Efficient Multimodal Inference

Follow this topic Ask about this topic

Momentum

28 papers in the last four weeks, up 211% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 157

May 26, 2026cs.CV

O-MARC: Omni Memory-Augmented Compression Distillation for Efficient Video Understanding

Omnimodal large language models enable unified audio video understanding, but long joint token sequences make inference costly, and existing benchmarks do not fully isolate audio visual association in noisy user generated videos. We introduce UGC-AVQA, a public UGC benchmark with 1,000 videos and 4,816 QA pairs, where an audio removal test ensures that benchmark questions require both acoustic and visual evidence. To reduce inference cost, we propose OMAC, a training free plug in compression method that preserves salient visual memory and temporally grounded audio anchors. To further make compact models robust to compressed inputs, we introduce O-MARC, a compression distillation framework for learning with memory compressed multimodal contexts. On Qwen2.5-Omni-3B, O-MARC improves the average score across four benchmarks to 45.8, outperforming full token inference at 44.1 and OmniZip at 41.0. OMAC also keeps inference efficient, reducing latency by 34.6% (1.53

\times

speedup) and memory by 34.7% compared with full token inference.

Peiran Wu, Yunze Liu, Chi-Hao Wu +2

University of Bristol · Memories.ai Research · University of Central Florida

Audio-Visual Understanding Efficient Multimodal Inference Audio Understanding Multimodal QA Audio-Visual QA Multimodal Token Compression+4

May 25, 2026cs.CV

VEN-VL: A Visual Ensemble MoE Framework for Effective and Efficient Multi-Modal Understanding

Despite the remarkable progress achieved by recent efficient methods in accelerating multimodal understanding, they still suffer from noticeable performance degradation. Their emphasis on the high compression ratio of a single visual clue and reliance on the heuristic pruning strategy with coarse attention alignment incurs a bottleneck on the information capacity and density of visual tokens. Addressing this limitation, we propose VEN-VL, a visual ensemble MoE framework for effective and efficient perception following the enrich then compact principle. Specifically, we first enrich the information capacity by unifying the visual representations of different perspectives, and then progressively compact it with adaptive routers in specialized visual experts to enhance the information density. Furthermore, we incorporate the reconstruction ability of vanilla structure via explicit visual supervision, facilitating crucial information preservation. Experimental results demonstrate our superiority in complex visual tasks with few information-condensed tokens, which effectively bridges the gap between performance and efficiency.

Yinghao Wu, Zhuoyan Luo, Yiyao Yu +3

Tsinghua University

Efficient Multimodal Inference Mixture-of-Experts Models Multimodal Learning Visual Token Compression Multimodal Understanding

May 24, 2026cs.IR

Your Embedding Model is SMARTer Than You Think

Multimodal retrieval relies heavily on single-vector retrievers, which compress rich, sequential token sequences into one single global representation. While efficient, they discard fine-grained, local evidence critical for dense retrieval tasks. Multi-vector approaches were introduced as a solution, but they strictly require training and many ignore the necessity of a globally summarizing representation. To address this, we introduce SMART, a framework that unlocks the latent multi-vector capabilities of standard single-vector models. We first demonstrate that standard contrastive training on the pooled embedding implicitly shapes the retrieval geometry of preceding hidden states via gradient flow. By applying direct late-interaction over these frozen hidden states during inference, SMART acts as a plug-and-play upgrade that consistently improves performance across diverse modalities, improving even the state-of-the-art models further on MMEB-V2. We also reveal SMART's superior performance, as simple lightweight post-training not only saves time and compute, but also brings forth further improvement on Visual Document retrieval, allowing a single-vector model to outperform SoTA multi-vector counterparts. Ultimately, SMART offers both a highly efficient inference enhancement and a powerful finetuning technique for multimodal retrieval. We open source our code and weights at https://github.com/HanSolo9682/SMART.

Jianrui Zhang, Hyun Jung Lee, Sukanta Ganguly +3

UW-Madison · Korea University · NetApp, Inc.

Multimodal IR Efficient Multimodal Inference Late Interaction Retrieval Multimodal Embedding Multi-Vector Retrieval Visual Document Retrieval

May 24, 2026cs.CV

Divide-and-Conquer Inference for Large-Scale Visual Recognition with Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have demonstrated strong capabilities across a wide range of vision language tasks. However, when applied to large scale image classification, their performance degrades significantly as the label space expands a phenomenon we define as Performance Collapse in Long Sequence Recognition. Through an information theoretic analysis, we reveal that this collapse stems from a fundamental conflict between the escalating information entropy and the prominent attention dilution and decay within attention mechanisms, which impairs the model's ability to maintain a sufficient signal-to-noise ratio when processing extremely long prompts. To mitigate this, we propose Divide-and-Conquer Inference (DCI), a novel test-time scaling strategy for visual recognition with MLLMs. DCI recursively decomposes complex global classification tasks into multiple simpler, localized subproblems and employs a dynamic pruning mechanism to compress the search space. This method effectively improves the local signal to noise ratio and model accuracy by mitigating the inherent weight dilution issues in long-sequence inference. Moreover, while traditional self-attention incurs a prohibitive quadratic computational complexity, DCI achieves more favorable scaling behavior and substantially accelerates inference in large scale classification scenarios. Extensive experiments on benchmarks such as ImageNet-1K and ImageNet-21K demonstrate that DCI consistently improves classification accuracy. This enables lightweight open-source models to rival or even surpass frontier closed-source giants without any additional training or fine-tuning. As a model-agnostic, plug-and-play paradigm, DCI offers an efficient approach for scaling the inferential precision of MLLMs in large-scale scenarios.

