Multimodal Token Compression

Recent training-free pruning approaches for Multimodal Large Language Models (MLLMs) effectively cut computational overhead by exploiting visual redundancy or text-vision attention. However, they frequently suffer from semantic degradation due to their task-agnostic design or unreliable attention estimates. Based on our empirical analysis, we have found that this issue arises because salient tokens in shallow layers persistently suppress emerging semantic ones through numerical inertia, leading to premature discarding of signals crucial for deep reasoning. To address the aforementioned issue, from the task-oriented aspects, we first reformulate training-free pruning as a minimization of the distortion in the final task loss and derive a tractable, token-wise upper bound to serve as a surrogate objective. Specifically, this formulation inherently reveals a previously neglected inter-layer term that accounts for gradients across layers. Accordingly, for the implementation, we propose DIPrune, a rank-based framework that employs a dual importance scoring mechanism to jointly optimize intra-layer static feature saliency and inter-layer dynamic semantic evolution. Extensive experiments on LLaVA and Qwen-VL demonstrate that DIPrune consistently achieves state-of-the-art results.

Multimodal large language models (MLLMs) have shown strong potential for universal multimodal representation learning. However, existing methods either compress each input into a single vector, limiting fine-grained expressiveness, or retain long sequences of visual-token vectors, incurring substantial storage and interaction costs. To resolve this trade-off, we propose ResComEmb, a trainable framework for effective and efficient universal multi-vector multimodal embedding. ResComEmb first encodes each input at native dynamic resolution into ordered global, intermediate, and fine-grained views. After MLLM contextualization and embedding projection, a trainable Residual Homogeneity Compression (RHC) module reduces within-granularity redundancy and cross-granularity repetition under explicit visual token budgets. Then, ResComEmb introduces a length-adaptive Bidirectional Late-Interaction Matching mechanism for robust query-document scoring, which averages the strongest token-level matches in each direction and combines the two scores using a weight based on how many valid tokens each side has. Extensive experiments on MMEB, ViDoRe V1, and ViDoRe V2 show that ResComEmb produces higher-quality universal multimodal embeddings than VLM2Vec-V2, and outperforms ColQwen2.5 in visual document retrieval using only 37.5% of its full visual token budget, demonstrating a favorable effectiveness-efficiency trade-off.

Omnimodal large language models (Omni-LLMs) encode audio and visual streams into temporally interleaved token sequences for multimodal reasoning. However, processing long audio-visual token sequences incurs substantial prefill costs. Existing compression methods have made progress, but often overlook temporal changes in audio-visual semantic relevance. Motivated by temporal variation and local continuity, we propose OmniRoute, a training-free, two-stage compression framework. First, Temporal Evidence-Guided Budgeting (TEGB) derives chunk-wise modality preferences and initial leading-modality budgets from semantic relevance and local content variation. Second, Budget-Constrained Semantic Compression (BCSC) compresses the leading modality and then calibrates the follower's retention target using the actual retained fraction. For video, it combines spatiotemporal grouping with query-guided selection; for audio, it selects tokens based on encoder attention and query relevance, then merges residual tokens into context anchors under visual guidance. Experiments on four representative benchmarks demonstrate a better trade-off between inference efficiency and performance than competitive baselines. The code and interface will be released to facilitate further research.

Whole-slide pathology images (WSIs) contain gigapixel-scale visual content, creating a major scalability challenge for slide-level multimodal large language models (MLLMs). Existing approaches process thousands of patch tokens and typically apply compression only after slide encoding, leaving multimodal attention computationally expensive. We introduce SLICEChat, a slide-level MLLM that integrates progressive token pruning within a hybrid Mamba--Transformer slide encoder. Mamba layers enable efficient long-range propagation, while Transformer layers preserve global interactions as the sequence is progressively shortened. Between stages, language-supervised, region-aware pruning removes spatially coherent low-utility regions under a controlled keep-rate schedule, producing compact slide representations before multimodal fusion. On SlideBench VQA, SLICEChat achieves 79.84% accuracy on TCGA and 59.09% on BCNB cohorts, outperforming prior slide-level pathology MLLMs, and achieves the highest overall WSI-Bench metrics. It also provides competitive memory usage and the inference latency among the evaluated models. These results demonstrate accurate and computationally efficient multimodal reasoning over gigapixel WSIs.

