WeaveTime: Stream from Earlier Frames into Emergent Memory in VideoLLMs

• URL: http://arxiv.org/abs/2602.22142v1
• Date: Wed, 25 Feb 2026 17:45:45 GMT
• Title: WeaveTime: Stream from Earlier Frames into Emergent Memory in VideoLLMs
• Abstract summary: We present WeaveTime, a simple, efficient, and model agnostic framework that first teaches order and then uses order.<n>At inference, a Past-Current Dynamic Focus Cache performs uncertainty triggered, coarse-to-fine retrieval, expanding history only when needed.<n>These results establish WeaveTime as a practical path toward time aware stream Video-LLMs under strict online, time causal constraints.
• Score: 37.61875409530676
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in Multimodal Large Language Models have greatly improved visual understanding and reasoning, yet their quadratic attention and offline training protocols make them ill-suited for streaming settings where frames arrive sequentially and future observations are inaccessible. We diagnose a core limitation of current Video-LLMs, namely Time-Agnosticism, in which videos are treated as an unordered bag of evidence rather than a causally ordered sequence, yielding two failures in streams: temporal order ambiguity, in which the model cannot follow or reason over the correct chronological order, and past-current focus blindness where it fails to distinguish present observations from accumulated history. We present WeaveTime, a simple, efficient, and model agnostic framework that first teaches order and then uses order. We introduce a lightweight Temporal Reconstruction objective-our Streaming Order Perception enhancement-that instills order aware representations with minimal finetuning and no specialized streaming data. At inference, a Past-Current Dynamic Focus Cache performs uncertainty triggered, coarse-to-fine retrieval, expanding history only when needed. Plugged into exsiting Video-LLM without architectural changes, WeaveTime delivers consistent gains on representative streaming benchmarks, improving accuracy while reducing latency. These results establish WeaveTime as a practical path toward time aware stream Video-LLMs under strict online, time causal constraints. Code and weights will be made publicly available. Project Page: https://zhangyl4.github.io/publications/weavetime/

Related papers

• The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMs [21.75029303199712]
  We propose VT-Contrast, a representation-level temporal counterfactual objective for VideoLMs.<n>Its design asks where temporal supervision should act and what temporal differences it should expose.<n> VT-Contrast supervises selected late-layer last-frame video tokens, where temporal information is expected to be integrated before language generation.
  arXiv  Detail & Related papers  (2026-09-03T17:14:55Z)
• MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention [53.80990122465395]
  We show how a cross-attention backbone is better suited to real-time vision-language fusion than the prevailing decoder-only design.<n>Our model trails the strong Qwen2.5-VL-7B baseline overall.<n>On a single H200 with 256 frames per video, achieves it about a 5x speedup in time to first token.
  arXiv  Detail & Related papers  (2026-06-01T09:07:15Z)
• STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models [81.32710031596591]
  Video reasoning tasks require tracking motion, temporal order, and evolving visual states across frames.<n>Existing methods built on vision-language models (LVLMs) often address this challenge by externalizing reasoning through chain-of-thought (CoT)<n>We propose STORMS, a two-stage framework that teaches LVLMs to reason through bounded continuous latent trajectories instead of explicit textual CoT.
  arXiv  Detail & Related papers  (2026-05-25T16:33:00Z)
• TV-RAG: A Temporal-aware and Semantic Entropy-Weighted Framework for Long Video Retrieval and Understanding [14.570869250170139]
  TV-RAG is a training-free architecture that couples temporal alignment with entropy-guided semantics to improve long-video reasoning.<n>By weaving these temporal and semantic signals together, TV-RAG realises a dual-level reasoning routine that can be grafted onto any LVLM without re-training or fine-tuning.
  arXiv  Detail & Related papers  (2025-12-29T14:10:22Z)
• Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs [54.502280390499756]
  We propose TimeWarp to create a targeted synthetic temporal dataset to fine-tune the model's responses to encourage it to focus on the given input video.<n>We demonstrate that when our method is applied to existing models, it significantly improves performance on temporal understanding benchmarks.
  arXiv  Detail & Related papers  (2025-10-04T21:48:40Z)
• Episodic Memory Representation for Long-form Video Understanding [52.33907540905242]
  Large Video Language Models excel at general video understanding but struggle with long-form context window limits.<n>We introduce Video-EM, a training free framework inspired by the principles of human memory.<n>Video-EM achieves performance gains of 4-9 percent over respective baselines while utilizing fewer frames.
  arXiv  Detail & Related papers  (2025-08-13T04:33:07Z)
• DisTime: Distribution-based Time Representation for Video Large Language Models [23.176698643825123]
  DisTime is a lightweight framework designed to enhance temporal comprehension in Video-LLMs.<n>DisTime employs a learnable token to create a continuous temporal embedding space.<n>DisTime achieves state-of-the-art performance across benchmarks in three time-sensitive tasks.
  arXiv  Detail & Related papers  (2025-05-30T08:10:18Z)
• STORM: Token-Efficient Long Video Understanding for Multimodal LLMs [116.4479155699528]
  STORM is a novel architecture incorporating a dedicated temporal encoder between the image encoder and the Video-LLMs.<n>We show that STORM achieves state-of-the-art results across various long video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-03-06T06:17:38Z)
• ODEStream: A Buffer-Free Online Learning Framework with ODE-based Adaptor for Streaming Time Series Forecasting [11.261457967759688]
  ODEStream is a buffer-free continual learning framework that incorporates a temporal isolation layer to capture temporal dependencies within the data.<n>It generates a continuous data representation, enabling seamless adaptation to changing dynamics in a data streaming scenario.<n>Our approach focuses on learning how the dynamics and distribution of historical data change over time, facilitating direct processing of streaming sequences.
  arXiv  Detail & Related papers  (2024-11-11T22:36:33Z)
• Live2Diff: Live Stream Translation via Uni-directional Attention in Video Diffusion Models [64.2445487645478]
  Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio. We present Live2Diff, the first attempt at designing a video diffusion model with uni-directional temporal attention, specifically targeting live streaming video translation.
  arXiv  Detail & Related papers  (2024-07-11T17:34:51Z)
• Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams [78.72965584414368]
  We present Flash-VStream, a video-language model that simulates the memory mechanism of human. Compared to existing models, Flash-VStream achieves significant reductions in latency inference and VRAM consumption. We propose VStream-QA, a novel question answering benchmark specifically designed for online video streaming understanding.
  arXiv  Detail & Related papers  (2024-06-12T11:07:55Z)

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.