Think in Sets for Streaming Video Token Compression

• URL: http://arxiv.org/abs/2608.01169v1
• Date: Sun, 02 Aug 2026 11:44:51 GMT
• Title: Think in Sets for Streaming Video Token Compression
• Abstract summary: 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video makes causal, frame-by-frame pruning decisions, so modeling cross-frame interactions requires an explicit historical reference.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.
• Score: 11.833562937219753
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Streaming VideoLLMs process frames causally while visual tokens grow continuously, making compression essential for controlling prefilling latency and memory. Existing training-free methods independently rank tokens, ignoring marginal-gain interactions among retained tokens. We argue that streaming video token compression should instead be formulated as set selection, where each candidate is valued by what it adds beyond the tokens already retained. Unlike existing set-wise methods designed for offline tasks, streaming makes causal, frame-by-frame pruning decisions, so modeling cross-frame interactions requires an explicit historical reference. This creates a reference-set dilemma: the reference must adequately represent previously conveyed content while remaining bounded for real-time inference. We introduce NovaCov, to our knowledge the first training-free, plug-and-play set-wise token compressor designed for streaming video. NovaCov maintains a capacity-bounded, recency-weighted Historical Reference Bank and optimizes a dual-branch submodular coverage objective that preserves representative current-frame content while prioritizing information insufficiently covered by history. Both branches are facility-location functions, so greedy selection retains the classical (1-1/e) approximation guarantee. Across streaming and offline benchmarks, NovaCov outperforms existing training-free compression methods, retaining 99.6% of ReKV accuracy while reducing LLM prefilling latency by 46%.

Related papers

• Surprise Forcing: What to Remember, When to Skip in Long Video Generation [65.0022589149937]
  Streaming autoregressive diffusion makes minute-scale video synthesis practical, but its bounded context and fixed denoising schedule allocate resources uniformly.<n>We introduce Surprise Forcing, a training-free framework that treats both limitations as online resource-allocation problems.<n> Experiments on VBench, VBench-Long, and VBench-2.0 show that the proposed allocation strategy improves long-horizon consistency and visual quality while retaining real-time streaming throughput.
  arXiv  Detail & Related papers  (2026-07-20T18:37:58Z)
• STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation [60.597357847359255]
  Video segmentation demands pixel-accurate object tracking across hundreds of frames under complex natural language queries.<n>Existing methods address this through token compression, yet typically operate on features lacking temporal context.<n>State-space models resolve this constraint, as their linear recurrence selectively conditions each token on temporal context at $mathcalO(T)$ cost compression to reduce.
  arXiv  Detail & Related papers  (2026-07-03T03:28:25Z)
• Adaptive Tokenisation Via Temporal Redundancy Masking And Latent Inpainting [18.71433885255431]
  Adaptive video tokenisation seeks to dynamically allocate token budgets based on the underlying visual complexity of a sequence.<n>We show that the latent space of a frozen continuous video tokeniser inherently encodes temporal redundancy that can be exploited directly.<n>We introduce a parameter-free adaptive token allocation mechanism that applies a fixed threshold to per-position temporal-L1 differences.
  arXiv  Detail & Related papers  (2026-06-04T13:31:12Z)
• MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering [75.0394545769057]
  KV-caching stores the Key-Value of the historical tokens via LLM prefill.<n>MuKV is a method that features a multi-grained KV cache compression module and a semi-hierarchical retrieval approach.<n> Experiments on long-streaming VideoQA benchmarks show that MuKV significantly improves answer accuracy, without sacrificing memory and online QA efficiency.
  arXiv  Detail & Related papers  (2026-05-21T10:13:03Z)
• CoRDS: Coreset-based Representative and Diverse Selection for Streaming Video Understanding [30.287018710590257]
  Streaming video understanding with large vision-language models (VLMs) requires a compact memory that can support future reasoning over an ever-growing visual history.<n>A common solution is to compress the key-value (KV) cache, but existing streaming methods typically rely on local token-wises.<n>We propose to view KV-cache compression as a coreset selection problem, rather than scoring tokens independently for retention.
  arXiv  Detail & Related papers  (2026-05-14T03:22:30Z)
• Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding [55.7992006853979]
  SAVEMem is a framework that brings semantic awareness into memory generation and lets the retrieval scope adapt per query.<n>We present SAVEMem, a training-free dual-stage framework that brings semantic awareness into memory generation and lets the retrieval scope adapt per query.
  arXiv  Detail & Related papers  (2026-05-08T15:40:40Z)
• 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)
• Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention [23.015486635502437]
  Video language models (Video-LLMs) face high computational costs due to large volumes of visual tokens.<n>We propose a unified selection mechanism that weights semantic similarity to globally select tokens.<n>Unselected tokens are merged via clustering and refilled, preserving information integrity.<n>Our unifiedtemporal token compression strategy establishes the state-of-theart in video understanding under ultra-low token retention.
  arXiv  Detail & Related papers  (2026-03-23T13:15:22Z)
• 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)
• StreamingTOM: Streaming Token Compression for Efficient Video Understanding [6.9203477336374775]
  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.
  arXiv  Detail & Related papers  (2025-10-21T03:39:41Z)
• VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models [35.38573641029626]
  We introduce the novel task of Extreme Short Token Reduction, which aims to represent entire videos using a minimal set of discrete tokens.<n>On the Extreme Short Token Reduction task, our VQToken compresses sequences to just 0.07 percent of their original length while incurring only a 0.66 percent drop in accuracy on the NextQA-MC benchmark.
  arXiv  Detail & Related papers  (2025-03-21T09:46:31Z)

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.