Zhipeng Ye, Jiaqi Huang, Feng Jiang +5

Taizhou Institute of Science and Technology, Nanjing University of Science and Technology, Taizhou, 225300, Jiangsu, China · Department of Intelligence Science, Xi’an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China · Department of Statistical Sciences, University of Toronto, Toronto, M5S 1A1, Ontario, Canada +1

Efficient Multimodal Inference Multimodal Large Language Models Image Classification

May 22, 2026cs.LG

Tackling Multimodal Learning Challenges with Mixture-of-Expert: A Survey

Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across diverse modalities and tasks. Despite its growing success, a comprehensive and systematic review on the MoE metho addressing multimodal challenges remains lacking. Existing surveys tend to evaluate either multimodal learning or MoE independently from method taxonomy, overlooking the unique interplay between them. This survey fills that gap by answering a central question: \textit{How does MoE effectively resolve multimodal challenges?} We approach this from three key perspectives: (1) \textbf{MoE as an Efficient Multimodal Engine:} enabling scalable multimodal modeling by decoupling computational cost from parameter growth and mitigating modality redundancy through selective expert activation; (2) \textbf{MoE as a Multimodal Representation Learner:} integrating complementary multi-opinion expert knowledge to enrich alignment and interaction representations; and (3) \textbf{MoE as a Multimodal Adapter:} providing a modular and flexible mechanism to model imperfect data scenarios such as modality imbalance and missing modality. Through our extensive literature review, we identify critical research gaps, including interpretable routing, expert communication, modality integration, and lifelong multimodal learning. We position this survey as a foundation for future research toward interpretable and sustainable multimodal Mixture-of-Experts system.

Liangwei Nathan Zheng, Wei Emma Zhang, Olaf Maennel +2

Adelaide University

Efficient Multimodal Inference Cross-Modal Representation Learning Modality Imbalance Mixture-of-Experts Models Multimodal Fusion Multimodal Learning

May 19, 2026cs.LG

FusionSense: Tri-Stage Near-Sensor Learning for Runtime-Adaptive Multimodal Edge Intelligence

Autonomous systems and smart-industry deployments increasingly split computation across near-sensor, edge, and cloud resources, where tight energy, latency, and reliability budgets demand run-time adaptivity. In practice, deciding what to compute and transmit at each point is pivotal; yet as multimodal sensor suites (cameras, LiDAR/depth, etc.) proliferate at the edge, most prior approaches either (i) fuse modalities on powerful servers or (ii) apply uni-modal near-sensor filters that ignore cross-modal dependencies, leading to redundant transmissions or missed events. We present FusionSense, a fusion-aware intelligent sensing framework for energy-constrained autonomous edge systems. Lightweight near-sensor classifiers are trained via a three-step procedure: (i) a server-side fusion model learns the downstream task, (ii) filter-out-safe (FoS) labels quantify each modality's necessity relative to the fused decision, and (iii) an edge-side fusion model is compacted by injecting near-sensor predictions as auxiliary signals. The result is a run-time decision layer that jointly reduces compute and communication while scaling linearly with sensor count. On a dual-modality (RGB+Depth/LiDAR) setup with SynDrone, FusionSense sustains task quality at substantially higher data-reduction rates than uni-modal filters and delivers large end-to-end gains: up to 33x lower energy at 1% FoI prevalence, 11x at 10%, a 92.3% reduction in quality loss at a fixed 30% data reduction, and roughly 1.5x higher energy savings than the best prior filtering baseline.

Sanggeon Yun, Ryozo Masukawa, Minhyoung Na +5

University of California, Irvine Irvine, CA, USA · Kookmin University Seoul, South Korea · Shibaura Institute of Technology Saitama, Japan

Efficient Multimodal Inference Edge Computing Multimodal Sensor Fusion

May 19, 2026cs.CV

Stage-adaptive Token Selection for Efficient Omni-modal LLMs

The unified audio-visual understanding capability of omni-modal large language models (om-LLMs) comes at the high cost of processing tens of thousands of visual and audio tokens throughout the LLM. To reduce the cost, training-free methods for om-LLM token selection are being actively developed, operating either pre-LLM or inner-LLM. Recognizing that the non-textual token redundancy varies across stages and LLM layers, we propose in this paper a novel stage-adaptive token selection (SEATS) method that operates in both pre-LLM and inner-LLM stages. Given an overall token budget measured by the token retention rate (TRR), SEATS performs top-down token budget allocation in an input-dependent manner. Specifically, a larger TRR is used for pre-LLM token selection, whilst within the LLM, all tokens are retained in shallow layers, increasingly decreased TRRs are applied in middle layers, and the non-textual tokens are fully removed in late layers. Extensive experiments on three representative om-LLMs and six benchmarks verify the viability of the proposed method. By retaining only 10% of visual and audio tokens, SEATS preserves 94.9% of the full-token performance on Qwen2.5-Omni while achieving a 9.3x FLOPs reduction and a 4.9x prefill speedup.

Zijie Xin, Jie Yang, Ruixiang Zhao +4

Renmin University of China · WeChat Vision, Tencent Inc.