Recent advances in multimodal large language mod- els (MLLMs) have opened new opportunities for edge intelligence by enabling reasoning across heterogeneous sensor modalities, such as vision, text, and telemetry data. However, deploying these capabilities on resource-constrained edge platforms remains challenging due to the substantial computational, memory, and communication demands of modern MLLMs. Rather than transmitting raw sensor observations or partitioning neural networks at intermediate layers, Edge Multi-Modal Intelligence (EMMI) communicates a compact representation between edge devices and server resources, enabling communication-efficient edge MLLM inference. To achieve this, EMMI performs modality-specific encoding, cross-modal representation fusion, and learned compression at the edge, transmitting only a compact latent representation to server-side resources for high-capacity MLLM reasoning. This representation-centric design reduces communication overhead, preserves local data privacy, and provides a fixed-size interface between heterogeneous edge devices and server-side MLLMs. Evaluation on a representative multimodal benchmark demonstrates that EMMI can reduce the communication payload by 32x while maintaining comparable downstream accuracy, resulting in up to a 3.4x reduction in estimated end-to-end inference latency under bandwidth-constrained edge conditions.

Despite their strong multimodal understanding ability, multimodal large language models (MLLMs) incur substantial computational overhead when processing long visual token sequences. To reduce inference costs, recent studies have explored visual token pruning through vision-centric or text-guided strategies. However, these methods often overlook high-norm outlier tokens, i.e., tokens with abnormally large feature norms, leading to suboptimal pruning decisions. In this work, we show that such high-norm outlier tokens are highly redundant in both feature and spatial dimensions, yet are often mistakenly preserved as informative cues by existing methods. Motivated by this observation, we propose SinkPruner, a training-free visual token pruning framework for efficient MLLM inference. SinkPruner follows a coarse-to-fine design with two key modules: a visual sanitizer that filters high-norm redundancies and alleviates attention sink and attention dispersion, and a text-guided pruner that further retains tokens semantically aligned with the text query. Extensive experiments on twelve image-language and four video-language benchmarks demonstrate the effectiveness, efficiency, and generalizability of our framework. Notably, SinkPruner preserves 96.5% (91.8%) of the original performance of LLaVA-1.5 (Qwen2.5-VL) under an 89% token reduction. Experiments further indicate that our visual sanitizer exhibits promising transferability in enhancing the performance of existing pruning methods. Our code is available at https://github.com/LaVi-Lab/SinkPruner.

Unified multimodal models jointly support understanding and generation, but incur substantial redundant computation across tokens, layers, and generation timesteps. Through token-importance probing, we identify an asymmetric core-expansion structure: understanding exhibits a stable importance component, while generation largely shares this component but requires progress-dependent corrections. We therefore propose CE-Router, which uses a task-shared core scorer and progress-conditioned generation expansions, optimized through generation decomposition and cross-task core alignment. At inference, CE-Router compacts token computation and supplies a learned routing signal to Unified Computation Scheduling, which coordinates layer skipping, FFN pruning, diffusion-head cache reuse, and denoising-step early exit. Experiments on two representative UMM architectures demonstrate consistent quality--efficiency improvements across both tasks, retaining 98.03% of dense understanding performance with a 1.93$\times$ end-to-end inference speedup.

Latent-space communication allows heterogeneous vision-language model agents to exchange continuous representations without serializing visual and reasoning states into text. Vision Wormhole realizes this approach by translating visual features into a universal latent representation that can be consumed by another model, but every message is transported as a dense tensor of the same size regardless of its content. A fixed-capacity dense tensor therefore need not have a fixed effective information density: some messages may use only a small fraction of the available representational degrees of freedom. This observation suggests that the communication channel may be substantially compressible. We study its redundancy by fitting a post-hoc sparse autoencoder to frozen Vision Wormhole activations and measuring reconstruction, downstream utility, feature reuse, and token-level interventions across nine reasoning benchmarks. Relative to the original float32 transport, a uint16-index/float16-value sparse payload with k=4 active coefficients per token reduces the transmitted bytes by 128x. In a single-run evaluation, the seven-task non-AIME mean accuracy changes from 49.85% to 49.77%. The fitted 4096-element dictionary uses only 50 features, and task-level active sets have a mean pairwise Jaccard similarity of 0.906. These measurements establish strong post-hoc compressibility relative to the original transport, but do not yet isolate the incremental contribution of sparse coding from position selection, reduced precision, low-rank structure, or SAE optimization effects. The results motivate matched-payload comparisons and communication mechanisms whose payload adapts to the information used by each message.

