware that can reduce computation dynamically rather than relying only on fixed precision or static model compression. Most-significant-digit-first (MSDF) arithmetic exposes the leading digits of a result during computation, enabling output-dependent decisions before the full value is generated. This paper presents an MSDF accelerator for quantized U-Net segmentation with a two-stage grouped processing element supporting signed INT8 operands and in-stream bias accumulation. Four runtime mechanisms operate directly on the output digit stream: exact early negative detection (END) in ReLU layers, exact sign-only decision making in the segmentation head, calibrated low-order-digit skipping, and calibrated pruning. The two approximate mechanisms are selected offline under an accuracy constraint, while execution requires only lightweight control and does not modify the stored weights. On a residual U-Net trained with nnU-Net for BraTS, the proposed mechanisms reduce digit cycles by 38.38% while achieving a mean Dice score of 80.58% on 73 held-out cases, compared with 81.20% for the floating-point model; the exact mechanisms alone reduce cycles by 18.79% without altering the quantized output. Synthesized in 45~~nm, the processing element operates at 500~~MHz, occupies 0.858~~mm $^2$ , and consumes 0.726~~mJ per

192\times192

patch under switching-activity-annotated power analysis. A projected eight-output accelerator with shared activation delivery achieves 16.6~~ms latency and 1.67~~mJ per patch.

Yousef Sadegheih, Dorit Merhof, Muhammad Usman

Faculty of Informatics and Data Science, University of Regensburg, 93053 Regensburg, Germany

Efficient Neural Network Inference Early-Exit Neural Networks U-Net

Sep 24, 2026eess.AS

Does per-frame early exit pay? A compute-matched study of dynamic depth for on-device speech enhancement

Deep learning-based speech enhancement is increasingly deployed on-device in hearing aids, headsets, and earbuds. Most of these devices, however, can only accelerate static int8 graphs, so a depth-varying network must be implemented as several graphs, orchestrated by a policy. In this paper, we supervise every intermediate depth of one causal model, then we fine-tune its output heads to guarantee that deeper outputs are never worse than shallower ones. Using this training protocol, we can derive a family of static models that are more Pareto-efficient than their equivalently-sized counterparts trained from scratch on the same budget. Specifically, we achieve up to 0.11 higher PESQ for equivalent compute, and match the best PESQ at 30% less compute. We then quantize the models to int8 and measure the latency-quality frontier on an STM32N6 microcontroller. On VoiceBank-DEMAND, the dynamic enhancer lies on the same frontier as the static models, rather than trading quality for dynamic execution. Running the policy on the companion Cortex-M55 takes only 26

μ

s per frame, while splitting the enhancer into separate NPU graphs adds 2.2% latency overhead. The cost of dynamic execution is therefore small.

Clément Laroche, Riccardo Miccini

GN A/S, Denmark · Technical University of Denmark, Denmark

Efficient Neural Network Inference Speech Enhancement Early-Exit Neural Networks On-Device Inference

Sep 14, 2026cs.NI

Proportional-Fair Resource Allocation and Dual-Threshold Early-Exit Inference for Secure Cooperative Multi-Layer Edge Intelligence

This paper proposes FREDI (Fair Resource Allocation for Edge Dual-Threshold Inference), a secure wireless edge-intelligence framework for event-triggered inference in a cooperative user equipment (UE)--edge server (ES)--cloud system. Each UE performs early-exit convolutional neural network (CNN) screening using dual confidence thresholds, while critical events are securely offloaded to an edge server for detailed classification. We formulate a proportionally-fair utility maximization problem that jointly optimizes UE--ES association, wireless and processing resources, and confidence thresholds. FREDI decomposes the problem into proportional-fair resource allocation and dual-threshold inference optimization. We prove that the detected-critical event set is set-monotone non-increasing in both thresholds, and exploit the finite empirical confidence domain for exact threshold optimization. An empirical resource--utility response envelope yields a computable global suboptimality bound and a sufficient condition for global optimality. By pre-eliminating infeasible UE--ES pairs and exactly projecting out bandwidth and transmit-power variables, the resource-allocation subproblem is reduced to a mixed-integer exponential-cone program solvable to the certified global optimality within a prescribed gap. Numerical results with early-exit MobileNetV2 and ShuffleNetV2 demonstrate near-perfect UE fairness with aggregate utility close to a Sum-Utility benchmark, reveal security-induced resource fragmentation, and demonstrate the Stage-A scalability from 6 to 144 UEs with median solving time below 0.1~s in the tested configurations.

