Efficient VLM Inference

VLM: Vision-Language Model

Follow this topic Ask about this topic

Momentum

38 papers in the last four weeks, up 100% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 322

Jun 23, 2026cs.RO

Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding

The rapid rise of Vision-Language Models (VLMs) in egocentric visual understanding has made low-latency inference in human-robot collaborative (HRC) tasks increasingly critical. Weight pruning techniques developed for VLMs to shrink model size and computation can be readily applied to satisfy the efficiency demands of on-board processing and real-time interactive robotics. Moreover, safe human-robot interaction demands pruning strategies that preserve doubly-correct predictions; outputs must be both accurate and evidentially grounded to mitigate risks and ensure user trust. In this paper, we present a new study of VLM pruning through the lens of doubly-correct prediction. Our experiments surprisingly show that existing pruning methods often preserve the right evidence localization but undermine correct prediction. To address this, we propose a rationale-informed pruning strategy that better aligns evidence with decisions. Benchmark results on egocentric video datasets demonstrate that our method not only achieves the highest prediction accuracy but also outperforms existing approaches in attaining doubly-correct predictions. We aim to stimulate research on efficient and reliable VLMs, ensuring accuracy-driven advances align with the transparency, auditability, and safety required for responsible human-robot interaction and embodied intelligence.

Qitong Wang, Fan Du, Pranav Maneriker +2

Dolby Laboratories, Inc., 1275 Market St, San Francisco, California, 94103, USA · Department of Computer and Information Sciences at the University of Delaware, Newark, DE 19711, USA · Dolby Laboratories, Inc.

Efficient VLM Inference Egocentric Vision VLMs for Robotics Neural Network Pruning

Jun 23, 2026cs.CV

video-SALMONN-R $^3$ : Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding

Video large language models (LLMs) are often constrained by computation and memory budgets, leading them to use reduced frame rates and spatial resolutions, which may cause them to miss critical information for question answering (QA). A practical and efficient solution is a two-stage paradigm: first perform coarse video understanding to localize relevant segments, and then re-watch these segments at higher temporal or spatial fidelity. In this paper, we present video-SALMONN-R

^3

, the first end-to-end video-LLM that enables re-watch through reinforcement learning without relying on chain-of-thought (CoT) cold-start. This design removes the need for costly CoT data annotations and avoids CoT-based supervised fine-tuning (SFT), which can otherwise degrade the pretrained video understanding abilities. To address the mismatch between the reasoning-first behavior induced by re-watch and the answer-first tendency of pretrained video-LLMs, we propose a re-answer strategy, in which the model first produces a direct answer in the first watch and then refines it after re-watching. Finally, to improve question adherence during re-watching, we propose a re-ask mechanism that re-injects the query when revisiting localized segments. Experimental results show that video-SALMONN-R

^3

consistently outperforms both the base model and the QA-SFT baseline, while surpassing prior re-watch-based approaches with significantly lower computational cost. Code, models, and data will be publicly released upon acceptance.

Yixuan Li, Guangzhi Sun, Yudong Yang +1

Tsinghua University · University of Cambridge

Efficient VLM Inference Video QA Video-Language Models RL for VLMs

Jun 23, 2026cs.CV

P-MTP: Efficient Document Parsing via Multi-Token Prediction with Progressive Depth Scaling

Vision-Language Models (VLMs) have revolutionized document parsing by enabling end-to-end mapping from images to structured text, imposing a significant latency bottleneck, particularly for token-dense documents. While Multi-Token Prediction (MTP) has emerged as a promising approach for accelerating inference, its potential is constrained by optimization instability when scaling to deeper look-ahead depth. In this paper, we propose \textbf{P-MTP}, a framework that leverages \textbf{Progressive Multi-Token Prediction} with a lightweight MTP module to scale the look-ahead depth for high-throughput document parsing. Specifically, we introduce Progressive Curriculum Loss that adaptively re-weights different look-ahead depths using cumulative path reliability and retrospective target consistency. By effectively suppressing gradient noise in long-range predictions, P-MTP, facilitates an automated easy-to-hard optimization transition, enabling the model to master increasingly distant look-ahead depths. Furthermore, we propose Confidence-Gated Dynamic Drafting to maximize the effective look-ahead depth and acceptance rate by adaptively calibrating speculative length during inference, thereby minimizing computational waste and further pushing the boundaries of inference speedup. Experimental results across multiple benchmarks and architectures demonstrate that P-MTP, achieves up to a

5\times

speedup with negligible loss in accuracy, providing the first successful validation of extensive look-ahead MTP in the document parsing domain.

Le Xiang, Chenxi Zhai, Shu Wei +5

Department of Computer Vision Technology (VIS), Baidu Inc., China · Tsinghua University, Shenzhen International Graduate School, China

Multi-Token Prediction Efficient VLM Inference Speculative Decoding Document Parsing

Jun 23, 2026cs.CV

Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction

Visual token reduction has emerged as an effective strategy for accelerating Multimodal Large Language Models (MLLMs). Many existing methods prune tokens by ranking text-visual attention scores. However, we show that attention is often dominated by a model-induced prior: even without textual instruction, MLLMs tend to focus on certain task-agnostic regions. Consequently, the attention scores of instruction-conditioned tokens are suppressed, increasing the risk that these tokens are discarded during pruning. To address this issue, we propose Prior-Corrected Token Reduction (PriorTR), a training-free token reduction method that explicitly separates task-conditioned attention from the model-induced prior. PriorTR estimates the attention map of the prior, and contrasts it with the task-conditioned attention distribution to measure the additional usable information contributed by each visual token. Importantly, PriorTR computes both the model-induced prior and the task-conditioned posterior within a single forward pass by introducing a null token that serves as an instruction-agnostic probe in the attention block. This design avoids duplicated propagation. Extensive experiments across multiple multimodal benchmarks and MLLMs demonstrate that PriorTR consistently improves the trade-off between accuracy and efficiency over strong training-free baselines, particularly under aggressive token budgets.