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

May 19, 2026cs.AI

AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees

Large Multimodal Models (LMMs) have recently emerged as promising backbones for GUI-agent models, where high-resolution GUI screenshots are introduced to the prompts at each iteration step. However, these screenshots exhibit highly non-uniform spatial information density: large regions may carry little information and are visually homogeneous, while key text and icons may require high visual fidelity. Existing approaches to this problem either require additional training or rely on attention-based token compression, ignoring the structured layout and spatial redundancy of GUI screenshots. To fill the gap, this paper proposes AquaUI, a training-free inference-time token reduction method for GUI agent models that utilizes the non-uniform information density in screenshots. AQuaUI constructs an adaptive quadtree on each screenshot input and keeps one representative merged token per leaf of the quadtree. AQuaUI preserves the spatial positions of retained tokens throughout the pipeline to ensure that all position-encoding stages remain consistent. To further improve temporal consistency across multi-step GUI interactions, we propose a conditional quadtree algorithm that leverages the continuity between consecutive screenshots within a single request. Specifically, it refines the current quadtree using previous quadtrees as references, helping preserve fine-grained regions across static or mildly shifted GUI states. We implement AQuaUI on state-of-the-art GUI agent models and conduct experiments on standard grounding and navigational benchmarks. AQuaUI consistently shows improved accuracy-efficiency trade-offs over prior baselines. Notably, on GUI-Owl-1.5-32B-Instruct, AQuaUI achieves up to 13.22% speedup and 29.52% fewer visual tokens while retaining 99.06% of full-token performance, suggesting that the spatial redundancy of GUI screenshots can be exploited at inference without retraining.

Yuankai Li, Tinghui Zhu, Ha Min Son +3

UC Davis

Efficient Multimodal Inference GUI Agents Visual Token Compression

May 18, 2026cs.CV

OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models

Omnimodal large language models (OmniLLMs) have recently gained increasing attention for unified audio-video understanding. However, processing long multimodal token sequences introduces substantial computational overhead, making efficient token compression crucial. Existing methods typically rely on fixed, modality-specific guidance, which fails to account for the varying importance of modalities across different queries. To address this limitation, we propose

\textbf{OmniSelect}

, a training-free, modality-adaptive token pruning framework that dynamically selects appropriate compression strategies for multimodal inputs. Specifically, we leverage a lightweight AudioCLIP model to estimate cross-modal relevance and categorize each input into three pruning regimes: Audio-Centric, Video-Centric, and Uniform pruning. Based on these relevance scores, OmniSelect further performs fine-grained token pruning within each temporal group, adaptively allocating pruning ratios to preserve informative tokens across modalities. By explicitly modeling modality preference and enabling dynamic strategy selection, OmniSelect effectively avoids the pitfalls of one-size-fits-all compression. Extensive experiments demonstrate that our method achieves efficient multimodal token reduction while maintaining strong performance, without requiring any additional training.

Morunliu Yang, Ruotao Xu, Le Li +6

1Soochow University · Peking University

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

May 15, 2026cs.AI

TTE-Flash: Accelerating Reasoning-based Multimodal Representations via Think-Then-Embed Tokens

Recent research has demonstrated that Universal Multimodal Embedding (UME) benefits significantly from Chain-of-Thought (CoT) reasoning. In this paradigm, a generative model produces explicit reasoning traces for a multimodal query, with the final representation extracted from an <eos> embedding token attending to both the query and the reasoning. Despite its effectiveness, the computational overhead of generating explicit CoT traces is often prohibitive. In this work, we propose replacing explicit CoT with latent think tokens, which are interpreted as latent variables that can produce explicit CoT traces as observed variables. By optimizing think tokens using CoT generation loss and subsequent embedding tokens using contrastive loss, we produce high-performance, reasoning-aware representations at a constant inference cost. Our study investigates two key architectural designs: 1) how think and embeddings tokens should be extracted from the same LLM backbone. 2) how the tokens should be trained as two dependent tasks. We introduce TTE-Flash-2B, a reasoning-aware multimodal representation model that outperforms its explicit-CoT counterpart on the MMEB-v2 benchmark, while producing latent think tokens that are interpretable both textually and visually. Furthermore, zero-shot evaluation across 15 video datasets reveals scaling behavior as the number of think tokens increases, and motivating a pilot study of adaptive think budget allocation based on task requirements.

Jianpeng Cheng, Xian Wu, Jiangfan Zhang +10

1Meta AI

Efficient Multimodal Inference Multimodal Embedding Multimodal CoT Reasoning Multimodal Foundation Models Multimodal Understanding

May 14, 2026cs.AI

OmniDrop: Layer-wise Token Pruning for Omni-modal LLMs via Query-Guidance

Omni-modal large language models have demonstrated remarkable potential in holistic multimodal understanding; however, the token explosion caused by high-resolution audio and video inputs remains a critical bottleneck for real-time applications and long-form reasoning. Existing omni-modal token compression methods typically prune tokens at the input embedding level, relying on audio-video similarity or temporal co-occurrence as proxies for semantic relevance. In practice, such assumptions are often unreliable. To address this limitation, we propose OmniDrop, a training-free, layer-wise token pruning framework that progressively prunes audiovisual tokens within the LLM decoder layers rather than at the input-level, allowing early layers to preserve sufficient omni-modal information fusion before aggressively removing tokens in deeper layers. We further utilize text queries as guidance for modality-agnostic and task-adaptive token pruning. We also introduce a temporal diversity score that encourages balanced token survival to preserve global temporal context. Experimental results across various audiovisual benchmarks demonstrate that OmniDrop outperforms all baselines by up to 3.58 points while reducing prefill latency by up to 40% and memory usage by up to 14.7%.