Thai T. Vu, John Le, Tu N. Nguyen +3

School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia · Department of Computer Science, Kennesaw State University, Georgia, USA · CodeZX Software Company Limited, Vietnam

Edge Inference Fair Resource Allocation Wireless Resource Allocation Early-Exit Neural Networks

Sep 14, 2026cs.AR

Adaptive AI: Energy Efficient Multi-exit TinyML on Intelligent Vision Systems at the Edge

Traditional TinyML systems for edge devices achieve high accuracy by relying on fixed-depth models that require a constant number of multiply-accumulate (MAC) operations regardless of the input complexity. This approach wastes critical resources in battery-powered Internet-of-Things (IoT) devices and limits the real-time performance of edge cyber-physical systems. Multi-exit execution schemes mitigate these issues and are widely used on high-end devices such as GPUs, but are rarely exploited on edge IoT devices because they require substantial rethinking given their strict memory and computational constraints. We address these aspects by designing and deploying, on an ultra-low-power GWT GAP9 System-on-Chip (SoC), a novel multi-exit computational scheme, demonstrating it on a MobileNetV2 convolutional neural network (CNN) for the ImageNet-100 classification task. Our approach introduces multiple exits at different CNN depths, each with a confidence-based gating mechanism that dynamically and autonomously decides whether to continue or stop inference. Comparing our multi-exit strategy to the standard MobileNetV2 on a GAP9 SoC, we show a 41% reduction in the average computational cost (from 313 MMAC to 185 MMAC), a 29% lower inference time (from 49 to 35 ms), and an energy saving of 24% (from 2.1 to 1.6 mJ per frame). All these improvements come with a ~1% loss in accuracy compared to the full-depth MobileNetV2, which achieves 80.5%. Finally, comparing our adaptable multi-exit scheme with a third-party state-of-the-art adaptive CNN, also deployed on the GAP9, we achieve more than 2x its computational efficiency, increasing it from 8.1 to 17.2 MAC/cycle.

Luca Crupi, Lorenzo Lamberti, Alessandro Giusti +1

IDSIA, SUPSI, Lugano, Switzerland · IIS, ETH Zürich, Switzerland

Efficient Neural Network Inference Energy-Efficient ML Edge Inference Tiny ML Adaptive Computation Early-Exit Neural Networks

Sep 14, 2026cs.LG

Theoretical Guarantees for One-Shot Magnitude Pruning and Compute-Adaptive Early Exit

We study compute reduction in neural networks through a unified partial versus full computation view, captured by one-shot magnitude pruning in the static regime and early exit in the adaptive regime. In an asymptotic single-neuron model, we prove a concentration theorem for one-shot magnitude pruning with explicit rates. We also introduce the conditional perceptron for early exit and show that its excess generalization error decays as a power of the compute gap, with an exponent that grows to infinity as the alignment between partial and full computations tends to one. We then extend the analysis to deep networks, characterizing how pruning-induced distortions accumulate with depth and deriving a corresponding compute-accuracy tradeoff for frozen-backbone early exit under a neural network Gaussian process model. Numerical simulations corroborate the predicted scaling laws.

Erdem Koyuncu

Department of Electrical and Computer Engineering, University of Illinois Chicago, IL, USA.

Neural Network Generalization Early-Exit Neural Networks Neural Network Pruning

Sep 3, 2026cs.CL

</think> Doesn't Stop Reasoning: Analysis of Spurious CoT Termination

Chain-of-thought (CoT) reasoning improves large reasoning models (LRMs) on complex tasks but often produces long, redundant traces. Recent training-free early-exit methods shorten these traces by choosing an intermediate point to stop reasoning. We study one such strategy that injects an end-of-think token (EoT, </think>) at this point to trigger the reasoning-to-answering transition, and find that the injected EoT does not always induce a clean answering phase. Answering-phase generation can continue before the model regenerates another EoT, with the span preceding this regenerated EoT scaling with the reasoning tokens saved by early exit and exhibiting continued reasoning behavior. We call this spurious CoT termination, where reasoning-like generation continues into the answering phase. We hypothesize that insufficient attention to the injected EoT contributes to spurious CoT termination and probe this hypothesis with Exit-token Attention Biasing (EAB). Across four LRMs, five benchmarks, and two early-exit methods, increasing attention to the injected EoT reduces spurious CoT termination and answering-phase length. These results reveal a limitation of controlling LRMs by externally matching their explicit think-block format. Inserting the EoT token conforms to this format but does not by itself guarantee the intended reasoning-to-answering transition. Our code is available at https://github.com/Seunghee-Koh/Spurious-CoT-Termination.

Seunghee Koh, Sungjae Choi, Minchan Kwon +2

Korea Advanced Institute of Science and Technology, South Korea

CoT Reasoning Efficient Language Model Reasoning Efficient Language Model Inference Early-Exit Neural Networks Large Reasoning Models

Aug 6, 2026cs.RO

Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion Features

Large video diffusion models provide rich spatiotemporal priors for autonomous driving, but existing world-action models often inherit the cost of iterative future-video generation even though deployment only requires an ego trajectory. We ask a more basic question: how much of a video diffusion model must be executed to make a reliable driving decision? Through a controlled study of video denoising timesteps and Diffusion Transformer (DiT) depth, we find that planning performance is largely insensitive to the tested video-noise levels, whereas strong trajectories can already be decoded from intermediate layers. Based on this observation, we introduce Adaptive-WAM, a quality-aware multi-exit planner built on a Wan2.2-5B backbone. Trajectory diffusion heads are attached to selected DiT blocks, and a lightweight trajectory-quality scorer terminates inference once the best trajectory decoded so far satisfies a quality threshold; otherwise, computation continues from the cached hidden state to a deeper exit. The deployed planner therefore avoids the iterative classifier-free denoising loop and VAE decoding required for future-video synthesis, while dynamically allocating backbone depth according to trajectory quality. On NAVSIM, the adaptive single-trajectory planner achieves 90.8 PDMS; a separate fixed-exit variant reaches 92.6 PDMS with 64 proposals. It further obtains 89.9 EPDMS on NAVSIM v2, yielding the best reported results among the compared front-view video world-model planners. Without target-domain fine-tuning, Adaptive-WAM transfers to nuScenes with 0.88 m average L2 error and a 0.08% collision rate. On an A100, adaptive routing improves PDMS from 90.62 to 90.79 while averaging 170 ms end-to-end planning latency, approximately 10% below the 190 ms fixed block-15 planner and 47% below the 320 ms fixed full-depth planner. Code will be released.