Zengjie Chen, Yuxiang Cai, Jingcai Guo +3

School of Software Technology, Zhejiang University, Ningbo, China · Zhejiang Key Laboratory of Digital-Intelligence Service Technology, China · Hong Kong Polytechnic University, Hong Kong SAR +1

Efficient VLM Inference Multimodal Large Language Models Visual Token Pruning Visual Token Compression

Jun 22, 2026cs.RO

UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models

Mainstream Fast-Slow dual system vision-language-action models decouple a high-frequency action expert from a low-frequency vision-language model for efficiency, yet they face a fundamental frequency dilemma: large update gaps cause semantic drift from stale context, while small gaps erode the intended computational savings. Moreover, because the action expert receives only the VLM's final-layer representation at a single fixed frequency, rich intermediate features are discarded, limiting both information coupling and manipulation precision. Inspired by multi-timescale neural processing in the human brain, we introduce UniFS, a unified fast-to-slow architecture that resolves these challenges through three key designs. First, we stratify the VLM layers into groups with progressively decreasing update frequencies, enabling shallow layers to capture fast-changing dynamics while deeper layers cache stable semantic context. Second, a latent vector inversion mechanism re-routes the interaction order between multi-scale VLM features and the action expert, aligning fast-varying representations with fine-grained action decoding and slow-varying ones with coarse planning. Third, a multi-level supervision strategy enforces a coarse-to-fine learning hierarchy across temporal scales. Together, these designs enable richer cross-frequency information transfer within a single backbone, while the low-frequency pathways additionally preserve temporal context across steps. Experiments on LIBERO show that UniFS achieves state-of-the-art performance (98.3% average success rate, a 2.5% gain over VLA-Adapter baseline) while reducing average inference latency from 36.5~~ms to 17.8~~ms (2.1

\times

speedup). Real-robot experiments on a Franka platform further validate its practical applicability. Code is opensourced at https://github.com/linsun449/UniFS.

Lin Sun, Zhiwei Guan, Conglin Wang +7

JD.com, China · Yiwu Research Institute of Fudan University, China · Tianjin University, China

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

Jun 20, 2026cs.CV

Look Before You Zoom: Adaptive Routing for the Resolution-Context Trade-off in Visual RAG

Vision-Language Models (VLMs) struggle as query-relevant objects become smaller. To address this, recent training-free approaches dynamically retrieve and zoom into local image regions. However, we show that indiscriminately applying retrieval ignores a critical vulnerability: the resolution-context trade-off. Patch-based zooming recovers details for small targets, but can split large objects and destroy global spatial context; attention-based retrieval better preserves large objects, but remains less reliable on tiny details; and global perception is often fastest when retrieval is unnecessary. Motivated by these failure modes, we introduce ViRGo (Visual Retrieval or Global Perception), a lightweight framework that formulates visual retrieval as an adaptive routing problem. ViRGo estimates object scale from the VLM's intrinsic localization heads during the initial forward pass and combines it with semantic token confidence to select between global perception, patch-based retrieval, and attention-based retrieval with minimal additional computation. Experiments across multiple VQA benchmarks and object-size groups show that ViRGo improves the accuracy-efficiency trade-off: it matches patch retrieval on small details, leverages attention-based retrieval for larger objects, and reduces inference time by routing to the global baseline when zooming is unnecessary.

Oanh N. Tran, Thanh Quoc Hung Le, Oscar Chew +2

VinUni-Illinois Smart Health Center, VinUniversity · Texas A&M University

Multimodal RAG Efficient VLM Inference Vision-Language Retrieval Fine-Grained Visual Perception

Jun 19, 2026cs.RO

FleetAgent: Teleoperation Assistant for Autonomous Fleets via Vectorized V2N Messages

Large-scale autonomous fleets rely on teleoperation to resolve rare failures, yet streaming raw sensor data from many vehicles is costly, and remote operators can only monitor a limited number of vehicles at a time. We introduce FleetAgent, a cloud-hosted multimodal large language model (MLLM) assistant that consumes compact vectorized vehicle-to-network (V2N) messages, such as map elements, detected objects, and the ego planned path. It provides a structured natural-language response (including narration, explanation, and evaluation of the plan and scene), along with an intervention urgency score for operator prioritization. To make structured messages compatible with token-based MLLMs, we propose VecFormer, a vector-to-embedding interface with differentiable top-K context selection that bounds context length and GPU KV-cache growth, enabling more efficient batch processing, which is important under the context of cloud-hosted large-scale fleet management. We also construct VecEval, a nuScenes-derived dataset with paired human and synthetic imperfect plans and human-verified language labels, to facilitate the training and evaluation of our proposed system. Our proposed system can reduce uplink payload by up to 625 times compared with raw images and reduce KV-cache memory by 16.54 times compared with original text descriptions. On VecEval, FleetAgent improves Lingo-Judge score by 16.8% and reduces intervention failure rate by 19.9%, compared with Qwen2.5-VL-7B using language descriptions. These results demonstrate that FleetAgent can utilize compact structured V2N messaging to enable efficient, explainable teleoperation monitoring for autonomous fleets.

Juntong Peng, Qi Chen, Deyuan Qu +3

College of Engineering, Purdue University, West Lafayette, IN, USA · Toyota InfoTech Labs, Mountain View, CA, USA

Vision-Language Models VLMs for Autonomous Driving Efficient VLM Inference Robot Teleoperation

Jun 18, 2026cs.CV

TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living

Long Video Question Answering (LVQA) requires identifying sparse, query-relevant evidence within hours-long untrimmed videos. Existing approaches either process videos densely with large vision-language models (VLMs), incurring prohibitive computational cost, or rely on sparse caption-based reasoning, which often misses temporally localized and motion-centric evidence. We introduce TimeProVe, a cost-efficient hybrid framework for temporally grounded reasoning in long videos. TimeProVe first employs lightweight modules to generate action-grounded answer--evidence hypotheses and subsequently invokes an expensive VLM only for targeted verification. The core of our framework lies in the Action-based Candidate Evidence (ACE) module, which converts temporally localized actions into query-conditioned candidate answers and supporting evidence windows through lightweight LLM reasoning. We further introduce OpenTSUBench (OTB), an open-ended benchmark designed to evaluate temporally grounded reasoning in real-world Activities of Daily Living (ADL) scenarios. Experiments show that TimeProVe outperforms the strongest baseline on OTB by 7.3%, while reducing VLM calls by 75% and inference cost by 93%. Furthermore, without explicit temporal grounding training, TimeProVe achieves competitive performance on Charades-STA, and reaches state-of-the-art results when enhanced with grounding VLMs.

Arkaprava Sinha, Dominick Reilly, Siddharth Krishnan +2

University of North Carolina, Charlotte

Temporal Video Grounding Efficient VLM Inference Long-Video QA Temporal QA

Jun 18, 2026cs.CV

ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference

Streaming VideoLLMs must continuously process incoming video while maintaining low query latency, making both video-ingestion throughput and query-time responsiveness critical for real-time deployment. Existing methods largely focus on accelerating individual modules, such as visual encoding, token pruning, or KV-cache compression, but provide limited insight into whether the resulting system can sustain real-time streaming performance. We formulate streaming VideoLLM inference as a coordinated pipeline spanning visual preprocessing, visual encoding, token dropping, and LLM prefilling/decoding. Building on this formulation, we propose ViCoStream (Video Coordinated Streaming), a stage-wise coordinated streaming framework that combines chunk-wise execution, CUDA-stream overlap, visual token control, bounded visual attention, and query-side retrieval to bound per-chunk computation and memory costs. We further provide a systematic study of bottleneck migration, revealing how chunk size, token retention, attention locality, and retrieval scope shape the throughput-accuracy trade-off. Experiments with Qwen2.5-VL-3B/7B-Instruct across multiple streaming benchmarks show that ViCoStream achieves 134 FPS video throughput and less than 50 ms TTFT on a single A100 GPU while maintaining accuracy close to full-history baselines.

Yang Tan, Junlong Tong, Linan Yue +3

Southeast University · Eastern Institute of Technology, Ningbo · Shanghai Jiao Tong University

Streaming Video Understanding Efficient VLM Inference

Jun 17, 2026cs.IR

SAFE-Cascade: Cost-Adaptive Vision-Language Routing for Chart Question Answering

Vision-language models (VLMs) are powerful for chart question answering, but invoking a VLM for every query can be unnecessarily expensive when many questions are answerable from OCR text and lightweight language reasoning. We demonstrate SAFE-Cascade, an interactive system for cost-adaptive chart question answering. Given a chart image and a natural-language question, SAFE-Cascade first extracts chart text with OCR, obtains a provisional answer from a text-only language model, and then uses a learned router to decide whether to accept the text answer or escalate to a VLM. The demo exposes this decision process to users: OCR evidence, text-only answer, routing probability, escalation decision, final answer, estimated cost, and estimated latency are shown side by side. SAFE-Cascade is designed as a transparent interface for understanding when visual grounding is actually needed. Users can upload or select charts, ask questions, inspect the evidence used by each pathway, compare text-only and VLM answers, and adjust the escalation threshold to explore the accuracy-cost frontier. The system is implemented with Azure Document Intelligence for OCR, gpt-5-mini as the text-only model, gemini-2.5-flash-image as the VLM, and a Random Forest router trained on inference-time features. On a held-out ChartQA test split of 375 examples from a 2,500-example experiment, SAFE-Cascade achieves 69.1% unified accuracy with 73.1% VLM invocation, compared with 67.7% accuracy and 100% VLM invocation for the full-VLM baseline. The observed +1.4 percentage-point difference is statistically uncertain, so we interpret SAFE-Cascade as matching full-VLM performance while reducing VLM calls by 26.9% and estimated cost by 9.3%. The demonstration shows how selective modality routing can make multimodal knowledge systems more transparent, tunable, and cost-aware.

Ayush Dwivedi, Qixin Wang, Ashvi Soni +5

Walmart USA · University of Arkansas USA

Visual Question Answering Efficient VLM Inference Chart QA Multimodal Foundation Models Multimodal Understanding

Jun 17, 2026cs.CV

CABLE: Cloud-Assisted Bandwidth-efficient LMM-based Encoding for V2X Systems

Cloud-hosted large multimodal models (LMMs) can provide strong open-vocabulary perception for Vehicle-to-Everything systems, but naively transmitting full-resolution frames from edge to cloud causes severe communication overhead and high cloud-side prefill latency. We present CABLE, a cloud-assisted bandwidth-efficient LMM-based encoding framework for edge-cloud perception. CABLE propagates the previous cloud segmentation mask on the edge using ego-motion compensation, refines it with residual-motion cues, and consolidates disconnected regions via a corridor envelope to form a robust region of interest (ROI). Only ROI-masked images are uploaded, while the cloud segmentation output is fed back as the prior for the next frame, forming a mask-to-ROI-to-LMM feedback loop. Experiments on five datasets (nuScenes, WOD-ZB, Waymo, KITTI, and CADC) show consistent communication savings while largely preserving perception, achieving

73

--

87\%

ROI pixel-coverage reduction with

5

--

8\times

estimated LMM prefill speedup at a modest detection-quality trade-off relative to full-frame inference.

Haohua Que, Zhipeng Bao, Qianyi Wu +1

College of Engineering, University of Georgia, Athens, GA 30602, USA

Efficient VLM Inference Edge Computing Autonomous Driving Perception V2X Communication

Jun 17, 2026cs.RO

Invertible Neural Network Adapter for One-Step Flow Matching in Robot Manipulation

This paper presents an invertible neural network adapter for general robotic manipulation, designed to generate precise high-dimensional actions conditioned on multimodal observations, including visual, linguistic, and proprioceptive inputs, through a one-step denoising process. Built upon a flow-matching formulation, the proposed adapter effectively constrains the action generation trajectory within an invertible latent space, thereby enabling efficient and high-quality dexterous action synthesis with only a single inference step. Compared with conventional iterative flow-matching policies, the proposed framework substantially reduces inference complexity while maintaining strong action prediction accuracy and stability. Extensive experiments are conducted across a diverse set of simulation benchmarks and real-world robotic platforms to evaluate the effectiveness of the proposed method. Across simulation benchmarks, the proposed adapter consistently demonstrates superior or near state-of-the-art performance on a wide range of manipulation tasks. Furthermore, real-world experiments reveal a significant improvement in inference efficiency for vision-language-action (VLA) models, reducing the average inference latency from 110 ms to 61 ms while maintaining strong task performance.

Yu Zhang, Kangyi Ji, Yongxiang Zou +3

Invertible Neural Networks Flow Matching Efficient VLM Inference Robotic Manipulation Vision-Language-Action Models

Jun 17, 2026cs.CV

Moving Beyond Diversity: Visual Token Pruning as Subspace Reconstruction for Efficient VLMs

Despite their remarkable performance, Vision Language Models (VLMs) incur substantial computational overhead due to the large number of visual tokens. While diversity maximization has become a dominant strategy for token reduction, existing methods rely on cosine-based normalized similarity that discards magnitude information, failing to faithfully approximate the original feature representation and leading to suboptimal performance, particularly on compositional multi-skill reasoning tasks. In this paper, we introduce SPARE, a subspace reconstruction method that reformulates token pruning as a column subset selection problem and explicitly minimizes reconstruction error. By iteratively selecting tokens with large projection residuals, SPARE performs reconstruction-driven pruning beyond angular diversity. Moreover, we reveal a counterintuitive anti-relevance phenomenon: tokens with lower image-text relevance score can better preserve contextual information. Based on this finding, we incorporate anti-relevance into SPARE as an additional selection criterion to promote context-aware token selection. Extensive experiments across multiple VLMs and benchmarks demonstrate that SPARE consistently achieves state-of-the-art performance, with strong gains on compositional tasks. When applied to LLaVA, SPARE removes up to 94% of visual tokens while retaining 95% of the baseline performance, all in a fully training-free manner.

Jaeyeon Lee, Shunjie Wen, Dong-Wan Choi

Inha University

Efficient VLM Inference Feature Selection Visual Token Pruning

Jun 15, 2026cs.CV

ActiveSAM: Fast and Accurate Open-Vocabulary Semantic Segmentation with Frozen SAM 3

Segment Anything Model 3 (SAM 3) provides a strong frozen backbone for concept-prompted segmentation, but applying it directly to open-vocabulary semantic segmentation (OVSS) is inefficient: full-resolution decoding is typically run over the entire dataset vocabulary, whereas each image contains only a small active subset of classes. We introduce ActiveSAM, a training-free inference framework that turns SAM 3 into an active-vocabulary segmenter. ActiveSAM first canonicalizes and expands class prompts, then uses evidence-proportional grounding to estimate an image-conditioned active set from a low-resolution presence preview. Only retained prompts receive full-resolution mask prediction, using bucketed prompt multiplexing with the frozen SAM 3 decoder. The preview stage uses only class-presence evidence and skips unnecessary segmentation-head computation. To resolve overlapping concept responses, exclusive concept decoding compares each pixel's joint score vector with class signatures estimated once per vocabulary from unlabeled images. ActiveSAM requires no weight updates, no oracle class-presence labels and no per-dataset hyperparameter tuning. Across eight OVSS benchmarks, ActiveSAM improves the speed-accuracy tradeoff of training-free open-vocabulary semantic segmentation, outperforming the current state-of-the-art SegEarth-OV3 by +2.1 mIoU on average while running much faster, with 7.3-12.2x speedups on large-vocabulary datasets. ActiveSAM also achieves the highest accuracy under image corruptions that simulate real-world distribution shift, making it well-suited for deployment in noisy-input domains such as autonomous driving and embodied AI. Code is available at https://github.com/VILA-Lab/ActiveSAM

Tran Dinh Tien, Zhiqiang Shen

VILA Lab, Mohamed bin Zayed University of Artificial Intelligence

Efficient VLM Inference Open-Vocabulary Semantic Segmentation Segment Anything Models

Jun 15, 2026cs.CV

DCP-Prune: Ultra-Low Token Pruning with Distribution Consistency Preservation

Recent vision token pruning methods effectively preserve model performance under moderate token budgets but become unstable under ultra-low token budget. Our analysis shows that as the pruning budget decreases, accuracy degradation is often accompanied by larger feature distribution shifts. Critically, the degree of this distribution shift strongly correlates with performance degradation. To better characterize this phenomenon, we introduce a lightweight distribution consistency metric to estimate the distribution shift between retained and full tokens. Motivated by these observations, we propose a two-stage pruning framework consisting of Anchor-Context Graph Recovery (ACGR) and Text-Aware Token Cluster Selection (TATCS). Specifically, ACGR transfers contextual information before token removal, while TATCS dynamically re-selects representative tokens when severe distribution shift is detected. Extensive experiments demonstrate that our method achieves superior and more stable performance under ultra-low token budget. Notably, it retains 92.1% of the upper-bound average performance on LLaVA-1.5-7B with only 16 visual tokens.

Xifeng Xue, Xiaokang Wang, Zirui Li +2

College of Computer Science, Nankai University, Tianjin, China · Nanjing University of Posts and Telecommunications, Nanjing, China

Efficient VLM Inference Visual Token Pruning Visual Token Compression

Jun 15, 2026cs.CV

Focus When Necessary: Adaptive Routing and Collaborative Grounding for Training-Free Visual Grounding

While Multimodal Large Language Models (MLLMs) excel in cross-modal reasoning, they often struggle to perceive fine-grained details in complex high-resolution images. Recent training-free methods address this through image scaling and localized cropping. However, applying these manipulations indiscriminately introduces computational redundancy for simple queries and can degrade accuracy by truncating essential global context or introducing irrelevant background noise. To this end, we propose LazyMCoT, a dynamic and training-free framework that adaptively allocates visual grounding efforts based on sample difficulty. The framework features an Adaptive Routing mechanism that evaluates predictive uncertainty using first-token statistics from a single forward pass. This efficiently bypasses confident cases while ensuring the recall of difficult samples via conformal calibration. For these challenging cases, a Collaborative Grounding module integrates the inherent cross-modal attention of the model with an external visual expert through a two-stage refinement process. This refinement process generates a precise localized display to recover small or occluded targets. Extensive experiments across diverse benchmarks demonstrate that LazyMCoT rivals training-based approaches by simultaneously improving reasoning accuracy and reducing average inference latency. Our code is availble at https://github.com/TencentBAC/LazyMCoT.

Yifan Wang, Peiming Li, Shiyu Li +5

1Tencent BAC · School of Electronic and Computer Engineering, Peking University · School of Mathematics and Statistics, University of Glasgow +1

Efficient VLM Inference Large Vision-Language Models Vision-Language Grounding Visually Grounded Reasoning

Jun 13, 2026cs.RO

Acting While Understanding: Asynchronous Semantic-Action Decoupling for Real-Time Vision-Language-Action Models

Vision-Language-Action models (VLAs) have demonstrated strong task understanding and generalization in robotic manipulation, yet the high computational cost of full-model inference limits their deployment in low-latency, high-frequency closed-loop control. We propose an asynchronous semantic-action decoupling framework that separates semantic understanding from action generation along the internal semantic-action interface of existing VLAs, without redesigning the vision-language backbone or introducing an external planner. A low-frequency understanding module asynchronously updates reusable semantic conditions, while a high-frequency action module continuously outputs control actions without repeatedly invoking the full model. To mitigate the temporal mismatch between stale semantics and the current execution state, we further introduce historical action conditioning and time-misalignment training, which provide short-horizon execution context and improve feedback control robustness under stale semantic conditions. Experiments on LIBERO with

π_{0.5}

and UniVLA, together with real-robot deployment using UniVLA, show that the proposed framework achieves up to 35.6 Hz server-side action-module inference throughput and offers a low-intrusion path to high-frequency closed-loop control without running full VLA inference at control rate.

Shenhao Yan, Ge Wang, Qi Liu +7

Northeastern University · Ising AI · CUHK-Shenzhen

Efficient VLM Inference Efficient VLA Model Inference Efficient VLA Models Vision-Language-Action Models Vision-Based Robot Control VLMs for Robotics

Jun 12, 2026cs.RO

Elastic Queries Reinforcement Learning: Self-Aware Policy Execution for VLA Models

Vision-language-action (VLA) models are powerful action generators for robot manipulation, but they are typically executed with fixed inference and replanning schedules. This rigidity ignores the uneven difficulty of robot control: contact-rich or uncertain states may need more computation and fresher feedback, while easier states can often be handled with fewer inference steps and longer open-loop execution. We propose Elastic Queries Reinforcement Learning (EQRL), a framework that makes each VLA policy query elastic. A lightweight latent-schedule adaptor jointly selects the latent input, denoising budget, and action chunk length, without fine-tuning the underlying VLA model. To make scheduling difficulty-aware, EQRL trains a critic over the joint latent-schedule action and derives a state difficulty signal from critic ensemble disagreement. This signal guides compute toward difficult states, while a learned residual allows task-driven correction. We formulate variable chunk execution as query-level macro-action RL with chunk-dependent discounting and an amortized number-of-function-evaluations (NFE) budget. Across simulation and real-robot manipulation, EQRL reduces amortized inference cost while preserving or improving task success.

Ge Wang, Xinyu Tan, Xiang Li +11

Ising AI · CUHK-Shenzhen · PKU

RL for Robotics Efficient VLM Inference Robotic Manipulation Vision-Language-Action Models Test-Time Adaptation of VLA Models

Jun 12, 2026cs.CV

One Layer's Trash is Another Layer's Treasure: Adaptive Layer-wise Visual Token Selection in LVLMs

Large Vision-Language Models (LVLMs) have achieved remarkable success across diverse multimodal tasks, yet their practical deployment remains constrained by the computational burden arising from lengthy visual tokens. While visual token pruning has emerged as a promising solution, existing methods suffer from a fundamental limitation: once tokens are pruned at a specific layer, they become inaccessible to all subsequent layers, leading to premature information loss that can compromise model performance. Through empirical studies, we observe that different layers exhibit distinct visual region focus, indicating a varying optimal token subset across layers. Motivated by this insight, we propose Adaptive Layer-wise Visual Token Selection (ALVTS), a novel framework that breaks away from the conventional static token pruning paradigm. ALVTS incorporates a lightweight token selector to identify and route important tokens for further processing, while allowing less important tokens to skip the layer, thus minimizing computational redundancy. These two streams of tokens are seamlessly reintegrated before being fed into subsequent layers, facilitating adaptive compression across the entire model. Grounded in our importance consistency constrained low-rank approximation, the proposed token selection module closely emulates the full attention mechanism, effectively capturing its essential patterns without requiring model retraining. Extensive experiments on LLaVA-1.5, LLaVA-NeXT, and Qwen2.5-VL validate the effectiveness of our method. With an 89% token compression ratio, ALVTS retains 96.7% of the original model's accuracy, achieving a superior efficiency-accuracy trade-off for LVLM inference.

Yongru Chen, Kai Zhang, Zeliang Zong +4

Hikvision Research Institute · East China Normal University · Peking University

Efficient VLM Inference Large Vision-Language Models Visual Token Pruning Visual Token Compression

Jun 12, 2026cs.RO

ReactVLA: Fast and Lightweight Reactive Robot Manipulation via Improved Mean Flow Action Generation

Diffusion-based Vision-Language-Action (VLA) policies have demonstrated strong capability in modeling expressive and multimodal action distributions. However, their reliance on iterative sampling introduces substantial inference latency, which limits their applicability to reactive closed-loop robot manipulation. To address this limitation, we propose \texttt{ReactVLA}, a lightweight and low-latency VLA framework for real-time robotic manipulation. \texttt{ReactVLA} combines two complementary designs: (1) an improved Mean Flow (iMF) action generator that reduces expensive multi-step diffusion sampling to one-to-few-step action generation, and (2) Attention Residuals (AttnRes), a dynamic depth-wise feature routing mechanism that replaces uniform residual accumulation to better preserve task-relevant multimodal representations. We evaluate \texttt{ReactVLA} on large-scale simulation benchmarks, including LIBERO and RoboIMI, as well as real-world robotic manipulation tasks. Experimental results show that \texttt{ReactVLA} consistently outperforms similarly sized VLA baselines, including SmolVLA and

π_0

. On challenging precision manipulation tasks, \texttt{ReactVLA} achieves up to a 1.65

\times

improvement in task performance while providing more than a 4

\times

increase in inference speed compared with leading VLA models. Finally, it reduces real-world policy latency to below 38.6 ms, enabling fast reactive control on physical robot platforms. Please check out our project website at: https://game-loader.github.io/ReactVLA/.

Yanzhao Guo, Wenkai Chen, Jianwei Zhang

Shanghai Jiao Tong University · Technical Aspects of Multimodal Systems (TAMS), Department of Informatics, Universität Hamburg

Language-Conditioned Robot Manipulation Efficient VLM Inference Attention Residual Connections Vision-Language-Action Models

Jun 12, 2026cs.CV

RT-VLA: Real-Time Vision-Language-Action Models via Knowledge Distillation

Vision-Language-Action (VLA) models have shown strong potential for end-to-end autonomous driving by jointly modeling visual perception, language reasoning, explainability and action prediction. However, their large vision-language backbones and reasoning modules introduce substantial inference latency and thereby prevent their deployment in the unforgiving reality of the road networks. We propose RT-VLA, a lightweight, distilled VLA model that transfers the driving and reasoning capabilities of the state-of-the-art SimLingo model into a compact student through multi-level supervised distillation. RT-VLA preserves language-based reasoning and supports post-hoc explanation through offline language analysis of safety-critical driving moments without adding latency to real-time control. Compared to the SimLingo teacher, RT-VLA maintains competitive closed-loop driving and language reasoning performance while reducing inference time by 44.8X in vision-only mode and 7.9X in vision+language mode. These results suggest that supervised distillation is a practical approach for building real-time, explainable VLA-style autonomous driving models.

Xiangyu Huang, Zhenlin Hua, Han Zhou +2

Carnegie Mellon University

End-to-End Autonomous Driving Efficient VLM Inference VLM Distillation Efficient VLA Model Inference VLM Reasoning Vision-Language-Action Models+1

Jun 10, 2026cs.CV

Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models

Vision-language models (VLMs) project images into hundreds to thousands of visual tokens, making decoder inference expensive in both attention computation and KV-cache memory. Existing visual-token reduction methods largely follow a rank-and-remove paradigm: they score visual tokens, keep a compact subset, and permanently discard the rest. We show that this irreversible action is fragile because visual-token importance changes across decoder depth; tokens ranked low at one stage may become relevant in later layers, especially for grounding-sensitive queries. We propose Reroute, a training-free plug-in that replaces removal with recoverable routing. At each routing stage, selected vision tokens pass through decoder blocks, while deferred tokens bypass the stage and re-enter the candidate pool at the next routing decision. Reroute reuses existing attention-score ranking rules and stage-wise schedules, preserving the theoretical TFLOPs and KV-cache budget class of the pruning method it augments. Across FastV, PDrop, and Nüwa variants on LLaVA-1.5 and Qwen backbones, reroute improves grounding under aggressive token reduction while maintaining general VQA performance. These results suggest that VLM token reduction should not be viewed only as irreversible pruning, but also as recoverable routing. The code can be found here: https://github.com/elmma/mllm-reroute/

Cheng-Yu Yang, Shao-Yuan Lo, Yu-Lun Liu

National Yang Ming Chiao Tung University · National Taiwan University

Efficient VLM Inference Visual Token Pruning

Jun 10, 2026cs.CV

From Content to Knowledge: Lightning Fast Long-Video Understanding with Neural Knowledge Representations

We propose a new paradigm for long video understanding by treating a long video as a Neural Knowledge Representation (NKR). NKR represents video contents neither as a stream of tokens nor pre-organized databases, but as an individual small portion of network weights attached to the VLM backbone. The NKR weights are optimized to encapsulate the video's semantic content via a novel Agentic Knowledge Distillation (AKD) process, where an agent automatically synthesizes dense descriptions and question-answer pairs to distill the video's knowledge into the NKR. While AKD serves as a comprehensive, one-time encoding phase, the resulting NKR transforms the video into a portable, reusable asset. At inference, the lightweight NKR is mounted onto a frozen Vision-Language Model (VLM), enabling direct, query-based understanding without reloading or re-encoding the original video. This approach decouples video length from inference cost, offering high amortized efficiency for multi-turn video understanding. Experiments on the LVBench benchmark show our method achieves performance comparable to state-of-the-art approaches while reducing end-to-end latency by over two orders of magnitude, opening new possibilities for interactive long-video understanding.

Yuchen Guan, Xiao Li, Zongyu Guo +4

Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Microsoft Research Asia

Efficient VLM Inference Long-Video Understanding Long-Video QA Temporal Video Understanding

Jun 10, 2026cs.CV

AVIS: Adaptive Test-Time Scaling for Vision-Language Models

Modern Vision-Language Models (VLMs) benefit from chain-of-thought prompting and test-time scaling, but these gains often come with prohibitive inference cost due to large visual contexts and long decoding chains. We view this cost through two coupled axes: Visual Context Scaling (VCS), which controls how much visual evidence is passed to the language model, and Visual Reasoning Scaling (VRS), which controls how much inference-time reasoning search is performed. Existing methods typically optimize one axis at a time, leaving the joint allocation of compute across these axes underexplored. We introduce Adaptive Visual Inference Scaling (AVIS), a lightweight policy that adapts both VCS and VRS per query. AVIS realizes VCS through Key Diversity Visual (KDV) pruning, a training-free

O(N)

key-based rule for removing redundant visual tokens before prefilling, and realizes VRS through adaptive self-consistency, using a learned difficulty predictor to select the number of reasoning rollouts. AVIS is deployment-friendly and compatible with shared-prefill inference, where all rollouts reuse a single prefilling pass and KV cache. Across diverse image and video reasoning benchmarks, AVIS improves the accuracy--compute trade-off relative to VCS-only and VRS-only baselines, and remains effective on top of RL post-trained VLMs while keeping compute and latency low.

Ahmadreza Jeddi, Minh Ngoc Le, Amirhossein Kazerouni +8

AI Center-Toronto, Samsung Electronics · University of Toronto · Vector Institute +1

Test-Time Adaptation of VLMs Efficient VLM Inference Test-Time Scaling for VLMs Test-Time Scaling VLM Reasoning Visually Grounded Reasoning+1

Jun 7, 2026cs.CV

Thinking Without Images: Internalizing Visual Manipulation with On-Policy Self-Distillation

''Thinking with Images'' has emerged as an effective paradigm for fine-grained visual reasoning: by explicitly zooming into relevant regions and reasoning over crops, models can access local evidence that is difficult to recover from a single global image. However, this benefit comes with redundant tool invocations and longer inference traces. Moreover, when such behaviors are learned mainly from outcome reward, the resulting intermediate crops or visual cues can be noisy or fail to faithfully capture task-relevant visual evidence. In this work, we ask whether the reasoning benefits of ''Thinking with Images'' can be internalized through Thinking with Imagination: an internal process that decides where to look and imagines what visual cues closer inspection would reveal without actually invoking tools. We propose Imagine-OPD, an on-policy self-distillation framework in which a teacher plays the role of a ''Thinking with Images'' reasoner during training: it receives privileged zoomed evidence views derived from annotated regions, and supervises the model's own imagination reasoning trajectories. Imagine-OPD does not require an external teacher or high-quality imagination demonstrations. Experiments on vision-centric benchmarks show that Imagine-OPD achieves the best average performance among compared models while significantly reducing inference overhead compared with ''Thinking with Images'' methods.

Yishuo Cai, Jiahui Liu, Yuanxin Liu +9

1State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University · 2Central South University · University of Science and Technology of China +2

Tool Use in VLMs Efficient VLM Inference On-Policy Self-Distillation Latent Visual Reasoning VLM Reasoning Visually Grounded Reasoning

Jun 7, 2026cs.CV

Learnable Token Sparsification for Efficient Gigapixel Whole Slide Image Reasoning

The processing of gigapixel whole slide images within vision language models faces a major difficulty due to an excessive number of visual tokens. Existing solutions typically rely on spatial downsampling or heuristic pruning strategies that operate without training, and these methods often discard subtle but clinically meaningful patterns because pathological evidence is scattered irregularly across the tissue. To overcome this limitation, we reformulate token reduction in whole slide images as a trainable sparsification problem, allowing the model to learn an optimal selection strategy instead of following fixed heuristics. We propose a decoupled routing architecture. To enable gradient propagation through the nondifferentiable pruning operation during training, we introduce a component called SparseLearn. This component uses a variance-preserving noise gate that regulates the information flow of each patch via a differentiable Soft Top-K operator, together with a diagonal attention denoiser that recovers perturbed representations without leaking spatial information. At inference time, the SparseLearn module is entirely discarded, and the trained scorer applies a deterministic Hard Top-K operator to keep only the highest scoring 32 tokens, incurring no extra computation. By compressing the visual sequence down to a sparse set of just 32 tokens, which represents as little as 0.78% of the original length, our framework achieves 73.32% overall accuracy on SlideBench (TCGA), consistently surpassing sampling-based baselines and general-purpose vision language models. It also demonstrates strong zero shot generalization on SlideBench (BCNB) and WSI VQA*. By resolving the visual context bottleneck and preventing the dilution of sparse diagnostic evidence, this work provides a highly efficient paradigm for end to end gigapixel whole slide image reasoning.