Multi-step language-model agents repeatedly process growing interaction histories, leading to substantial context costs. Vision--text compression reduces these costs by rendering history as images, but the resulting modality shift creates a marked capability gap. Through controlled evaluations of history recovery, matched-state decisions, and complete trajectories, we show that this gap cannot be explained by OCR quality alone. Visual-history agents exhibit systematic drift in action selection, query formulation, stopping, and evidence use, revealing an agentic policy gap. We introduce \textbf{CAPS}, a two-stage \textbf{C}ross-modal \textbf{A}gentic \textbf{P}olicy \textbf{S}elf-distillation framework that uses the same model's stronger text-history policy to supervise its visual-history counterpart. Offline trajectory self-distillation transfers successful text-policy behavior to visual-history inputs, while online policy self-distillation provides dense supervision on states visited by the visual-history policy during reinforcement learning. On SearchQA, CAPS improves over AgentOCR by 5.0% and 3.4% with 3B and 7B backbones, respectively. On full-history ALFWorld, the corresponding gains are 15.6% and 14.5%. Across settings, CAPS reduces average memory-context cost by up to 63.3% and peak cost by up to 83.4% relative to matched text-history policies. These results show that explicit cross-modal policy self-distillation can preserve agent capability under vision--text compression. Our code will be made publicly available in a future release.

Omni-modal LLMs jointly process audio, video, and text, but long multimodal sequences incur substantial prefill and KV-cache costs. Existing omni-modal compression methods primarily focus on pre-LLM token reduction, leaving modality-specific compression across the LLM boundary underexplored. We propose A-PACK, a two-stage framework that defers audio pruning until query-conditioned multimodal interactions emerge. Our analysis shows that audio exhibits higher task-relevant information density and representational diversity per token than video. We further find that local audio-visual dynamics provide a more effective cue for visual selection than token-wise matching. We therefore preserve audio and compress video with local dynamics before the LLM, then progressively prune low-relevance audio and visual tokens and their KV-cache entries inside the LLM. Across four benchmarks on Qwen2.5-Omni-7B/3B, A-PACK achieves the strongest average performance among the evaluated prior methods while reducing prefill FLOPs by up to 78% and improving decoding throughput by up to 2.21x.

Vision Language Models (VLMs) face significant challenges with ultra-long, interleaved image-text sequences due to the quadratic complexity of self-attention. Current solutions either resort to aggressive token pruning, risking irreversible information loss, or adopt efficient but less precise architectures, while largely ignoring the equally vital textual component. We introduce VLZip, a framework that unifies visual and textual compression for high-fidelity reasoning within a pure Transformer. At its core, VLZip hierarchically distills visual and textual segments into compact, layer-specific "soft prefixes" and injects them into each decoder layer's hidden states, drastically shortening the attention sequence while preserving fine-grained global context. To address deficient evaluations in the field, we also introduce LongVLBench, a new benchmark derived from video narratives that demands holistic, narrative-level reasoning. Extensive experiments show VLZip achieves leading performance on long-context multimodal reasoning, enabling training up to 120K tokens, a 6x increase over the baseline, and inference beyond 280K tokens with significantly reduced memory, while demonstrating the memory scalability to handle up to 2M tokens. By excelling at extreme context lengths where existing methods collapse, VLZip establishes an efficient and powerful new standard for long-context multimodal AI. Code is available at https://github.com/ShareLab-SII/VLZip.

