ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling

• URL: http://arxiv.org/abs/2603.22911v1
• Date: Tue, 24 Mar 2026 08:01:16 GMT
• Title: ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling
• Abstract summary: We propose a novel and training-free token pruning method for video MLLMs, termed ForestPrune.<n>ForestPrune achieves effective and high-ratio pruning via Spatial-temporal Forest Modeling.<n>In practice, ForestPrune construct token forests across video frames based on semantic, spatial and temporal constraints.
• Score: 58.993082360672645
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Due to the great saving of computation and memory overhead, token compression has become a research hot-spot for MLLMs and achieved remarkable progress in image-language tasks. However, for the video, existing methods still fall short of high-ratio token compression. We attribute this shortcoming to the insufficient modeling of temporal and continual video content, and propose a novel and training-free token pruning method for video MLLMs, termed ForestPrune, which achieves effective and high-ratio pruning via Spatial-temporal Forest Modeling. In practice, ForestPrune construct token forests across video frames based on the semantic, spatial and temporal constraints, making an overall comprehension of videos. Afterwards, ForestPrune evaluates the importance of token trees and nodes based on tree depth and node roles, thereby obtaining a globally optimal pruning decision. To validate ForestPrune, we apply it to two representative video MLLMs, namely LLaVA-Video and LLaVA-OneVision, and conduct extensive experiments on a bunch of video benchmarks. The experimental results not only show the great effectiveness for video MLLMs, e.g., retaining 95.8% average accuracy while reducing 90% tokens for LLaVA-OneVision, but also show its superior performance and efficiency than the compared token compression methods, e.g., +10.1% accuracy on MLVU and -81.4% pruning time than FrameFusion on LLaVA-Video.

Related papers

• EvoPrune: Early-Stage Visual Token Pruning for Efficient MLLMs [11.74199552426475]
  EvoPrune is an early-stage visual token pruning method for MLLMs that performs pruning directly during visual encoding.<n>EvoPrune achieves 2$times$ inference speedup with less than 1% performance degradation, demonstrating its potential for latency-sensitive MLLM deployment.
  arXiv  Detail & Related papers  (2026-03-04T03:15:14Z)
• Variation-aware Vision Token Dropping for Faster Large Vision-Language Models [24.952668143243542]
  Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding tasks.<n> Token compression offers a direct solution by reducing the number of tokens to be processed, thereby improving computational efficiency.<n>We propose Variation-aware Vision Token Dropping (textiti.e., textbfV$2$Drop), which progressively removes visual tokens with minimal variation during LVLM inference.
  arXiv  Detail & Related papers  (2025-09-01T15:28:44Z)
• 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)
• BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding [51.49345400300556]
  Large video-language models (VLMs) have demonstrated promising progress in various video understanding tasks.<n>Traditional approaches, such as uniform frame sampling, often inevitably allocate resources to irrelevant content.<n>We introduce BOLT, a method to BOost Large VLMs without additional Training through a comprehensive study of frame selection strategies.
  arXiv  Detail & Related papers  (2025-03-27T13:18:40Z)
• AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding [55.320254859515714]
  Multimodal Large Language Models (MLLMs) have revolutionized video understanding, yet are still limited by context length when processing long videos.<n>We propose AdaReTaKe, a training-free method that flexibly reduces visual redundancy by allocating compression ratios among time and layers with theoretical guarantees.<n>Experiments on VideoMME, MLVU, LongVideoBench, and LVBench datasets demonstrate that AdaReTaKe outperforms existing methods by 2.3% and 2.8% for 7B and 72B models, respectively.
  arXiv  Detail & Related papers  (2025-03-16T16:14:52Z)
• PruneVid: Visual Token Pruning for Efficient Video Large Language Models [24.889834611542955]
  We introduce PruneVid, a visual token pruning method designed to enhance the efficiency of multi-modal video understanding.<n>LLMs have shown promising performance in video tasks due to their extended capabilities in comprehending visual modalities.<n>We validate our method across multiple video benchmarks, which demonstrate that PruneVid can prune over 80% of tokens.
  arXiv  Detail & Related papers  (2024-12-20T18:01:58Z)
• VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation [66.00245701441547]
  We introduce a novel approach to reduce vision compute by leveraging redundant vision tokens "skipping layers" rather than decreasing the number of vision tokens. Our method, VideoLLM-MoD, is inspired by mixture-of-depths LLMs and addresses the challenge of numerous vision tokens in long-term or streaming video.
  arXiv  Detail & Related papers  (2024-08-29T17:21:58Z)
• An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models [65.37846460916042]
  We find out that the attention computation over visual tokens is of extreme inefficiency in the deep layers of popular LVLMs. We introduce FastV, a versatile plug-and-play method designed to optimize computational efficiency.
  arXiv  Detail & Related papers  (2024-03-11T14:35:32Z)

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.