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

• URL: http://arxiv.org/abs/2605.12056v1
• Date: Tue, 12 May 2026 12:42:44 GMT
• Title: OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models
• Abstract summary: We propose a training-free two-stage framework for efficient audio-visual token compression in Omni-LLMs.<n>First, Correspondence-Preserving Chunk Refinement refines native chunk boundaries into cross-modally aligned compression units.<n>Second, Modality-Aware Cooperative Compression jointly compresses video and audio tokens within each refined unit to reduce redundancy while preserving critical evidence.
• Score: 14.355322423471018
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Omni2LoRA: Coherence-Preserving Parametric Memory for Efficient Omni Language Models [65.49950267695267]
  We introduce Omni2LoRA, a framework for efficient parametric memory compression via coherence-preserving context distillation.<n>By converting multimodal memory into a fixed-budget, reusable parameter state, our method drives answer-time multimodal-token load to zero.
  arXiv  Detail & Related papers  (2026-08-10T07:49:10Z)
• VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference [53.883871460875234]
  VoxZip is a semantic-anchored KV cache compression framework.<n>First stage uses automatic speech recognition (ASR) transcriptions as explicit semantic anchors to temporally align, compress, and fuse audio tokens.<n>Second stage employs a dynamic filtering strategy based on temporally decayed accumulated attention to evict non-essential tokens.
  arXiv  Detail & Related papers  (2026-08-09T08:17:18Z)
• OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models [22.092281562681297]
  We propose OmniPack, a training-free framework that coordinates structural compression before the large language model.<n>It consolidates diverse, task-relevant representations through textual guidance and audio-visual collaboration.<n>Experiments show that OmniPack consistently achieves the best performance-efficiency trade-off across diverse retention ratios.
  arXiv  Detail & Related papers  (2026-08-04T15:23:42Z)
• WaveZip: Wavelet-Driven Space-Time Decoupling for Video Token Condensation [69.37452950816122]
  WaveZip is a joint signal-frequency-domain framework for efficient video inference.<n> experiments on long video understanding benchmarks demonstrate that WaveZip retains 99.6% of the full performance.
  arXiv  Detail & Related papers  (2026-07-25T16:05:22Z)
• OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models [72.34361439042634]
  We propose a training-free query-guided token compression method for OmniLLMs that performs independent importance estimation for video and audio.<n>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.
  arXiv  Detail & Related papers  (2026-07-03T07:41:00Z)
• OmniMem: Perturbation-aware Memory Compression for Streaming Audio-Visual LLMs [30.52254659395564]
  We present OmniMem, a memory-efficient streaming framework for audio-visual large language models (LLMs)<n>Unlike existing compression methods that treat all tokens uniformly, OmniMem introduces a modality-aware memory allocation strategy.<n>We show that OmniMem consistently improves over strong training-free compression baselines by 2-4% absolute accuracy under the same memory budgets.
  arXiv  Detail & Related papers  (2026-05-26T19:12:13Z)
• OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models [49.34557936004057]
  We propose a training-free, modality-adaptive token pruning framework that dynamically selects appropriate compression strategies for multimodal inputs.<n>Our method achieves efficient multimodal token reduction while maintaining strong performance, without requiring any additional training.
  arXiv  Detail & Related papers  (2026-05-18T08:33:52Z)
• One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding [51.08792182064565]
  Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames.<n>With each video frame typically expanding into tens or hundreds of tokens, the limited context length of large language models (LLMs) forces the VLMs to perceive the frames sparsely and lose temporal information.<n>We propose an extreme compression model for long video understanding, named XComp, achieving a significantly larger compression ratio and enabling denser frame sampling.
  arXiv  Detail & Related papers  (2026-04-15T17:59:52Z)
• DASH: Dynamic Audio-Driven Semantic Chunking for Efficient Omnimodal Token Compression [5.201210378318278]
  We propose Dynamic Audio-driven Semantic cHunking (DASH) to align token compression with semantic structure.<n>DASH treats audio embeddings as a semantic anchor and detects boundary candidates via cosine-similarity discontinuities.<n> experiments on AVUT, VideoMME, and WorldSense demonstrate that DASH maintains superior accuracy while achieving higher compression ratios compared to prior methods.
  arXiv  Detail & Related papers  (2026-03-15T15:22:06Z)
• Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity [54.95089105944234]
  Vision-language models (VLMs) face significant computational inefficiencies caused by excessive generation of visual tokens.<n>We propose PruneSID, a training-free Synergistic Importance-Diversity approach featuring a two-stage pipeline.<n>We demonstrate state-of-the-art performance, achieving 96.3% accuracy on LLaVA-1.5 with only 11.1% token retention, and 92.8% accuracy at extreme compression rates (5.6%) on LLaVA-NeXT.
  arXiv  Detail & Related papers  (2026-03-10T10:31:58Z)
• OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models [42.615226139135174]
  We propose OmniSIFT, a token compression framework tailored for Omni-LLMs.<n>The entire framework is optimized end-to-end via a differentiable straight-through estimator.<n>With merely 25% of the original token context, OmniSIFT consistently outperforms all compression baselines and even surpasses the performance of the full-token model on several tasks.
  arXiv  Detail & Related papers  (2026-02-04T17:51:05Z)
• DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding [58.29124051111574]
  We introduce DIFFA-2, a practical diffusion-based LALM for general audio understanding.<n>DIFFA-2 upgrades the speech encoder, employs dual semantic and acoustic adapters, and is trained with a four-stage curriculum.<n>Experiments on MMSU, MMAU, and MMAR show that DIFFA-2 consistently improves over DIFFA.
  arXiv  Detail & Related papers  (2026-01-30T16:44:23Z)
• EchoingPixels: Cross-Modal Adaptive Token Reduction for Efficient Audio-Visual LLMs [28.295585578439212]
  EchoingPixels is a framework inspired by the coexistence and interaction of visuals and sound in real-world scenes.<n>It reduces tokens from an entire combined pool of audio-visual tokens rather than using fixed budgets per modality.<n>It achieves performance comparable to strong baselines using only 5-20% of the original tokens, with a 2-3x speedup and memory reduction.
  arXiv  Detail & Related papers  (2025-12-11T06:18:58Z)
• VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction [55.66673587952058]
  Video understanding models are increasingly limited by the prohibitive storage and computational costs of large-scale datasets.<n>VideoCompressa is a novel framework for video data synthesis that reframes the problem as dynamic latent compression.
  arXiv  Detail & Related papers  (2025-11-24T07:07:58Z)
• OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models [21.542205813984243]
  We present a training-free, audio-visual token-compression framework that optimize multimodal token representation and inference.<n>Specifically, OmniZip first identifies salient audio tokens, then computes an audio retention score for each time group to capture information.<n>For each time window, OmniZip compresses the video tokens using an interleaved-temporal scheme.
  arXiv  Detail & Related papers  (2025-11-18T15:22:32Z)
• CoDiCodec: Unifying Continuous and Discrete Compressed Representations of Audio [7.093237513313511]
  CoDiCodec is a novel audio autoencoder that overcomes limitations by both efficiently encoding global features via summary embeddings.<n>It produces both compressed continuous embeddings at 11 Hz and discrete tokens at a rate of 2.38 kbps from the same trained model.<n>Our work enables a unified approach to audio compression, bridging the gap between continuous and discrete generative modelling paradigms.
  arXiv  Detail & Related papers  (2025-09-11T20:31:18Z)
• LaCo: Efficient Layer-wise Compression of Visual Tokens for Multimodal Large Language Models [62.240460476785934]
  We propose LaCo (Layer-wise Visual Token Compression), a novel framework that enables effective token compression within the intermediate layers of the vision encoder.<n>LaCo introduces two core components: 1) a layer-wise pixel-shuffle mechanism that systematically merges adjacent tokens through space-to-channel transformations, and 2) a residual learning architecture with non-parametric shortcuts.
  arXiv  Detail & Related papers  (2025-07-03T03:42:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.