Lune

CVPR Findings2026

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

Shaobo Ju, Baiyang Song, Tao Chen, Jiapeng Zhang, Qiong Wu, Chao Chang, Huaixi Wang, Yiyi Zhou, Rongrong Ji

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 imagelanguage 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 highratio 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. Our code is given in the ForestPrune.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
  • Visual Instruction Tuning cites BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
  • Visual Instruction Tuning cites Learning Transferable Visual Models From Natural Language Supervision
  • Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models cites InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
  • Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models cites Learning Transferable Visual Models From Natural Language Supervision
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on36

  1. Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
  2. Visual Instruction TuningHaotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae LeeNeurIPS 2023 · 11,349 citations
  3. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsJunnan Li, Dongxu Li, Silvio Savarese, Steven C. H. HoiICML 2023 · 7,873 citations
  4. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction TuningWenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong et al.NeurIPS 2023 · 4,013 citations
  5. Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language ModelsMuhammad Maaz, Hanoona Abdul Rasheed, Salman Khan, Fahad KhanACL 2024 · 279 citations

Related papers

  1. MoPrune: Scene-Guided Motion-Aware Token Pruning for Efficient Video Large Language ModelsWenhao Hong, Ziyang Wang, Yixin Zhang, Zilei WangACL Findings 2026
  2. HoliTom: Holistic Token Merging for Fast Video Large Language ModelsKele Shao, Keda Tao, Can Qin, Haoxuan You et al.NeurIPS 2025 · 72 citations
  3. MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMsJunpeng Ma, Qizhe Zhang, Ming Lu, Zhibin Wang et al.AAAI 2026
  4. Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language ModelsWeihao Ye, Qiong Wu, Wenhao Lin, Yiyi ZhouAAAI 2025 · 99 citations
  5. DyCoke: Dynamic Compression of Tokens for Fast Video Large Language ModelsKeda Tao, Can Qin, Haoxuan You, Yang Sui et al.CVPR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines