StreamingTOM: Streaming Token Compression for Efficient Video Understanding

• URL: http://arxiv.org/abs/2510.18269v1
• Date: Tue, 21 Oct 2025 03:39:41 GMT
• Title: StreamingTOM: Streaming Token Compression for Efficient Video Understanding
• Abstract summary: Existing approaches only regulate post-LLM kv-cache, leaving costly pre-LLM prefill unchanged.<n>We introduce StreamingTOM, a training-free, plug-and-play two-stage framework that addresses both pre-LLM and post-LLM bottlenecks with predictable latency.<n> Experiments demonstrate our method achieves $15.7times$ kv-cache compression, $1.2times$ lower peak memory and $2times$ faster TTFT compared to prior SOTA.
• Score: 6.9203477336374775
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unlike offline processing, streaming video vision-language models face two fundamental constraints: causality and accumulation. Causality prevents access to future frames that offline methods exploit, while accumulation causes tokens to grow unbounded, creating efficiency bottlenecks. However, existing approaches only regulate post-LLM kv-cache, leaving costly pre-LLM prefill unchanged. We introduce StreamingTOM, a training-free, plug-and-play two-stage framework that addresses both pre-LLM and post-LLM bottlenecks with predictable latency. Causal Temporal Reduction imposes a fixed per-frame budget and selects tokens based on adjacent-frame changes and token saliency, drastically reducing per-frame prefill cost by processing only a compact subset of visual tokens per frame instead of all visual tokens. Online Quantized Memory stores tokens in 4-bit format, retrieves relevant groups on demand, and dequantizes them, keeping the active kv-cache bounded regardless of stream length. Experiments demonstrate our method achieves $15.7\times$ kv-cache compression, $1.2\times$ lower peak memory and $2\times$ faster TTFT compared to prior SOTA. StreamingTOM maintains state-of-the-art accuracy among training-free methods with an average of $63.8\%$ on offline benchmarks and $55.8\%/3.7$ on RVS. These results highlight the practical benefits of our two-stage approach for efficient streaming video understanding with bounded growth.

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)
• CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models [9.660619113725843]
  We propose CRAFT: Compression via Resive Adaptive Fusion Video Tokens.<n>CRAFT consistently outperforms prior state-of-the-art token-compression methods.<n>At about $8times$ compression, it retains roughly $97% of the backbone's average accuracy.
  arXiv  Detail & Related papers  (2026-08-03T03:27:46Z)
• Think in Sets for Streaming Video Token Compression [11.833562937219753]
  Streaming video makes causal, frame-by-frame pruning decisions, so modeling cross-frame interactions requires an explicit historical reference.<n>We introduce NovaCov, to our knowledge the first training-free, plug-and-play set-wise token compressor designed for streaming video.
  arXiv  Detail & Related papers  (2026-08-02T11:44:51Z)
• Towards a Dynamic and Fixed-budget Memory Bank for Efficient Streaming Video Understanding [56.17043150838547]
  CausalMem is dedicated to constructing a dynamic visual memory update mechanism.<n>It estimates the redundancy of visual tokens and updates the memory bank via an online semantic basis.<n>It achieves more than textbf20$times$ visual token compression ratio and only occupies about textbf82 MB storage.
  arXiv  Detail & Related papers  (2026-06-24T10:11:08Z)
• Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions [75.23170605943457]
  textbfmodel is a framework that decouples reasoning control from memory integration.<n>emphActive Thinking Decision Maker (ATDM) is a transparent reasoning controller that externalizes its decision process.<n>emphHierarchical Progressive Semantic Integration (HPSI) module acts as an efficient memory system.
  arXiv  Detail & Related papers  (2026-04-20T16:15:33Z)
• Small Vision-Language Models are Smart Compressors for Long Video Understanding [73.65465038390771]
  Long-form video understanding relies on intent-driven efficiency rather than greedily padded context.<n>We propose Tempo, an efficient query-aware framework compressing long videos for downstream understanding.<n>Tests show Tempo compresses hour-long videos substantially below theoretical limits, proving true long-form video understanding relies on intent-driven efficiency.
  arXiv  Detail & Related papers  (2026-04-09T11:40:25Z)
• Going Down Memory Lane: Scaling Tokens for Video Stream Understanding with Dynamic KV-Cache Memory [50.30283773196725]
  Existing approaches rely on key-value caching to accumulate frame-level details over time, but use a limited number of tokens per frame.<n>We propose scaling the token budget to enable more granular-temporal understanding and reasoning.
  arXiv  Detail & Related papers  (2026-02-20T18:59:50Z)
• PIO-FVLM: Rethinking Training-Free Visual Token Reduction for VLM Acceleration from an Inference-Objective Perspective [59.24570811503256]
  We propose PIO-FVLM to reduce redundant visual tokens in vision-models (VLMs) to accelerate inference.<n>The proposed PIO-FVLM is training-free and compatible with FlashAttention, friendly to practical application and deployment.<n>On LLaVA-Next-7B, PIO-FVLM retains just 11.1% of visual tokens but maintains 97.2% of the original performance.
  arXiv  Detail & Related papers  (2026-02-04T15:33:10Z)
• ConsensusDrop: Fusing Visual and Cross-Modal Saliency for Efficient Vision Language Models [4.273730624882391]
  Vision-Language Models (VLMs) are expensive because the LLM processes hundreds of largely redundant visual tokens.<n>We show that neither signal alone is sufficient: fusing them consistently improves performance compared to unimodal visual token selection (ranking)<n>We propose textbfConsensusDrop, a training-free framework that derives a emphconsensus ranking by reconciling vision encoder saliency with query-aware cross-attention.
  arXiv  Detail & Related papers  (2026-02-01T00:28:55Z)
• HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding [92.59317281526239]
  HERMES is a training-free architecture for real-time and accurate understanding of video streams.<n>Hermes reuses a compact KV cache, enabling efficient streaming understanding under resource constraints.<n>Hermes achieves superior or comparable accuracy across all benchmarks, with up to 11.4% gains on streaming datasets.
  arXiv  Detail & Related papers  (2026-01-21T07:26:15Z)
• Fast SAM2 with Text-Driven Token Pruning [52.8350457627401]
  Segment Anything Model 2 (SAM2), a vision computation model has significantly advanced in prompt-driven video object segmentation.<n>SAM2 pipelines propagate all visual tokens produced by the image encoder through downstream temporal reasoning modules, regardless of their relevance to the target object.<n>We introduce a text-guided token pruning framework that improves inference efficiency by selectively reducing token density prior to temporal propagation.
  arXiv  Detail & Related papers  (2025-12-24T18:59:05Z)
• CacheFlow: Compressive Streaming Memory for Efficient Long-Form Video Understanding [0.0]
  CacheFlow is a training-free pipeline that pairs Dynamic Token Dropping with a long-term memory.<n>Online, per-frame processing makes our approach fundamentally suited for live streaming VQA.<n>At inference, a consensus-based retrieval mechanism retrieves only the Top-K most relevant blocks.
  arXiv  Detail & Related papers  (2025-11-17T17:56:14Z)
• Attention Is All You Need for KV Cache in Diffusion LLMs [36.94369617373333]
  Elastic-Cache performs adaptive, layer-aware cache updates for diffusion large language models.<n>Our method achieves significantly higher throughput ($6.8times$ on GSM8K) than existing confidence-based approaches.
  arXiv  Detail & Related papers  (2025-10-16T17:59:48Z)
• Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction [58.044803442346115]
  Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding but suffer from prohibitive computational complexity and memory overhead during inference.<n>We propose Sparse-dLLM, the first training-free framework integrating dynamic cache eviction with sparse attention via delayed bidirectional sparse caching.
  arXiv  Detail & Related papers  (2025-08-04T16:14:03Z)
• VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers [23.541896057977745]
  VideoScan is an efficient vision-language model (VLM) inference framework for real-time video interaction.<n>VideoScan employs a single semantic carrier token to represent each frame.
  arXiv  Detail & Related papers  (2025-03-12T13:30:40Z)
• Post-Training Sparse Attention with Double Sparsity [44.772593893621085]
  "Double Sparsity" is a novel post-training sparse attention technique designed to alleviate this bottleneck by reducing KV cache access. Double Sparsity combines token sparsity, which focuses on utilizing only the important tokens for computing self-attention, with channel sparsity, an approach that uses important feature channels for identifying important tokens. With offloading, it achieves a decoding speed acceleration of 16.3$times$ compared to state-of-the-art solutions at a sequence length of 256K.
  arXiv  Detail & Related papers  (2024-08-11T18:40:36Z)
• Training-Free Exponential Context Extension via Cascading KV Cache [49.608367376911694]
  We introduce a novel mechanism that leverages cascading sub-cache buffers to selectively retain the most relevant tokens.<n>Our method reduces prefill stage latency by a factor of 6.8 when compared to flash attention on 1M tokens.
  arXiv  Detail & Related papers  (2024-06-24T03:59:17Z)
• ReBotNet: Fast Real-time Video Enhancement [59.08038313427057]
  Most restoration networks are slow, have high computational bottleneck, and can't be used for real-time video enhancement. In this work, we design an efficient and fast framework to perform real-time enhancement for practical use-cases like live video calls and video streams. To evaluate our method, we emulate two new datasets that real-world video call and streaming scenarios, and show extensive results on multiple datasets where ReBotNet outperforms existing approaches with lower computations, reduced memory requirements, and faster inference time.
  arXiv  Detail & Related papers  (2023-03-23T17:58:05Z)

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.