Latent diffusion modeling (LDM), a prominent paradigm, utilizes tokenizers to map input signal to compressed representation. This dependency positions tokenizer as an integral part of generation process itself, since it affects learning speed, quality of synthesized samples and lay foundation for later applications. This report presents series of KVAE tokenizers for audio, image and video, all designed for subsequent text-conditioned generation: KVAE-Audio, a continuous full-band 48 kHz tokenizer with a 50 Hz latent of 64 channels; KVAE-3D -- two causal video tokenizers for 4x16x16 and 4x8x8 compression; KVAE-2D, an image model, compressing input by factor of 8 with 32 channels. We demonstrate that reconstruction (PSNR, LPIPS, PESQ, etc.) and generation results on objective (Frechet Distance, CLIP score, CLAP score, etc.) and subjective (side-by-side evaluation) metrics matches or surpasses frontier opensource tokenizers, such as VAEs from Wan-2.2, HunyuanVideo-1.5, FLUX.2, MovieGen, StableAudio and MMAudio. Considering difficulty of development, we share with community training details, model selection method and ablation on design choices. The code is publicly available at https://github.com/kandinskylab/kvae and https://github.com/kandinskylab/kvae-audio.

Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices. However, this slice-wise formulation produces thousands of visual tokens that burden the LLM backbone, many of which capture overlapping visual evidence across adjacent slices. To understand how effectively a growing visual token budget improves performance, we perform scaling analyses on two 3D medical VQA benchmarks and find diminishing returns: cost keeps rising while accuracy saturates, and improving in-plane resolution is more effective than adding slices at comparable budgets. The budget should therefore be allocated more selectively rather than simply enlarged, yet most token compression methods are designed for 2D images or videos, where redundancy arises from spatial layout or temporal motion rather than from near-duplicate content along the depth axis. We present CARVE, a training-free framework that compresses visual tokens prior to LLM inference and casts token reduction as budget-constrained 2.5D allocation. CARVE partitions the depth axis into coherent windows and allocates tokens non-uniformly according to normalized cross-slice evidence. Under a shared budget, CARVE builds spatial anchors on representative slices and retrieves locally varying evidence from the full volume, then merges remaining eligible tokens into nearby anchors within each window. Removing roughly 80% of the visual tokens on Hulu-Med-7B, CARVE leads all compression baselines on every AMOS-MM report-generation metric, with 6.2 points higher retention of full-token quality than the strongest baseline, and preserves 98.1% of full-token performance across three VQA benchmarks.

Multimodal temporal data are inherently irregular and uneven in information density, yet most models rely on uniform discretization, leading to inefficient representations. We propose \textbf{EvtGraph}, a unified framework that aligns computation with temporal salience under explicit budget constraints. EvtGraph reparameterizes sequences into event-level tokens via event-adaptive compression (EAMC), selects a compact subset with a node budget (NBC), and performs temporally constrained sparse graph reasoning (T2SG). This transforms dense sequences into structured computation over salient events, reducing complexity while preserving critical transitions. We show that this design provides a practical mechanism for allocating representational capacity under a fixed budget, yielding a consistent performance--efficiency trade-off, where a small budget is often sufficient in practice. Experiments on multimodal clinical (MIMIC-IV + CXR) and cross-domain benchmarks demonstrate that EvtGraph outperforms both Transformer-based and recurrent baselines while significantly improving efficiency. These results suggest that budget-constrained event-centric representation provides a general paradigm for learning from high-redundancy temporal data.

Omni-modal large language models (Omni-LLMs) have achieved remarkable performance on audio-visual understanding tasks, but processing long and highly redundant visual and audio token sequences incurs substantial computational overhead, demanding aggressive token compression for efficient deployment. Existing methods often degrade at low token budgets: pre-LLM compression may discard structurally important and globally distributed evidence, whereas inner-LLM compression often underexploits query-conditioned audio-visual collaboration. To address these limitations, we propose OmniPack, a training-free framework that coordinates structural compression before the LLM with task-relevant semantic refinement within the LLM. Before the LLM, OmniPack removes structural redundancy through modality-specific importance, global coverage, and similarity-aware merging. After sufficient multimodal interaction, it further consolidates diverse, task-relevant representations through textual guidance and audio-visual collaboration. Extensive experiments on five benchmarks with three Omni-LLM backbones demonstrate that OmniPack consistently achieves the best performance-efficiency trade-off across diverse retention ratios, outperforming all existing methods. Notably, on Qwen2.5-Omni-7B, OmniPack preserves 98.0% of the original performance while reducing FLOPs to 16.7%, and still retains 92.9% of the original performance with only 6.8% of the original FLOPs.