Yeo Jeong Park, Hyemi Jang, Minseo Choi +3

Samsung Research

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

May 14, 2026cs.CV

Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA Architecture

Multimodal large language models (MLLMs) have emerged as a powerful backbone for multimodal embeddings. Recent methods introduce chain-of-thought (CoT) reasoning into the embedding pipeline to improve retrieval quality, but remain costly in both model size and inference cost. They typically employ separate reasoner and embedder with substantial parameter overhead, and generate CoT indiscriminately for every input. However, we observe that for simple inputs, discriminative embeddings already perform well, and redundant reasoning can even mislead the model, degrading performance. To address these limitations, we propose Think When Needed (TWN), a unified multimodal embedding framework with adaptive reasoning. TWN introduces a dual-LoRA architecture that attaches reasoning and embedding adapters to a shared frozen backbone, detaching gradients at their interface to mitigate gradient conflicts introduced by joint optimization while keeping parameters close to a single model. Building on this, an adaptive think mechanism uses a self-supervised routing gate to decide per input whether to generate CoT, skipping unnecessary reasoning to reduce inference overhead and even improve retrieval quality. We further explore embedding-guided RL to optimize CoT quality beyond supervised training. On the 78 tasks of MMEB-V2, TWN achieves state-of-the-art embedding quality while being substantially more efficient than existing generative methods, requiring only 3-5% additional parameters relative to the backbone and up to 50% fewer reasoning tokens compared to the full generative mode.

Longxiang Zhang, Weilong Dai, Guanghao Zhang +2

Alibaba Group

Efficient Multimodal Inference Multimodal Embedding Cross-Modal Retrieval Multimodal CoT Reasoning

May 13, 2026cs.CV

Learning to See What You Need: Gaze Attention for Multimodal Large Language Models

When humans describe a visual scene, they do not process the entire image uniformly; instead, they selectively fixate on regions relevant to their intended description. In contrast, current multimodal large language models (MLLMs) attend to all visual tokens at each generation step, leading to diluted focus and unnecessary computational overhead. In this work, we introduce Gaze Attention, a novel mechanism that enables MLLMs to selectively attend to task-relevant visual regions during generation. Specifically, we spatially group visual embeddings-stored as key-value caches-into compact gaze regions, each represented by a lightweight descriptor. At each decoding step, the model dynamically selects the most relevant regions and restricts attention to them, reducing redundant computation while enhancing focus. To mitigate the loss of global context caused by localized attention, we further propose learnable context tokens appended to each image or frame, allowing the model to maintain holistic visual awareness. Extensive experiments on image and video understanding benchmarks demonstrate that Gaze Attention matches or surpasses dense-attention baselines, while using up to 90% fewer visual KV entries in the attention computation.

Junha Song, Byeongho Heo, Geonmo Gu +3

1KAIST · 2NAVER AI Lab

Efficient Multimodal Inference Visual Attention Multimodal Large Language Models Sparse Attention Visual Token Pruning Multimodal Understanding

May 12, 2026cs.CV

G $^2$ TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models

The development of separate-encoder Unified multimodal models (UMMs) comes with a rapidly growing inference cost due to dense visual token processing. In this paper, we focus on understanding-side visual token reduction for improving the efficiency of separate-encoder UMMs. While this topic has been widely studied for MLLMs, existing methods typically rely on attention scores, text-image similarity and so on, implicitly assuming that the final objective is discriminative reasoning. This assumption does not hold for UMMs, where understanding-side visual tokens must also preserve the model's capabilities for editing images. We propose G

^2

TR, a generation-guided visual token reduction framework for separate-encoder UMMs. Our key insight is that the generation branch provides a task-agnostic signal for identifying understanding-side visual tokens that are not only semantically relevant but also important for latent-space image reconstruction and generation. G

^2

TR estimates token importance from consistency with VAE latent, performs balanced token selection, and merges redundant tokens into retained representatives to reduce information loss. The method is training-free, plug-and-play, and applied only after the understanding encoding stage, making it compatible with existing UMM inference pipelines. Experiments on image understanding and editing benchmarks show that G

^2

TR substantially reduces visual tokens and prefill computation by 1.94x while maintaining both reasoning accuracy and editing quality, outperforming baselines on almost all benchmarks. Code is at: https://github.com/lijunxian111/G2TR.

Junxian Li, Kai Liu, Zizhong Ding +4

Shanghai Jiao Tong University · Huawei Technologies Ltd

Efficient Multimodal Inference Unified Multimodal Models Visual Token Merging Visual Token Compression Multimodal Understanding

May 12, 2026cs.AI

OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models

Omnimodal large language models (Omni-LLMs) show strong capability in audio-video understanding, but their practical deployment remains limited by high inference cost of long video streams and dense audio sequences. Despite recent progress, existing compression methods for Omni-LLMs typically rely on fixed or native compression units, which can disrupt cross-modal correspondence and the complementary information required for audio-video reasoning, making it difficult to improve inference efficiency while stably preserving performance. To address this, we propose OmniRefine, a training-free two-stage framework for efficient audio-visual token compression in Omni-LLMs. First, Correspondence-Preserving Chunk Refinement refines native chunk boundaries into cross-modally aligned compression units through frame-audio similarity and dynamic programming. Second, Modality-Aware Cooperative Compression jointly compresses video and audio tokens within each refined unit to reduce redundancy while preserving critical evidence. Extensive experiments show that OmniRefine achieves a better efficiency-performance trade-off than strong baselines and maintains stable performance under lower compression ratios. On WorldSense, it still reaches 46.7% accuracy at a 44% token retention ratio, nearly matching the full-token baseline. The code and interface will be released to facilitate further research.

