FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging

• URL: http://arxiv.org/abs/2602.08024v1
• Date: Sun, 08 Feb 2026 15:56:46 GMT
• Title: FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
• Authors: Ziyang Fan, Keyu Chen, Ruilong Xing, Yulin Li, Li Jiang, Zhuotao Tian,
• Abstract summary: FlashVID is a training-free acceleration framework for Video Large Language Models (VLLMs)<n>It selects the most representative tokens for basic video representation, then applies Tree-based Stemporal Tokenging (TSTM) for fine-temporal redundancy.<n>FlashVID can serve as a training-free and plug-and-play module for extending long video frames, which enables a 10x increase in video frame input to Qwen2.5-VL.
• Score: 27.981298261747288
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Although Video Large Language Models (VLLMs) have shown remarkable capabilities in video understanding, they are required to process high volumes of visual tokens, causing significant computational inefficiency. Existing VLLMs acceleration frameworks usually compress spatial and temporal redundancy independently, which overlooks the spatiotemporal relationships, thereby leading to suboptimal spatiotemporal compression. The highly correlated visual features are likely to change in spatial position, scale, orientation, and other attributes over time due to the dynamic nature of video. Building on this insight, we introduce FlashVID, a training-free inference acceleration framework for VLLMs. Specifically, FlashVID utilizes Attention and Diversity-based Token Selection (ADTS) to select the most representative tokens for basic video representation, then applies Tree-based Spatiotemporal Token Merging (TSTM) for fine-grained spatiotemporal redundancy elimination. Extensive experiments conducted on three representative VLLMs across five video understanding benchmarks demonstrate the effectiveness and generalization of our method. Notably, by retaining only 10% of visual tokens, FlashVID preserves 99.1% of the performance of LLaVA-OneVision. Consequently, FlashVID can serve as a training-free and plug-and-play module for extending long video frames, which enables a 10x increase in video frame input to Qwen2.5-VL, resulting in a relative improvement of 8.6% within the same computational budget. Code is available at https://github.com/Fanziyang-v/FlashVID.

Related papers

• FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding [55.700832127331324]
  FLoC is an efficient visual token compression framework based on the facility location function.<n>Our method achieves remarkable efficiency gains by swiftly selecting a compact subset of tokens.<n>Our approach is training-free, model-agnostic, and query-agnostic, providing a versatile solution.
  arXiv  Detail & Related papers  (2025-10-31T17:29:39Z)
• An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes [85.00111442236499]
  This paper presents textbfQuicksviewer, an LMM with new perceiving paradigm that partitions a video of nontemporal density into varying cubes using Gumbel Softmax.<n>We train the model from a language backbone through three progressive stages, each incorporating lengthy videos on average of 420s/1fps thanks to the perceiving efficiency.<n>With only 0.8M total video-text samples for training, our model outperforms the direct baseline employing a fixed partitioning strategy by a maximum of 8.72 in accuracy.
  arXiv  Detail & Related papers  (2025-04-21T17:57:21Z)
• Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation [20.67434288227437]
  ViLAMP is a hierarchical video-language model that processes hour-long videos at "mixed precision"<n>ViLAMP retains full information ins while reducing non-keyframes to their most salient features, resembling mixed-precision training.<n> Notably, ViLAMP can process ultra-long videos (up to 10K frames) on a single NVIDIA A100 GPU.
  arXiv  Detail & Related papers  (2025-04-03T09:55:09Z)
• FastVID: Dynamic Density Pruning for Fast Video Large Language Models [38.267065642416554]
  We propose Density Pruning for Fast Video LLMs termed FastVID.<n>FastVID partitions videos into temporally ordered segments to preserve temporal structure.<n>Our method significantly reduces computational overhead while maintaining temporal and visual integrity.
  arXiv  Detail & Related papers  (2025-03-14T08:33:08Z)
• 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)
• Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs [56.040198387038025]
  We present a novel prompt-guided visual perception framework (abbreviated as Free Video-LLM) for efficient inference of training-free video LLMs. Our method effectively reduces the number of visual tokens while maintaining high performance across multiple video question-answering benchmarks.
  arXiv  Detail & Related papers  (2024-10-14T12:35:12Z)
• SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models [51.712700398020075]
  We propose a training-free video large language model (LLM) that can jointly capture detailed spatial semantics and long-range temporal context. This is realized by using a two-stream SlowFast design of inputs for Video LLMs to aggregate features from sampled frames in an effective way. Experimental results show that SF-LLaVA outperforms existing training-free methods on a wide range of video tasks.
  arXiv  Detail & Related papers  (2024-07-22T17:58:04Z)
• Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization [52.63845811751936]
  Video pre-training is challenging due to the modeling of its dynamics video. In this paper, we address such limitations in video pre-training with an efficient video decomposition. Our framework is both capable of comprehending and generating image and video content, as demonstrated by its performance across 13 multimodal benchmarks.
  arXiv  Detail & Related papers  (2024-02-05T16:30:49Z)
• TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding [20.16000249533665]
  TESTA condenses video semantics by adaptively aggregating similar frames, as well as similar patches within each frame. Building upon TESTA, we introduce a pre-trained video-language model equipped with a divided space-time token aggregation module in each video block. We evaluate our model on five datasets for paragraph-to-video retrieval and long-form VideoQA tasks.
  arXiv  Detail & Related papers  (2023-10-29T16:25:32Z)

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.