Vision-Text Compression (VTC) renders long texts into images and encodes them through the vision encoder (ViT), compressing thousands of text tokens into far fewer visual tokens. However, since the ViT is pretrained predominantly on natural images, it captures visual attributes (glyphs, font sizes, layout) rather than linguistic semantics, causing rendered-image representations to diverge from native-text representations. We term this cross-path inconsistency and show, via rendering perturbation experiments, that it is a critical yet overlooked bottleneck of VTC. We propose SPIRAL (Self-improving Path Integration and Realignment), a self-supervised alignment framework that closes this gap using only the model's own text-path behavior as supervision, requiring no external teachers or additional annotations. SPIRAL operates at two complementary granularities: token-level on-policy distillation (OPD) for local faithfulness, and sequence-level preference optimization (DPO) for global coherence. On VTCBench, SPIRAL improves the overall score of Qwen3-VL-8B from 35.10 to 54.02, approaching the native text-input performance (55.60) and outperforming models up to 30x larger. The two granularities exhibit complementary strengths: OPD excels at retrieval and is sample-efficient, while DPO is stronger on reasoning and memory and scales better with data. SPIRAL's benefits also generalize to out-of-domain benchmarks, confirming that effective VTC hinges on aligning rendered-image representations back to native-text semantics.

Token compression in OmniLLMs is typically posed as a single saliency-ranking problem: score each multimodal token, keep the top-K. We argue this abstraction is mis-specified. The same attention score simultaneously decides two things: how much retained capacity each modality receives, and which tokens within a modality are kept. A shared top-K rule therefore inherits this audio-favoring allocation prior, spending retained capacity on audio before video tokens have a chance to compete. We propose Macer, a training-free compressor that first assigns explicit audio and video budgets, then performs allocation-normalized ranking within each modality at modality-specific shallow layers. Macer significantly reduces token cost while preserving accuracy across audio-grounded, audio--video joint, visual-dominant, and video-centric benchmarks. At 25 % retention, Macer preserves 98.7 % of full-token performance on Qwen2.5-Omni-7B and 97.3 % on Qwen2.5-Omni-3B. On Qwen2.5-Omni-7B, this 25 % setting reaches OmniZip-level performance at 45 % retention while using lower FLOPs. On OmniVinci-9B, the same allocation-before-ranking principle improves over shared top-K ranking by up to 12.9 points.

Recent 3D vision-language models (3D VLMs) construct geometry aware tokens by projecting 2D visual features into world coordinates, enabling spatial reasoning for tasks such as 3D question answering. However, this design generates thousands of tokens per scene, resulting in substantial computational and memory overhead. While token compression has been extensively studied in 2D VLMs, existing approaches rely on semantic relevance or attention-based selection that overlook the structured spatial nature of 3D tokens. Moreover, redundancy in 3D representations cannot be resolved by spatial proximity alone, as object-level token imbalance persists even after spatial aggregation. To address this, we propose 3DZip, a three-stage token compression framework that first applies coarse voxelization to remove point-level redundancy, then selects anchor tokens based on feature-space diversity via a Determinantal Point Process, and finally merges remaining tokens under spatial constraints to preserve geometric coherence. Experiments on three 3D question answering benchmarks demonstrate that 3DZip consistently outperforms existing compression methods, retaining 94.7% of the original performance with only 128 tokens, achieving a $1.92\times$ faster inference speed.

Retrieval-Augmented Generation (RAG) has become essential for knowledge-intensive question answering, yet scaling RAG pipelines remains challenging due to the prohibitive computational cost of processing lengthy retrieved contexts. Existing compression approaches face a fundamental trade-off: hard compression methods operate online in a query-aware fashion but achieve only modest compression rates and typically require fine-tuning the generative model, while soft compression methods attain higher ratios but rely on costly offline encoding that is entirely agnostic to the input query. To bridge this gap, we introduce RAGOCR, a novel framework that compresses retrieved documents into compact visual representations conditioned on the input query. To further balance compression rate and information fidelity, we introduce a query-aware dynamic resolution mechanism that adaptively allocates visual granularity based on each document's estimated relevance and complexity: highly relevant passages are rendered at higher resolution to preserve fine-grained details, while peripheral documents are aggressively compressed at lower resolution. Experiments on five QA benchmarks using the MedOmniKB retrieval corpus demonstrate that RAGOCR surpasses naive RAG by over 15% in accuracy while requiring only one-eighth the number of input tokens, and consistently outperforms both hard and soft compression baselines across varying retrieval depths.

Rendering source code as images offers a promising way to reduce the input costs of Multimodal Large Language Models (MLLMs). Adjusting image resolution can trade visual token cost against content fidelity. However, resolution scaling alone overlooks two sources of inefficiency: blank regions created by line breaks and indentation, and code regions irrelevant to the current instruction. Moreover, the best compression setting varies across inputs, tasks, and models, limiting fixed-ratio strategies. We propose CodeShrink, an adaptive visual compression framework with three components. Blank-Free Rendering replaces whitespace-dependent layouts with compact layouts and explicit structural markers, removing layout-induced tokens. Adaptive Compression Configuration uses a lightweight agent trained with reinforcement learning to predict a per-input setting that balances token efficiency and readability. Dominant Token Selection jointly analyzes the instruction and code image to prune task-irrelevant visual tokens during inference. We evaluate CodeShrink on code question answering, clone detection, and code completion. CodeShrink reduces visual token use by up to 71.2% while matching or exceeding uncompressed text-only inputs, and consistently outperforms text-based and visual compression baselines across all three tasks. These results show that combining layout compaction, adaptive configuration, and instruction-aware pruning can make multimodal code understanding more efficient. Our code is available at https://github.com/vinsontang1/CodeShrink.

Integrating 3D medical images with vision-language models (VLMs) holds substantial promise for computer-aided diagnosis. However, volumetric images generate prohibitively long visual-token sequences with considerable spatial and inter-slice redundancy. Existing token compression methods typically apply uniform reduction or rely on a single importance signal, increasing the risk of removing regions that are clinically relevant to the query or structurally distinctive. To address this limitation, we propose MedARC, a unified, training-free framework for Adaptive Redundancy Compression of visual tokens in 3D medical VLMs. MedARC estimates token importance by integrating three complementary cues: self-attention from the VLM vision encoder, which reflects the model's intrinsic visual focus; similarity between projected visual tokens and text embeddings, which identifies query-relevant regions; and deviations of local visual foundation model features from the volume-level feature center, which highlight structurally distinctive anatomy. The resulting importance distribution guides a saliency-aware merging strategy that preserves informative tokens while consolidating redundant ones rather than simply discarding them. Experiments on CT-RATE and MR-RATE show that MedARC reduces visual-token overhead and inference time while preserving or improving diagnostic performance. Its multi-cue scoring cost is outweighed by the savings from processing fewer tokens, with greater benefits expected for larger language models.

Emerging Omni-modal Large Language Models (OmniLLMs) enable unified understanding of text, audio, and video, but their long audio-video token sequences introduce substantial memory and inference costs. Existing compression methods mainly focus on selecting important tokens under fixed budgets, leaving the preceding budget-allocation problem underexplored. We show that direct query-to-audio/video similarity is unreliable for inter-modal budget allocation, and that uniform intra-modal budgets can miss key evidence while retaining redundant content. To address these limitations, we propose OmniDelta, a training-free, skill-driven framework that couples intent-aware inter-modal allocation with content-aware intra-modal allocation. OmniDelta first constructs audio and video skill pools to shift the fixed retained-token budget according to query demand, then reallocates modality budgets over audio segments and video frames using local complexity and temporal redundancy. The resulting local budgets can be combined with existing pruning strategies, preserving the total retained-token ratio while changing where the budget is spent. Experiments on four audio-video benchmarks with two Qwen2.5-Omni models show that OmniDelta establishes a new accuracy-efficiency Pareto frontier across pruning ratios. At 25% token retention on Qwen2.5-Omni-7B, OmniDelta reduces GPU memory by 22.0% and achieves a 1.64x end-to-end speedup over full-token inference.

Omnimodal large language models (OmniLLMs) are rapidly extending multimodal reasoning to cover synchronized audio and video. However, the resulting audio-video token sequences are long, leading to high prefill latency and GPU memory usage at inference time. Existing token pruning methods, designed mainly for vision-only inputs, miss both the cross-modal links between audio and video and the user query that decides which content matters. To bridge this gap, we present Omni-Prune, a training-free, query-aware audio-visual token pruning framework that jointly removes redundancy from both modalities while keeping task-relevant cross-modal evidence. Specifically, Omni-Prune first splits the token sequence into adaptive time windows placed at audio saliency peaks, then scores audio and video tokens on a single scale that combines encoder attention with text-query relevance, and pairs related audio-video tokens so that they are kept together. Within each window, a final K-medoids step then selects a few representative tokens, adding diverse cues that score-based selection alone would miss. Extensive experiments demonstrate that Omni-Prune outperforms established baseline methods, delivering up to 3.25x prefill speedup and 1.3x memory reduction while retaining over 99% of full-model performance.

Existing token compression methods for omnimodal large language models typically rely on one modality to determine what to retain in the other. We show that this assumption often breaks down: for the same query, audio and video relevance often peaks at different moments. This cross-modal salience mismatch makes unidirectional guidance prone to discarding answer-critical cues under aggressive compression. We propose OmniScope, a training-free token compression framework that uses the query as a shared semantic anchor while estimating relevance separately for audio and video. OmniScope allocates modality-specific token budgets, prunes visual tokens with an anchor-delta strategy that preserves both global context and temporal changes, and merges audio tokens within each second to reduce redundancy while maintaining temporal continuity. Across four audio-video benchmarks and two Qwen2.5-Omni model scales, OmniScope achieves the best average accuracy across all compression settings. At 25% overall token retention, it delivers up to 3.53x prefill speedup and more than 15% GPU memory reduction, with only a 0.35-point drop in average accuracy. These results suggest a simple design principle for OmniLLM inference: share the query across modalities, but not the salience estimates. The code is available at https://github.com/MAC-AutoML/OmniScope.

Autoregressive foundation models trained on tokenized electronic health records (EHRs) can support zero-shot clinical prediction, yet most operate on structured event codes alone, and do not incorporate multiple modalities in a principled way. We present a framework for conditioning such models on auxiliary clinical modalities, including ECG waveforms, chest X-ray images, and clinical notes, using modality-specific latent compression and gated cross-attention with temporal alignment. We investigate two key design choices: (1) how to compress long per-modality sequences (e.g., ECG time series) before they enter the multi-modal cross-attention. This feature may be essential to reduce compute overheads and may be beneficial for generalization; (2) how the choice of pretrained encoder for each modality impacts downstream performance. Through controlled ablations on MIMIC-IV, we show that the best latent-compression configurations outperforms both uncompressed cross-attention and mean pooling. Encoder choice has a clear within-modality effect, with stronger pretrained encoders consistently outperforming weaker alternatives. We further show that merely adding auxiliary modalities does not guarantee improvement on ICU mortality prediction over an EHR-only baseline. This implies that careful design of the fusion architecture and an appropriate evaluation in the clinical context are required.

The goal of this paper is to reduce the input token cost of Omni-modal large language models (Omni-LLMs) at inference time. Omni-LLMs reason jointly over audio, video and text, but the cost of the three streams is highly unbalanced: visual tokens account for the vast majority of the input, and are highly redundant. In this paper, we propose ReMo, a training-free framework that compresses visual tokens by redistributing their information across modalities: a visual token is kept only if its information appears nowhere else. ReMo achieves this in two ways: (i) it aligns audio and video in a common embedding space, and removes visual tokens already explained by the audio or by other visual tokens; and (ii) it replaces object-level visual tokens with compact text proxies, short descriptions of each object and its location, conveying the same content in far fewer tokens. On Qwen2.5-Omni at two model scales, ReMo removes 54% of the input tokens with no loss in accuracy. Indeed, it slightly exceeds the full-token model, reaching 101.2% and 101.3% of its average accuracy over five audio-visual benchmarks.

Efficient multimodal inference is increasingly constrained not only by model quality or FLOP count, but also by the cost of preserving, moving, routing, caching, and quantizing multimodal representations under latency, memory, and energy constraints. This paper reviews recent advances in efficient vision-language and multimodal large language models, covering visual token compression, video token management, KV-cache optimization, Mixture-of-Experts (MoE) routing, low-bit quantization, edge deployment, and hardware-aware benchmarking. We argue that these techniques cannot be treated as independent optimizations. Visual token compression alters downstream feature distributions and MoE routing decisions, routing behavior affects expert utilization and quantization sensitivity, quantized router logits influence expert assignment, KV-cache policies determine retained multimodal evidence, and hardware constraints often transform computational savings into memory and communication bottlenecks. We organize the literature around these interactions and identify key design trade-offs, including accuracy versus token budget, static versus adaptive compression, sparse routing efficiency versus expert collapse, and low-bit inference versus modality-specific degradation. Finally, we introduce Temporal Routing Consistency as a diagnostic for video MoE models and highlight open research directions in routing-aware compression, cross-modal cache management, hardware-aware co-design, and unified benchmarking for multimodal edge intelligence.

Vision-language models (VLMs) process large numbers of visual tokens, resulting in substantial inference latency and memory overhead. This has motivated extensive research on visual token compression. While training-free strategies rely on heuristic metrics and suffer significant performance degradation under high compression ratios, many training-based methods introduce external compression modules that force the VLM backbone to adapt, incurring substantial retraining cost and compromising VLMs' priors. Effective visual token compression hinges on strong information encoding, a capability already present in pretrained VLMs but underutilized by existing approaches. Motivated by this, we propose VisCo, a training-efficient self-compression framework that reuses the pretrained VLM itself as an intrinsic compressor. VisCo is a parameter-sharing autoencoder that compresses visual information using a small set of memory tokens and transfers hierarchical information from encoding to decoding. Experiments show that VisCo surpasses prior methods across all evaluated compression ratios, with larger gains under more aggressive compression, and remains stable even in the extreme single-token setting. Moreover, when combined with the original visual tokens, the learned memory tokens can even improve the base model, suggesting that VisCo captures complementary representations beyond compression.

Omni modal large language models (OmniLLMs) have attracted wide attention for their ability to jointly process audio and video, but they generate large token sequences under audio-visual inputs, leading to substantial inference cost. Existing audio-visual token compression methods often rely on unimodal guidance, overlooking the temporal locality of query-relevant evidence in audio-visual inputs and implicitly assuming that the two modalities share a temporally aligned information density distribution. We propose \textbf{OmniFocus}, a training-free query-guided token compression method for OmniLLMs that performs independent importance estimation for video and audio, enabling a modality-symmetric compression design that preserves modality-specific salient evidence while maintaining audio-visual alignment, thereby mitigating the modality bias issue that can arise from unimodal-guided compression. Experiments on the Qwen2.5-Omni model family across four audio-visual benchmarks show that OmniFocus maintains strong compressed performance at low token retention ratios and outperforms existing baselines on several major benchmark scores at 25% token retention. On DailyOmni with Qwen2.5-Omni-7B at 25% token retention, OmniFocus maintains 59.40 accuracy while delivering up to 1.38$\times$ prefill speedup relative to the full-token baseline, highlighting a favorable practical accuracy-efficiency trade-off.

Visual token pruning is a crucial strategy for accelerating VLMs by compressing redundant image patches, yet existing methods often fail to preserve critical cues under dense instructions and fine-grained queries. In this paper, we investigate this failure and identify two underlying bottlenecks: the widespread dispersion of textual noise that corrupts dense cross-modal scoring, and the feature fragmentation inherent to standard token selection. To address these issues, we propose Entropy-Aware Dense Pruning (EADP), a framework that reformulates pruning as a structured compression problem. EADP first leverages statistical entropy to quantify and filter out textual noise, yielding a robust, fine-grained instruction relevance score. Subsequently, instead of naive Top-K selection, EADP casts token selection as a submodular maximization problem with a spatial prior, explicitly ensuring a holistic and non-redundant visual representation. Extensive experiments demonstrate that EADP improves the accuracy-efficiency trade-off of VLMs, robustly preserving fine-grained visual cues under strict token budgets while achieving SoTA performance on challenging multimodal benchmarks.