Yuchen Deng, Zidang Cai, Hai-Tao Zheng +3

Tsinghua Shenzhen International Graduate School, Tsinghua University · Pengcheng Laboratory

Audio-Visual Understanding Efficient Multimodal Inference Audio Token Compression Multimodal Large Language Models Multimodal Token Compression Multimodal Foundation Models+2

May 12, 2026cs.IR

Very Efficient Listwise Multimodal Reranking for Long Documents

Listwise reranking is a key yet computationally expensive component in vision-centric retrieval and multimodal retrieval-augmented generation (M-RAG) over long documents. While recent VLM-based rerankers achieve strong accuracy, their practicality is often limited by long visual-token sequences and multi-step autoregressive decoding. We propose ZipRerank, a highly efficient listwise multimodal reranker that directly addresses both bottlenecks. It reduces input length via a lightweight query-image early interaction mechanism and eliminates autoregressive decoding by scoring all candidates in a single forward pass. To enable effective learning, ZipRerank adopts a two-stage training strategy: (i) listwise pretraining on large-scale text data rendered as images, and (ii) multimodal finetuning with VLM-teacher-distilled soft-ranking supervision. Extensive experiments on the MMDocIR benchmark show that ZipRerank matches or surpasses state-of-the-art multimodal rerankers while reducing LLM inference latency by up to an order of magnitude, making it well-suited for latency-sensitive real-world systems. The code is available at https://github.com/dukesun99/ZipRerank.

Yiqun Sun, Pengfei Wei, Lawrence B. Hsieh

Magellan Technology Research Institute (MTRI), Japan.

Multimodal IR Efficient Multimodal Inference Learning to Rank Multimodal Reranking Visual Document Retrieval

May 12, 2026cs.CV

UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs

Multimodal large language models are increasingly expected to perform thinking with images, yet existing visual latent reasoning methods still rely on explicit textual chain-of-thought interleaved with visual latent tokens. This interleaved design limits efficiency and keeps reasoning fragmented across separate text and vision channels. We propose UniVLR, a unified visual latent reasoning framework that treats textual reasoning and auxiliary visual evidence as a shared visual workspace. Instead of preserving text CoT as an independent inference-time path, UniVLR renders reasoning traces together with auxiliary images and learns to compress this unified representation into compact visual latent tokens. At inference time, the model reasons only through visual latents and directly decodes the final answer, avoiding both external tool calls and verbose text reasoning. Experiments on real-world perception and visual reasoning tasks show that UniVLR outperforms prior visual latent reasoning methods while using substantially fewer generated reasoning tokens, suggesting a more unified and efficient paradigm for visual thinking in MLLMs.

Houcheng Jiang, Jiajun Fu, Junfeng Fang +4

University of Science and Technology of China · Zhongguancun Academy · National University of Singapore +1

Efficient Multimodal Inference Multimodal Large Language Models Latent Visual Reasoning VLM Reasoning Multimodal CoT Reasoning Visually Grounded Reasoning+1

May 12, 2026cs.CV

Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs

Omnimodal Large Language Models (Omni-LLMs) incur substantial computational overhead due to the large number of multimodal input tokens they process, making token reduction essential for real-world deployment. Existing Omni-LLM pruning methods typically reduce this cost by selecting tokens that are important for the current query or strongly aligned with cross-modal cues. However, such strategies can discard evidence that falls outside these criteria, even when needed for different questions or for understanding context beyond aligned audio-visual cues. To address this limitation, we reframe Omni-LLM token reduction as preserving broad audio-visual context while removing cross-modal redundancy. We propose ContextGuard, an inference-time token pruning framework built on this principle. ContextGuard predicts coarse visual semantics from audio and prunes video tokens whose coarse semantics are likely recoverable from audio, while retaining additional video tokens to preserve localized visual details that audio alone cannot specify. For further compression, our method merges temporally similar video tokens. The framework requires no downstream LLM fine-tuning and uses only an independently trained lightweight predictor. On Qwen2.5-Omni and Video-SALMONN2+ at 3B and 7B scales across six audio-visual benchmarks, ContextGuard outperforms prior inference-time pruning methods while pruning more tokens. Notably, on Qwen2.5-Omni 7B, ContextGuard achieves full-token-level performance on five of six benchmarks while pruning 55% of input tokens.

Chaeyoung Jung, Kyeongha Rho, Joon Son Chung

Korea Advanced Institute of Science and Technology (KAIST)

Audio-Visual Understanding Efficient Multimodal Inference Multimodal Token Compression Video Token Compression Visual Token Pruning

May 12, 2026cs.AI

CAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and Aggregation

Multimodal Graph Neural Networks (MGNNs) have shown strong potential for learning from multimodal attributed graphs, yet most existing approaches rely on tightly coupled architectures that suffer from prohibitive computational overhead. In this paper, we present a systematic empirical analysis showing that decoupled MGNNs are substantially more efficient and scalable for large-scale graph learning. However, we identify a critical bottleneck in existing decoupled pipelines, namely modal conflict, which arises in both the propagation and aggregation stages. Specifically, independent multi-hop diffusion causes cross-modal semantic divergence during propagation, while naive fusion fails to align multi-hop feature trajectories during aggregation, jointly limiting effective representation learning. To address this challenge, we propose CAMPA, a Cross-modal Aligned Multimodal Propagation & Aggregation framework for decoupled multimodal graph learning. Concretely, CAMPA introduces a two-stage alignment mechanism: (1) cross-modal aligned propagation, which injects cross-modal similarity priors into message passing to preserve semantic consistency without additional parameter overhead; (2) trajectory aligned aggregation, which leverages trajectory-level self-attention and cross-attention to capture and align long-range dependencies across modalities and hops. Extensive experiments on diverse benchmark datasets and tasks demonstrate that CAMPA consistently outperforms strong coupled and decoupled baselines while preserving the efficiency advantages of the decoupled paradigm.