Sining Ang, Yuguang Yang, Yan Wang

Institute for AI Industry Research (AIR), Tsinghua University · Department of Automation, University of Science and Technology of China · School of Electronic Information Engineering, Beihang University

Efficient Inference Diffusion Transformer Diffusion-Based Planning World Models for Autonomous Driving Autonomous Driving Planning Diffusion Model Inference Acceleration+1

Aug 4, 2026cs.AI

Diversity is Not Ambiguity: Toward Accurate and Efficient Ambiguity Detection for Open-Domain QA

How can question answering (QA) systems determine whether a query is ambiguous? Ambiguity detection is essential in open-domain QA, as misclassification leads to answering the wrong interpretation or unnecessary clarification. However, existing methods conflate answer diversity with ambiguity, leading to inaccurate predictions. They also process queries uniformly, resulting in wasteful computation. We propose ARCHIVE (Ambiguity Recognition via Cascaded Hypothesis Inspection and Conflict Verification), an accurate and efficient framework that detects ambiguity via logical conflict: a query is ambiguous when its valid answers cannot all be true under a single interpretation. ARCHIVE combines a lightweight early-exit encoder for surface-detectable cases with a conflict reasoning module that models logical relations among answers, reinforced by an invariance objective for robustness to noisy answer sets. We present QuireQA, a 4,703-query benchmark spanning factoid, non-factoid, and ill-formed queries. Experiments show ARCHIVE outperforms competitors, improving F1-amb by up to 10.4% and F1-unamb by up to 21.6%, while operating 16

\times

faster than the best competitor.

Jiwon Lee, Yong-chan Park, Jungin Hong +1

Seoul National University

Question Answering Open-Domain QA Early-Exit Neural Networks

Aug 2, 2026cs.LG

Stop When Memory Suffices: Evidence-Conditioned Progressive Execution for LLM Agents

The continued development of LLMs toward persistent and adaptive intelligence increasingly requires long-term memory mechanisms that preserve and reuse information across interactions. Existing memory systems either compress and structure histories for efficient access or perform deep research over broader trajectories. The former lowers online cost but may omit temporal, causal, or cross-step dependencies, while the latter improves evidence coverage at substantial latency and inference cost. This raises a key question: can a memory system achieve strong answer quality while maintaining low online latency? We introduce Router-Mem, an evidence-conditioned progressive execution framework for long-horizon agent memory. Router-Mem first applies a shared low-cost retrieval prefix to obtain evidence. A lightweight sufficiency router then predicts whether the context supports early termination, which enable a single-token decision at inference time. It is trained with evidence-level supervision and rationale-conditioned representation distillation. When evidence is insufficient, Router-Mem reuses retrieval hits to expand memory blocks and perform deeper analysis and aggregation. Experiments on AMA-Bench and BEAM show that Router-Mem achieves 55.17% and 38.77% score while reducing average inference time by 27.3% and 25.5% compared with full memory execution.

Yidan Lin, Kaixiang Wang, Jiong Lou +1

LLM Inference Efficiency Efficient Inference LLM Agent Memory Long-Horizon LLM Agents Agent Memory Management Early-Exit Neural Networks

Jul 31, 2026cs.CV

Real-Time Visual Obstruction Detection in Surgical Augmented Reality

Surgical augmented reality (AR) can provide contextual guidance by overlaying virtual annotations, tool cues, and procedural information onto the surgical workspace. However, the virtual content may obstruct task-relevant real-world information, such as surgical instruments, and interfere with users' perception during time-sensitive surgical tasks. In this paper, we investigate visual obstruction detection for surgical AR and present a latency-aware pipeline that combines vision-language model (VLM)-based surgical-object recognition with segmentation-based obstruction reasoning. To reduce inference overhead, the system adopts a cascaded small-to-large VLM architecture with segmentation-guided early exiting and attention-based visual token pruning. The small VLM handles easy frames when its key-object prediction is supported by segmentation consistency, while difficult frames are forwarded to a large VLM with pruned visual tokens. We construct a pseudo-AR surgical obstruction detection benchmark by overlaying virtual content onto surgical-tool images and labeling whether the virtual content obstructs task-relevant instruments. Evaluation results show that the proposed system achieves 87.43% obstruction detection accuracy with an average end-to-end latency of 479 ms, reducing latency by 62.90% compared with a cloud large-model baseline. These results demonstrate the feasibility of latency-aware obstruction detection for surgical AR and motivate future work on dynamic surgical videos, multi-object scenes, and clinically grounded AR guidance content.

Shih-Chin Yang, Yanming Xiu, Hanting Ye +3

Department of Computer Science, Duke University · Department of Electrical and Computer Engineering, Duke University

Efficient Inference Medical VLMs Early-Exit Neural Networks

Jul 31, 2026cs.CL

BLADE: Boundary-Expanded and Layer-Adaptive Dynamic Exit for Efficient LLM Reasoning

Large language models often improve task performance by generating long reasoning traces, but the resulting computation is frequently wasted on redundant verification and revision. Existing probe-based early-exit approaches mainly inspect explicit self-doubt expressions, leaving many earlier termination opportunities undetected. Expanding inspection to ordinary reasoning boundaries improves coverage, but also exposes highly diverse intermediate states whose predictive information may reside in different hidden layers. We present Boundary-Expanded and Layer-Adaptive Dynamic Exit for Efficient LLM Reasoning (BLADE), a lightweight framework that dynamically terminates reasoning by estimating whether the generated prefix is sufficient for correct answering. BLADE constructs multi-granular checkpoints from sentence, self-doubt, and paragraph boundaries, and derives robust training labels through repeated answer completions. It further learns a compact subset of informative probe layers instead of relying on fixed choices or expensive representations from all layers. At inference time, calibrated predictions are combined with checkpoint-specific confirmation rules to balance responsiveness and premature-exit risk. Experiments on five benchmarks and two Qwen3 reasoning models show that BLADE preserves near-baseline accuracy while reducing generated tokens by 24.8% on Qwen3-8B and 15.8% on Qwen3-4B. Ablation studies further confirm the benefits of diverse checkpoints and automatic layer selection, demonstrating an effective approach to more efficient LLM reasoning.

Keshu Fu, Keqin Peng, Jun Bai +6

School of Computer Science and Engineering, Beihang University · Beijing Institute for General Artificial Intelligence, BIGAI · Academy for Advanced Interdisciplinary Studies, Peking University +1

Efficient Language Model Reasoning Efficient Language Model Inference Language Model Probing LLM Reasoning Early-Exit Neural Networks

Jun 28, 2026eess.SP

Fast Wireless Foundation Models with Early-Exits

While wireless foundation models (FMs) are demonstrating strong potential to enable AI-Native 6G networks, their high computational cost remains a critical barrier to deployment. The large computational cost stems from the rigid, full-depth execution of the FM backbone for every task, a process we show is not only inefficient but can also degrade performance on unseen out-of-distribution (OOD) tasks. In this paper, we propose a novel early-exit FM framework that attaches lightweight, per-task heads, at the most appropriate exit-stage of a frozen wireless FM encoder, enabling variable-depth inference tailored to each task's preferred representation depth. Our results demonstrate that these intermediate-layer features not only speed-up inference significantly (up to 93% fewer FLOPs), but also provide more transferable representations that exceed the full encoder accuracy on unseen tasks. We further demonstrate that a simple fixed-exit strategy per task is more effective than traditional early-exiting policies that route different samples to different exits based on their perceived difficulty levels.

Omar Mashaal, Hatem Abou-Zeid

Department of Electrical and Software Engineering, University of Calgary, Calgary, AB T2N 1N4, Canada

Wireless Foundation Models Efficient Inference Early-Exit Neural Networks

Jun 20, 2026cs.LG

Early-Exit Graph Neural Networks for Link Prediction

Graph Neural Networks are great for link prediction in various network-like structures; however, the question of their speed/quality tradeoff has been barely studied. While in practice the time it takes to do inference matters little for small benchmarks, the latency does limit applicability in large-scale domains. In this work, we explore early-exiting strategies that can be applied to Graph Neural Networks to solve the problem of link-prediction faster. We use no auxiliary losses to enforce early exiting, allowing it to emerge as an implicit property of the architecture. We show that our method enables early exiting in several setups, moving the Pareto frontier on the HeaRT benchmark for GCN and SAS-GNN backbones. Our findings show that inference speed of GNNs on many link-prediction problems can be improved, while losing little, or even winning in terms of prediction quality. The code is available in our repository: https://github.com/knyazer/link_prediction.

Roman Knyazhitskiy, Andrea Giuseppe Di Francesco

University of Cambridge · Sapienza University of Rome

Efficient Neural Network Inference Graph Neural Networks Link Prediction Early-Exit Neural Networks

Jun 13, 2026cs.CV

Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models

Existing Vision-Language-Action (VLA) models predominantly rely on explicit Chain-of-Thought (CoT) reasoning to bridge perception and action. While effective, this paradigm suffers from high computational costs and error propagation in multi-step tasks. In this paper, we propose Adaptive Variable Alignment VLA (AVA-VLA), a novel Latent Reasoning VLA framework that models reasoning as a sequence of unobservable latent variables, bypassing the need for explicit text generation. However, latent trajectories are inherently susceptible to noise interference and misalignment with downstream objectives. To address this, we introduce a Reinforcement Learning-based Denoising mechanism that treats latent state generation as a sequential decision process, optimizing reasoning trajectories via task-level rewards. Furthermore, we incorporate an Early-Exit Strategy that adaptively terminates reasoning based on state confidence, enabling a dynamic trade-off between depth and efficiency. Extensive experiments on embodied decision benchmarks demonstrate that AVA-VLA achieves a 6x inference speedup over explicit CoT methods while attaining a 98.3% average success rate on LIBERO, improving both efficiency and long-horizon stability over full-reasoning baselines.