Jingzhi Chen, Landi He, Zhuo Chen +2

Shenzhen University of Advanced Technology

Efficient VLM Inference Medical VLMs Visual Token Pruning Whole-Slide Image Analysis

Jun 6, 2026cs.RO

vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models

Deploying vision--language--action (VLA) models on robots requires adapting model-specific inference pipelines to heterogeneous processors and limited onboard memory. We present vla.cpp, a unified C++ inference runtime for eleven VLA models, with no PyTorch dependency for model execution. The runtime shares model loading, tensor execution, and serving while retaining architecture-specific attention, conditioning, and action heads. Iterative policies reuse observation-dependent computation across solver steps, while regression policies predict actions directly. We evaluate task success on LIBERO-Object and profile supported configurations on NVIDIA, Apple, and Intel hardware. BitVLA completes 200/200 LIBERO-Object episodes on an 8,GB Jetson Orin Nano. A ternary tensor-core kernel accelerates its client inference by

4.0

--

4.6\times

over the CUDA-core baseline on RTX 3060 and AGX Orin. A SmolVLA case study links positional-index precision to gripper commands and task success, showing why fixed-input numerical checks should accompany rollout evaluation. Deployments on UR10e and ALOHA demonstrate physical robot integration; delay and execution-horizon studies characterize synchronous chunked control. The results demonstrate a common deployment path across VLA architectures and hardware, with numerical validation and control settings guiding deployment alongside inference efficiency.

Khanh D. Nguyen, Hung T. Ho, Chinh T. Nguyen +5

VinRobotics, Vietnam · Max Planck Research School for Intelligent Systems, Germany · University of Stuttgart, Germany +3

AI Accelerator Inference Efficient VLM Inference Efficient VLA Model Inference Efficient VLA Models Vision-Language-Action Models VLMs for Robotics

Jun 5, 2026cs.RO

RhinoVLA Technical Report

Vision-Language-Action (VLA) models have shown strong potential for robotic manipulation, but real-time deployment on edge hardware remains challenging. In this work, we identify VLM visual and context tokens as a major source of deployment latency: for GEMM-dominated projection operators, computation grows linearly with the number of input tokens when model dimensions are fixed. Motivated by this observation, we propose RhinoVLA, a deployment-oriented VLA model co-designed with the Huixi R1 edge SoC. RhinoVLA adopts a token-efficient Qwen3-VL backbone and a continuous Action Expert, reducing the VLM-side token and computation burden while preserving pretrained multimodal capability. To support cross-robot learning, RhinoVLA further introduces a unified interface that combines View Registry, 72D physical state-action slot space, and robotinstance LoRA, allowing heterogeneous robot observations and action schemas to be aligned under a shared policy. On the deployment side, RhinoVLA is optimized through hardware-aware compilation, mixed-precision execution, and parallel visual encoding. Experiments show that RhinoVLA achieves downstream performance comparable to π0.5 at a similar parameter scale, while reaching 11.69 Hz end-to-end inference on Huixi R1, meeting the 10 Hz real-time closedloop control target. The project will be open-sourced at https://github.com/HuixiAI/RhinoVLA.

Huixi Technology, :, Chen Zhang +13

Huixi Technology

Efficient VLM Inference Efficient VLA Model Inference Cross-Embodiment Robot Learning Vision-Language-Action Models Vision-Based Robot Control

Jun 5, 2026cs.CV

SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language Models

Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but remain highly fragile under adversarial perturbations. Recent test-time adaptation defenses improve robustness by leveraging many augmented views, but this leads to impractical slowdown and a clear robustness-throughput trade-off. To address this challenge, we present Stability and Suitability-guided Test-time Prompt Tuning (SS-TPT), evaluating the quality of each augmented view via two complementary scores: (1) stability, measuring prediction invariance to weak augmentations, and (2) suitability, measuring feature-space density among views. These stability and suitability (SS) scores guide both adaptation and inference through an SS-guided consistency loss and an SS-weighted prediction, amplifying trustworthy views while suppressing corrupted ones. Extensive experiments demonstrate that SS-TPT significantly outperforms prior state-of-the-art methods, achieving superior robustness-throughput trade-offs across diverse datasets and varying numbers of views, thereby demonstrating both strong practicality and generality. Our code is available at https://github.com/sunoh-kim/SS-TPT.

Sunoh Kim, Daeho Um

Dankook University, Yongin, South Korea · University of Seoul, Seoul, South Korea

VLM Robustness VLM Adaptation Test-Time Adaptation of VLMs Efficient VLM Inference Neural Network Robustness Adversarial Robustness+1

Jun 4, 2026cs.CV

MemoVAD: Resource-Efficient Video Anomaly Detection via Dynamic Semantic Memory in Edge Computing Scenarios

Deploying Video Anomaly Detection (VAD) in real-world surveillance faces a fundamental tension between the demand for high-level semantics to ensure effectiveness and the limited computational resources of edge devices. Vision-Language Models (VLMs) provide rich open-vocabulary semantics, but their latency and computational cost preclude on-device deployment. To address the challenge, we propose MemoVAD, an edge-cloud collaborative framework that selectively incorporates VLM semantics into streaming VAD. MemoVAD runs most inference on the edge with a lightweight detector and a causal Temporal Context Encoder (TCE) to model temporal dependencies. Specifically, we introduce an Uncertainty-Aware Gating (UAG) policy grounded in Subjective Logic to model perceived uncertainty and query the cloud-based VLM only for high-uncertainty and semantically novel clips. Besides, a Dynamic Semantic Memory (DSM) is designed to cache VLM-verified prototypes for efficient retrieval, enabling the edge model to progressively incorporate VLM-level semantics via a semantic adapter. Experiments on UCF-Crime and XD-Violence datasets via a real edge device show that MemoVAD substantially reduces communication overhead while surpassing state-of-the-art performance.

Guo Li, Jiandian Zeng, Yang Li +3

Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai, China · School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China · Engineering Research Center of Cloud-Edge Intelligent Collaboration on Big Data, Ministry of Education, Beijing Normal University, Zhuhai, Guangdong, China

Streaming Video Understanding Efficient VLM Inference Edge Computing Video Anomaly Detection