Daohan Su, Hao Liu, Xunkai Li +6

Efficient Multimodal Inference Cross-Modal Alignment Multimodal Graph Learning

May 11, 2026cs.AI

LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?

Multimodal large language models (MLLMs) have heterogeneous strengths across OCR, chart understanding, spatial reasoning, visual question answering, cost, and latency. Effective MLLM routing therefore requires more than estimating query difficulty: a router must match the multimodal requirements of the current image-question input with the capabilities of each candidate model. We propose LatentRouter, a router that formulates MLLM routing as counterfactual multimodal utility prediction. Given an image-question query, LatentRouter extracts learned multimodal routing capsules, represents each candidate MLLM with a model capability token, and performs latent communication between these states to estimate how each model would perform if selected. A distributional outcome head predicts model-specific counterfactual quality, while a bounded capsule correction refines close decisions without allowing residual signals to dominate the prediction. The resulting utility-based policy supports performance-oriented and performance-cost routing, and handles changing candidate pools through shared per-model scoring with availability masking. Experiments on MMR-Bench and VL-RouterBench show that LatentRouter outperforms fixed-model, feature-level, and learned-router baselines. Additional analyses show that the gains are strongest on multimodal task groups where model choice depends on visual, layout-sensitive, or reasoning-oriented requirements, and that latent communication is the main contributor to the improvement. The code is available at: https://github.com/LabRAI/LatentRouter.

Xueqi Cheng, Yushun Dong

Department of Computer Science Florida State University University

Efficient Multimodal Inference Multimodal Large Language Models LLM Routing Multimodal Foundation Models Multimodal Understanding

May 11, 2026cs.CV

EnergyLens: Interpretable Closed-Form Energy Models for Multimodal LLM Inference Serving

As large language models span dense, mixture-of-experts, and state-space architectures and are deployed on heterogeneous accelerators under increasingly diverse multimodal workloads, optimising inference energy has become as critical as optimizing latency and throughput. Existing approaches either treat latency as an energy proxy or rely on data-hungry black-box surrogates. Both fail under varying parallelism strategies: latency and energy optima diverge in over 20% of configurations we tested, and black-box surrogates require hundreds of profiling samples to generalize across model families and hardware. We present EnergyLens, which uses symbolic regression as a structure-discovery tool over profiling data to derive a single twelve-parameter closed-form energy model expressed in terms of system properties such as degree of parallelism, batch size, and sequence length. Unlike black-box surrogates, EnergyLens decouples tensor and pipeline parallelism contributions and separates prefill from decode energy, making its predictions physically interpretable and actionable. Fitted from as few as 50 profiling measurements, EnergyLens achieves 88.2% Top-1 configuration selection accuracy across many evaluation scenarios compared to 60.9% for the closest prior analytical baseline, matches the predictive accuracy of ensemble ML methods with 10x fewer profiling samples, and extrapolates reliably to unseen batch sizes and hardware platforms without structural modification, making it a practical, interpretable tool for energy-optimal LLM deployment.

Vittorio Palladino, Gianluca Palermo, Michael E. Papka +1

Politecnico di Milano & UIC · Politecnico di Milano · University of Illinois Chicago

Efficient Multimodal Inference LLM Inference Efficient Language Model Inference

May 10, 2026cs.RO

ORICF -- Open Robotics Inference and Control Framework

Recent advances in artificial intelligence (AI) have enabled effective perception and language models for robots, but their deployment remains computationally expensive, increasing latency and energy use. This work presents the Open Robotics Inference and Control Framework (ORICF), a modular, declarative, and model-agnostic platform for composing multimodal robotic inference pipelines. ORICF integrates input/output (I/O) adapters, pluggable inference back ends, and post-processing logic, while lightweight YAML specifications allow models, hardware targets, and data channels to be changed without code modification. The framework also supports edge offloading, i.e., executing inference on nearby external computers instead of onboard the robot. ORICF is evaluated on a mobile robot that answers spoken queries about people detected in its camera stream by combining automatic speech recognition (ASR), a large language model (LLM), and a convolutional neural network (CNN) detector through Robot Operating System 2 (ROS2). Compared with onboard execution, ORICF-based edge deployment reduces robot-side compute utilization by up to 83.16% and estimated energy consumption by 65.8%, while preserving modularity and reproducibility.