Dianqiao Lei, Lianlei Shan

1Tsinghua University, Beijing, China.

Efficient Inference Efficient VLA Model Inference Efficient VLA Models Latent Visual Reasoning Vision-Language-Action Models VLMs for Robotics+3

Jun 10, 2026cs.CV

ViT-FREE: Efficient Face Recognition via Early Exiting and Synthetic Adaptation

Vision Transformers (ViTs) have gained significant attention in computer vision and shown strong potential for face recognition (FR). However, their high computational cost makes deployment on resource-constrained devices challenging, motivating the need for methods that balance efficiency and accuracy. In this work, we investigate early exiting in pretrained ViTs as a simple yet effective training-free strategy for efficient FR inference. Leveraging the uniform feature dimensionality across transformer encoder blocks, we introduce ViT-FREE, a multi-exit framework that enables face verification directly from intermediate representations without modifying or retraining the backbone model, and thus, reducing inference cost. Empirically, we show that patch embeddings and attention maps evolve progressively across depth, exhibiting high similarity between consecutive ViT blocks and increasing alignment with the final representation. This indicates gradual feature refinement and attention convergence, suggesting that intermediate layers already provide stable and discriminative representations suitable for early exiting. Through extensive experiments on multiple FR benchmarks, we systematically analyze the accuracy-efficiency trade-off across exit depths. Our results demonstrate that later exits achieve a highly favorable balance, with exiting at layer 10 yielding up to a 20% speedup while incurring only a 1.5 drop in verification performance on benchmarks such as IJB-C. Also, we propose ViT-FREE_FT, a lightweight exit-specific fine-tuning strategy that adapts only the projection layers using a small synthetic dataset while keeping the transformer backbone frozen. This approach improves the performance of shallow exits while preserving the efficiency benefits and leaving deeper exits largely unaffected.

Tahar Chettaoui, Guray Ozgur, Eduarda Caldeira +2

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

Inference-Time Optimization Efficient ViTs Face Recognition Early-Exit Neural Networks

Jun 5, 2026cs.LG

TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention

Tabular foundation models, exemplified by TabPFN, perform prediction via in-context learning, inferring test labels directly from labeled training examples. They have demonstrated competitive performance, particularly on small-to-medium datasets. However, recent tabular foundation models often improve accuracy with increasingly complex architectures, incurring higher inference cost and limiting practical deployment. In this work, we revisit the original TabPFN design and show that a lightweight row-wise attention-only backbone can remain highly competitive with two simple enhancements: a gated attention stabilization mechanism and a small set of learnable register tokens that provide global context and improve pretraining quality. The resulting model, TabSwift, supports both classification and regression, and is competitive with stronger tabular foundation models (e.g., TabPFN v2 and TabICL) while being more efficient at inference. For latency-sensitive serving, we further introduce an adaptive layer-wise early-exit mechanism that dynamically adjusts inference depth per sample. Overall, TabSwift enables efficient and anytime tabular in-context learning for practical deployments.

Si-Yang Liu, Han-Jia Ye

School of Artificial Intelligence, Nanjing University, China · National Key Laboratory for Novel Software Technology, Nanjing University, China.

Tabular Foundation Models Efficient Inference Attention Mechanisms Tabular ICL Tabular Prediction Early-Exit Neural Networks

May 17, 2026cs.LG

t-gems: text-guided exit modules for decreasing clip image encoder

Multimodal deep neural networks enhance deep comprehension by integrating diverse data modalities. Data from different modalities are typically projected into a shared latent space for similarity computation, but this process is resource intensive due to large image encoders and equal processing of test data during prediction. Early exit methods reduce computational load by utilizing intermediate layers, saving time and memory. However, developing such methods is challenging for multimodal data like image-text pairs. This study investigates the semantic content distributions present in intermediate layers of encoders such as CLIP, which can be derived from textual descriptions. We introduce Text-Guided Exit Modules (T-GEMs) and a rate-based regularizer to control encoder usage costs while maintaining cross-modal understanding performance.

Alberto Presta, Grzegorz Stefanski, Michal Byra +1

Samsung AI Center Warsaw · Institute of Fundamental Technological Research, PAS, Warsaw

Cross-Modal Learning Vision-Language Models Efficient Inference Efficient VLM Inference Multimodal Embedding Early-Exit Neural Networks

May 12, 2026cs.CV

Trajectory-Aware Adaptive Inference in Object Detection Models

The increasing integration of sensors in autonomous maritime navigation has led to large-scale multimodal datasets, raising challenges in achieving efficient real-time perception. In such systems, object detection and trajectory perception of nearby vessels are tightly coupled, particularly in dynamic environments such as maritime navigation. However, the efficiency of object detection models during inference remains an often-overlooked aspect. To this end, we build upon an existing object detection framework by incorporating GPS trajectory data into the inference process to enable input-adaptive computation. Specifically, we introduce an early-exit mechanism in a YOLOv8-based detector that incorporates motion cues - such as inter-vessel distances. Frames of vessels that are separated by short distances, converging with high speed, are processed using the full model, while only a subset of the network's architecture is activated otherwise. The difficulty degree (or scene complexity) of a frame or set of frames per second is evaluated by leveraging inter-object distance and the rate at which the distance between them decreases. Experimental results demonstrate that this strategy maintains satisfactory detection performance while significantly reducing inference time and computational cost, thus enabling a flexible trade-off between accuracy and efficiency compared to full-model inference.