Andrés Meseguer Valenzuela, Luís Miguel Bartolín Arnau

Instituto Tecnológico de Informática (ITI), Paterna, Spain

Efficient Multimodal Inference Edge Inference

May 8, 2026cs.LG

HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents

Existing multimodal search agents process target entities sequentially, issuing one tool call per entity and accumulating redundant interaction rounds whenever a query decomposes into independent sub-retrievals. We argue that effective multimodal agents should search wider rather than longer: dispatching multiple grounded queries concurrently within a round. To this end, we present HyperEyes, a parallel multimodal search agent that fuses visual grounding and retrieval into a single atomic action, enabling concurrent search across multiple entities while treating inference efficiency as a first-class training objective. HyperEyes is trained in two stages. For cold-start supervision, we develop a Parallel-Amenable Data Synthesis Pipeline covering visual multi-entity and textual multi-constraint queries, curating efficiency-oriented trajectories via Progressive Rejection Sampling. Building on this, our central contribution, a Dual-Grained Efficiency-Aware Reinforcement Learning framework, operates at two levels. At the macro level, we propose TRACE (Tool-use Reference-Adaptive Cost Efficiency), a trajectory-level reward whose reference is monotonically tightened during training to suppress superfluous tool calls without restricting genuine multi-hop search. At the micro level, we adapt On-Policy Distillation to inject dense token-level corrective signals from an external teacher on failed rollouts, mitigating the credit-assignment deficiency of sparse outcome rewards. Since existing benchmarks evaluate accuracy as the sole metric, omitting inference cost, we introduce IMEB, a human-curated benchmark of 300 instances that jointly evaluates search capability and efficiency. Across six benchmarks, HyperEyes-30B surpasses the strongest comparable open-source agent by 9.9% in accuracy with 5.3x fewer tool-call rounds on average.

Guankai Li, Jiabin Chen, Yi Xu +2

Xiaohongshu Inc. · University of Cambridge

Efficient Multimodal Inference Multimodal Search Agents Multimodal Agents RL for Tool Use Multimodal Tool Use

Apr 30, 2026cs.CL

MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction

Recent progress in multimodal large language models (MLLMs) has brought AI capabilities from static offline data processing to real-time streaming interaction, yet they still remain far from human-level multimodal interaction. The key bottlenecks are no longer modality coverage or latency alone, but the interaction paradigm itself. First, perception and response are still separated into alternating phases, preventing models from incorporating new inputs for timely adjustment during generation. Second, most current models remain reactive, responding only to explicit user requests instead of acting proactively in the evolving multimodal environment. We present MiniCPM-o 4.5, our latest effort towards human-like multimodal interaction, which mitigates these gaps by real-time full-duplex omni-modal interaction. It can see, listen, and speak simultaneously in real-time, while also exhibiting proactive behaviors such as issuing reminders or comments based on its continuous understanding of the live scene. The key technique behind MiniCPM-o 4.5 is Omni-Flow, a unified streaming framework that aligns omni-modal inputs and outputs along a shared temporal axis. This formulation converts conventional turn-based interaction into a full-duplex, time-aligned process, enabling simultaneous perception and response and allowing proactive behavior to arise within the same framework. With a total of 9B parameters, MiniCPM-o 4.5 approaches Gemini 2.5 Flash in vision-language capabilities, delivering state-of-the-art open-source performance at its scale. It also surpasses Qwen3-Omni-30B-A3B in omni-modal understanding and delivers better speech generation, with significantly higher computation efficiency. Driven by its efficient architecture design and inference optimization, the model can perform real-time full-duplex omni-modal interaction on edge devices with less than 12GB RAM cost.

Junbo Cui, Bokai Xu, Chongyi Wang +33

MiniCPM-o Team, OpenBMB

Efficient Multimodal Inference Unified Multimodal Models Multimodal Large Language Models Multimodal Foundation Models Multimodal Agents Full-Duplex Spoken Dialogue Systems+1

Apr 28, 2026cs.LG

SWAN: World-Aware Adaptive Multimodal Networks for Runtime Variations

Multimodal deep neural networks deployed in realistic environments must contend with runtime variations: changes in modality quality, overall input complexity, and available platform resources. Current networks struggle with such fluctuations -- adaptive networks cannot adhere to a strict compute budget, controller-based networks neglect to consider input complexity, and statically provisioned networks fail at all the above. Consequently, they do not extract maximum utility from the expended computational resources. We present SWAN (Sample and World-Aware Multimodal Network), the first adaptive multimodal network that accomplishes all three goals. SWAN employs a quality-aware controller to assign resources among modalities according to a variable user-specified maximum budget. Within this budget, an adaptive gating module further optimizes efficiency by scaling layer utilization according to sample complexity. For further gains, SWAN also employs a token dropping module that masks semantically irrelevant multimodal features before performing detections. We evaluate SWAN in the domain of autonomous driving with complex multi-object 3D detection, reducing FLOPs by up to 49% with minimal degradation.

Jason Wu, Shir-Kang Scott Jin, Yuyang Yuan +4

University of California, Los Angeles · University of California, Riverside · U.S. Army DEVCOM Army Research Laboratory

Efficient Multimodal Inference Dynamic Neural Networks 3D Object Detection

Apr 27, 2026cs.LG

Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence

We introduce Nemotron 3 Nano Omni, the latest model in the Nemotron multimodal series and the first to natively support audio inputs alongside text, images, and video. Nemotron 3 Nano Omni delivers consistent accuracy improvements over its predecessor, Nemotron Nano V2 VL, across all modalities, enabled by advances in architecture, training data and recipes. In particular, Nemotron 3 delivers leading results in real-world document understanding, long audio-video comprehension, and agentic computer use. Built on the highly efficient Nemotron 3 Nano 30B-A3B backbone, Nemotron 3 Nano Omni further incorporates innovative multimodal token-reduction techniques to deliver substantially lower inference latency and higher throughput than other models of similar size. We are releasing model checkpoints in BF16, FP8, and FP4 formats, along with portions of the training data and codebase to facilitate further research and development.

NVIDIA, :, Amala Sanjay Deshmukh +216

Efficient Multimodal Inference Multimodal Large Language Models Audio Understanding Audio-Language Models Multimodal Foundation Models Multimodal Understanding

Apr 23, 2026cs.LG

Focus Session: Hardware and Software Techniques for Accelerating Multimodal Foundation Models

This work presents a multi-layered methodology for efficiently accelerating multimodal foundation models (MFMs). It combines hardware and software co-design of transformer blocks with an optimization pipeline that reduces computational and memory requirements. During model development, it employs performance enhancements through fine-tuning for domain-specific adaptation. Our methodology further incorporates hardware and software techniques for optimizing MFMs. Specifically, it employs MFM compression using hierarchy-aware mixed-precision quantization and structural pruning for transformer blocks and MLP channels. It also optimizes operations through speculative decoding, model cascading that routes queries through a small-to-large cascade and uses lightweight self-tests to determine when to escalate to larger models, as well as co-optimization of sequence length, visual resolution & stride, and graph-level operator fusion. To efficiently execute the model, the processing dataflow is optimized based on the underlying hardware architecture together with memory-efficient attention to meet on-chip bandwidth and latency budgets. To support this, a specialized hardware accelerator for the transformer workloads is employed, which can be developed through expert design or an LLM-aided design approach. We demonstrate the effectiveness of the proposed methodology on medical-MFMs and on code generation tasks, and conclude with extensions toward energy-efficient spiking-MFMs.

Muhammad Shafique, Abdul Basit, Muhammad Abdullah Hanif +3

eBRAIN Lab, New York University (NYU) Abu Dhabi, Abu Dhabi, United Arab Emirates

Model Compression Efficient Multimodal Inference Hardware-Software Co-Design Multimodal Foundation Models Multimodal Learning

Apr 19, 2026cs.LG

MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference

Mixture-of-Experts Multimodal Large Language Models (MoE MLLMs) suffer from a significant efficiency bottleneck during Expert Parallelism (EP) inference due to the straggler effect. This issue is worsened in the multimodal context, as existing token-count-based load balancing methods fail to address two unique challenges: (1) Information Heterogeneity, where numerous redundant visual tokens are treated equally to semantically critical ones, and (2) Modality Dynamics, where varying visual to text ratios across tasks lead to resource misallocation. To address these challenges, we propose MACS (Modality-Aware Capacity Scaling), a training-free inference framework. Specifically, MACS introduces an Entropy-Weighted Load mechanism to quantify the semantic value of visual tokens, addressing information heterogeneity. Additionally, the Dynamic Modality-Adaptive Capacity mechanism allocates expert resources based on the real-time modal composition of the input. Extensive experiments demonstrate that MACS significantly outperforms existing methods on various multimodal benchmarks, providing a novel and robust solution for the efficient deployment of MoE MLLMs in EP inference.

Bo Li, Chuan Wu, Shaolin Zhu

School of Software, Tsinghua University, Beijing, China · TJUNLP Lab, School of Computer Science and Technology, Tianjin University, China · School of New Media and Communication, Tianjin University, China

Efficient Multimodal Inference Expert Load Balancing Mixture-of-Experts Inference Multimodal Large Language Models

Apr 18, 2026cs.CV

EvoComp: Learning Visual Token Compression for Multimodal Large Language Models via Semantic-Guided Evolutionary Labeling

Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language understanding tasks, yet their inference efficiency is often hampered by the large number of visual tokens, particularly in high-resolution or multi-image scenarios. To address this issue, we propose EvoComp, a visual token compression framework that significantly reduces token count while preserving task accuracy. EvoComp introduces a lightweight encoder-only transformer-based compressor that selects the most informative and non-redundant visual tokens by jointly considering visual and textual contexts. A core challenge lies in providing effective supervision for training the compressor. To this end, we design an evolutionary labeling strategy that searches for token subsets minimizing the MLLM's output loss, while enforcing semantic diversity through vocabulary-based token grouping. We further train the compressor using a tailored loss function combining the GHM loss to mitigate class and difficulty imbalance, and a cosine similarity regularization to encourage semantic separation between retained and discarded tokens. Extensive experiments across multiple vision-language benchmarks show that EvoComp outperforms existing methods based on attention or similarity heuristics. Notably, it retains 99.3% of the original accuracy under 3x token compression and delivers up to 1.6x speedup on mobile devices.

Jiafei Song, Fengwei Zhou, Jin Qu +7

OPPO CTG

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

Apr 17, 2026cs.CV

Reducing Peak Memory Usage for Modern Multimodal Large Language Model Pipelines

Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale to richer visual representations, inference increasingly relies on storing large numbers of vision tokens in the key-value (KV) cache, making memory consumption a central bottleneck. Existing methods address this issue by identifying redundancy in vision tokens and compressing the cache, but such compression is typically applied only after all inputs are processed, resulting in high peak memory usage during the prefill stage. In this work, we show that MLLMs exhibit inherent structural regularities and representational redundancy that can be exploited to control memory growth throughout inference. Based on this insight, we propose a sequential input-compression mechanism that enforces a fixed memory budget by performing structure-aware key-value cache compression during the prefill process. This approach substantially reduces peak memory usage while maintaining generative performance with only minimal degradation, enabling more practical and memory-efficient multimodal inference.

Junwan Kim, Hyunkyung Bae

New York University

Efficient Multimodal Inference Multimodal Large Language Models Multimodal Token Compression KV-Cache Compression