Grigorios Papanikolaou, Ioannis Kontopoulos, Giannis Spiliopoulos +2

Department of Electrical and Computer Engineering, National Technical University of Athens, Greece · Department of Product and Systems Design Engineering, University of the Aegean, Syros, Greece

Adaptive Inference Dynamic Neural Networks Object Detection Real-Time Object Detection Early-Exit Neural Networks

May 8, 2026cs.CV

Amortized-Precision Quantization for Early-Exit Vision Transformers

Vision Transformers (ViTs) achieve strong performance across vision tasks, yet their deployment with low-precision early exiting remains fragile. Existing quantization methods assume static full-depth execution, making them unstable when exit decisions are perturbed by quantization noise, which can amplify errors along dynamic inference paths. In this paper, we introduce Amortized-Precision Quantization (APQ), a utilization-aware formulation that accounts for layer-wise stochastic exposure to quantization noise and reveals depth-precision trade-offs. Building on APQ, we propose Mutual Adaptive Quantization with Early Exiting (MAQEE), a bi-level framework that jointly optimizes exit thresholds and bit-widths under explicit risk control to improve inference stability. MAQEE establishes a superior Pareto frontier in the accuracy-efficiency trade-off, reducing BOPs by up to 95% while maintaining accuracy and outperforming strong baselines by up to 20% across classification, detection, and segmentation tasks.

Rui Fang, Hsi-Wen Chen, Ming-Syan Chen

National Taiwan University

Mixed-Precision Quantization Dynamic Neural Networks Vision Transformer Efficient ViTs Neural Network Quantization Early-Exit Neural Networks

May 6, 2026cs.LG

Balancing Stability and Plasticity in Sequentially Trained Early-Exiting Neural Networks

Early-exiting neural networks enable adaptive inference by allowing inputs to exit at intermediate classifiers, reducing computation for easy samples while maintaining high accuracy. In practice, exits can be trained sequentially by incrementally adding them to a shared backbone; however, this sequential training can cause newly introduced exits to interfere with previously learned ones, degrading the performance of earlier classifiers. We address this problem by retaining the knowledge embedded in existing exits while allowing new ones to specialize. We propose two alternative approaches that operate at different levels of the model. The first constrains learning by protecting parameters that are important for previously trained exits, while the second preserves the output distributions of earlier exits as the network adapts. These alternatives directly reflect the stability-plasticity trade-off studied in continual learning. Accordingly, we leverage \textit{Elastic Weight Consolidation} to constrain critical weights and \textit{Learning without Forgetting} to preserve output distributions. Experiments on standard benchmarks show that our approaches consistently improve early-exit performance, achieving higher accuracy over existing sequential training methods and significant performance speedups at low computational budgets.

Alaa Zniber, Ouassim Karrakchou, Mounir Ghogho

⋆TICLab, International University of Rabat, Morocco · ‡ School of Electronic and Electrical Engineering, University of Leeds, UK

Adaptive Inference Dynamic Neural Networks Early-Exit Neural Networks Catastrophic Forgetting

May 1, 2026cs.LG

LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference

Layer-aligned distillation and convergence-based early exit represent two predominant computational efficiency paradigms for transformer inference; yet we establish that they exhibit systematic incompatibility under standard deployment conditions for convergence-based early exit. Distillation objectives that align intermediate student layers to teacher representations suppress the representational convergence that early-exit mechanisms exploit, rendering such mechanisms ineffective on distilled models. We introduce LEAP (Layer-wise Exit-Aware Pretraining), an auxiliary training objective that reconciles this incompatibility. LEAP requires no architectural modifications; it augments standard distillation with a single constraint ensuring intermediate layers approximate final-layer representations. LEAP-MiniLM achieves 1.61

\times

measured wall-clock speedup (batch=1, NVIDIA L4) at

θ

=0.95, with 91.9% of samples exiting by layer 7 and 1.80

\times

theoretical layer reduction, where standard distilled models achieve zero effective speedup. We validate across sentence similarity (STS-B: 0.760

\pm

0.006) and retrieval benchmarks (BEIR), providing operational guidance including latency measurements, decision thresholds, and deployment criteria.

Shashank Kapadia, Deep Naryan Mishra, Sujal Reddy Alugubelli +4

Walmart Inc. · Sam’s Club

Efficient Transformer Inference Dynamic Neural Networks Language Model Distillation Teacher-Student Learning Knowledge Distillation Early-Exit Neural Networks

Apr 27, 2026cs.LG

A Comparative Analysis on the Performance of Upper Confidence Bound Algorithms in Adaptive Deep Neural Networks

Edge computing environments impose strict constraints on energy consumption and latency, making the deployment of deep neural networks a significant challenge. Therefore, smart and adaptive inference strategies that dynamically balance computational cost or latency with predictive accuracy are critical in edge computing scenarios. In this work, we build on Adaptive Deep Neural Networks (ADNNs) that employ the Multi-Armed Bandit (MAB) framework. Current literature leverages the first version of the Upper Confidence Bound (UCB1) strategy to dynamically select the optimal confidence threshold, enabling efficient early exits without sacrificing accuracy. However, we introduce four additional Upper Confidence Bound strategies in ADNNs, namely UCB-V, UCB-Tuned, UCB-Bayes, and UCB-BwK, and perform, for the first time, a comparative study of these strategies with respect to trade-offs between accuracy, energy consumption, and latency. The proposed UCB strategies are employed on the ResNet and MobileViT neural networks, and are evaluated on the benchmark datasets of CIFAR-10, CIFAR-10.1, and CIFAR-100. Experimental results demonstrate that all strategies achieve sub-linear cumulative regret, with UCB-Bayes converging the fastest, followed by UCB-Tuned and UCB-V. Finally, UCB-V and UCB-Tuned dominate the Pareto Frontiers of accuracy-latency and accuracy-energy trade-offs. The implementation code is available here: https://github.com/gr3gor1/MAB_UCB

Grigorios Papanikolaou, Ioannis Kontopoulos, Konstantinos Tserpes

Department of Electrical and Computer Engineering National Technical University of Athens, Greece

Multi-Armed Bandits Dynamic Neural Networks Energy-Efficient ML Edge Computing UCB Algorithms Adaptive Computation+1

Apr 27, 2026cs.LG

Progressive Approximation in Deep Residual Networks: Theory and Validation

The Universal Approximation Theorem (UAT) guarantees universal function approximation but does not explain how residual models distribute approximation across layers. We reframe residual networks as a layer-wise approximation process that builds an approximation trajectory from input to target, and prove the existence of progressive trajectories where error decreases monotonically with depth. It reveals that residual networks can implement structured, step-by-step refinement rather than end-to-end (E2E) black-box mapping. Building on this, we propose Layer-wise Progressive Approximation (LPA), a theoretically grounded training principle that explicitly aligns each layer with its residual target to realize such trajectories. LPA is architecture-agnostic: we observe progressive behavior in residual FNNs, ResNets, and Transformers across tasks including complex surface fitting, image classification, and NLP with LLMs for generation and classification. Crucially, this enables ``train once, use

N

models": a single network yields useful predictions at every depth, supporting efficient shallow inference without retraining. Our work unifies approximation theory with practical deep learning, providing a new lens on representation learning and a flexible framework for multi-depth deployment. The source code will be released unpon acceptance at https://(open_upon_acceptance).

Wei Wang, Xiao-Yong Wei, Qing Li

Department of Computing, the Hong Kong Polytechnic University.

Efficient Neural Network Inference Residual Learning Universal Approximation Neural Network Approximation Theory Early-Exit Neural Networks

Apr 21, 2026cs.CV

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 Inference Efficient Inference Vision Transformer Image Quality Assessment Early-Exit Neural Networks

Apr 20, 2026cs.CL

River-LLM: Large Language Model Seamless Exit Based on KV Share

Large Language Models (LLMs) have demonstrated exceptional performance across diverse domains but are increasingly constrained by high inference latency. Early Exit has emerged as a promising solution to accelerate inference by dynamically bypassing redundant layers. However, in decoder-only architectures, the efficiency of Early Exit is severely bottlenecked by the KV Cache Absence problem, where skipped layers fail to provide the necessary historical states for subsequent tokens. Existing solutions, such as recomputation or masking, either introduce significant latency overhead or incur severe precision loss, failing to bridge the gap between theoretical layer reduction and practical wall-clock speedup. In this paper, we propose River-LLM, a training-free framework that enables seamless token-level Early Exit. River-LLM introduces a lightweight KV-Shared Exit River that allows the backbone's missing KV cache to be naturally generated and preserved during the exit process, eliminating the need for costly recovery operations. Furthermore, we utilize state transition similarity within decoder blocks to predict cumulative KV errors and guide precise exit decisions. Extensive experiments on mathematical reasoning and code generation tasks demonstrate that River-LLM achieves 1.53 to 2.16 times of practical speedup while maintaining high generation quality.

Yingtao Shen, An Zou

Shanghai Jiao Tong University Shanghai, China

Decoder-Only Language Models KV-Cache Management LLM Inference Acceleration Early-Exit Neural Networks

Apr 18, 2026cs.AI

Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning

Large reasoning models that use long chain-of-thought excel at problem-solving yet waste compute on redundant checks. Curbing this overthinking is hard: training-time length penalties can cripple ability, while inference-time early-exit adds system overhead. To bridge this gap, we propose Step-GRPO, a novel post-training framework that internalizes dynamic early-exit capabilities directly into the model. Step-GRPO shifts the optimization objective from raw tokens to semantic steps by utilizing linguistic markers to structure reasoning. We introduce a Dynamic Truncated Rollout mechanism that exposes the model to concise high-confidence trajectories during exploration, synergized with a Step-Aware Relative Reward that dynamically penalizes redundancy based on group-level baselines. Extensive experiments across three model sizes on diverse benchmarks demonstrate that Step-GRPO achieves a superior accuracy-efficiency trade-off. On Qwen3-8B, our method reduces token consumption by 32.0% compared to the vanilla model while avoiding the accuracy degradation observed in traditional length-penalty methods.

Benteng Chen, Weida Wang, Shufei Zhang +2

East China Normal University · Shanghai AI Laboratory · Fudan University +1

RL for Language Model Reasoning LLM Inference Acceleration Early-Exit Neural Networks Large Reasoning Models

Apr 17, 2026cs.LG

When Do Early-Exit Networks Generalize? A PAC-Bayesian Theory of Adaptive Depth

Early-exit neural networks enable adaptive computation by allowing confident predictions to exit at intermediate layers, achieving 2-8

\times

inference speedup. Despite widespread deployment, their generalization properties lack theoretical understanding -- a gap explicitly identified in recent surveys. This paper establishes a unified PAC-Bayesian framework for adaptive-depth networks. (1) Novel Entropy-Based Bounds: We prove the first generalization bounds depending on exit-depth entropy

H(D)

and expected depth

\mathbb{E}[D]

rather than maximum depth

K

, with sample complexity

\mathcal{O}((\mathbb{E}[D] \cdot d + H(D))/ε^2)

. (2) Explicit Constructive Constants: Our analysis yields the leading coefficient

\sqrt{2\ln 2} \approx 1.177

with complete derivation. (3) Provable Early-Exit Advantages: We establish sufficient conditions under which adaptive-depth networks strictly outperform fixed-depth counterparts. (4) Extension to Approximate Label Independence: We relax the label-independence assumption to

ε

-approximate policies, broadening applicability to learned routing. (5) Comprehensive Validation: Experiments across 6 architectures on 7 benchmarks demonstrate tightness ratios of 1.52-3.87

\times

(all

p < 0.001

) versus

>

100

\times

for classical bounds. Bound-guided threshold selection matches validation-tuned performance within 0.1-0.3%.

Dongxin Guo, Jikun Wu, Siu Ming Yiu

The University of Hong Kong, Hong Kong, China · Brain Investing Limited, Hong Kong, China

Neural Network Generalization PAC-Bayesian Generalization Bounds Adaptive Inference Dynamic Neural Networks Early-Exit Neural Networks

Apr 16, 2026cs.AI

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 Inference Edge Inference Neural Network Quantization Neural Network Compression Early-Exit Neural Networks Neural Network Pruning

Mar 3, 2026cs.IT

Channel-Adaptive Edge AI: Maximizing Inference Throughput by Adapting Computational Complexity to Channel States

\emph{Integrated communication and computation} (IC

^2

) has emerged as a new paradigm for enabling efficient edge inference in sixth-generation (6G) networks. However, the design of IC

^2

technologies is hindered by the lack of a tractable theoretical framework for characterizing \emph{end-to-end} (E2E) inference performance. The metric is highly complicated as it needs to account for both channel distortion and artificial intelligence (AI) model architecture and computational complexity. In this work, we address this challenge by developing a tractable analytical model for E2E inference accuracy and leveraging it to design a \emph{channel-adaptive AI} algorithm that maximizes inference throughput, referred to as the edge processing rate (EPR), under latency and accuracy constraints. Specifically, we consider an edge inference system in which a server deploys a backbone model with early exit, which enables flexible computational complexity, to perform inference on data features transmitted by a mobile device. The proposed accuracy model characterizes high-dimensional feature distributions in the angular domain using a Mixture of von Mises (MvM) distribution. This leads to a desired closed-form expression for inference accuracy as a function of quantization bit-width and model traversal depth, which represents channel distortion and computational complexity, respectively. Building upon this accuracy model, we formulate and solve the EPR maximization problem under joint latency and accuracy constraints, leading to a channel-adaptive AI algorithm that achieves full IC

^2

integration. The proposed algorithm jointly adapts transmit-side feature compression and receive-side model complexity according to channel conditions to maximize overall efficiency and inference throughput. Experimental results demonstrate its superior performance as compared with fixed-complexity counterparts.

Jierui Zhang, Jianhao Huang, Kaibin Huang

Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong

Adaptive Inference Edge Inference Early-Exit Neural Networks

Dec 4, 2025cs.CC

Hardware-Algorithm Co-Optimization of Early-Exit Neural Networks for Multi-Core Edge Accelerators

The deployment of Early-Exiting Neural Networks (EENNs) on edge accelerators requires optimizing not only the network architecture but also its hardware deployment. Exit configuration, quantization, and hardware workload mapping interact in non-trivial ways, influencing memory traffic, accelerator utilization, and ultimately the energy-latency trade-off. This work presents a hardware-aware co-design framework for EENNs that jointly optimizes exit configuration, quantization-aware training, and multi-core hardware mapping within a unified NAS process. Leveraging analytical design space exploration, the framework identifies efficient workload mappings for each candidate architecture while providing accurate latency and energy estimates during the search. We further formulate EENN deployment as a constrained multi-objective optimization problem balancing predictive accuracy, energy-latency product, exit overhead, and dynamic inference efficiency. Experimental results on CIFAR-10 demonstrate that the proposed framework achieves over a 50% reduction in energy-latency product compared with static baselines under 8-bit quantization. These results demonstrate that jointly optimizing architecture and deployment is essential for realizing the full efficiency potential of dynamic inference on heterogeneous edge accelerators.

Alaa Zniber, Arne Symons, Ouassim Karrakchou +2

TICLab, International University of Rabat, Morocco · MICAS, KU Leuven, Belgium

Efficient Neural Network Inference Dynamic Neural Networks Edge Inference Hardware-Aware NAS Early-Exit Neural Networks