Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for converting visual tokens into tokens are limited by their high volume . et al., 2023; Zheng e.t., 2023): a revolution in video understanding. |
| Approach: | They propose a language-aware dynamic token compression system that converts video clips into soft caption tokens as visual representations. |
| Outcome: | The proposed method reduces FLOPs by 49% while maintaining competitive performance. |
Similar Papers
Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown that Video Large Language Models (Vide-oLLMs) are efficient at video understanding but lack the quadratic complexity of visual tokens. |
| Approach: | They propose a plug-and-play inference acceleration framework for VideoLLM token compression that quantifies each frame’s uniqueness and adaptively adjusts compression intensity across frames. |
| Outcome: | Extensive experiments on video large language models and benchmarks show that the proposed framework can preserve essential information while reducing redundancy in video sequences. |
D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing training-free adaptation frameworks for video large language models are limited by the scarcity of high-quality video-text data. |
| Approach: | They propose a training-free adaptation framework that incorporates dynamic compression and question decomposition to address perception bottleneck and token overload. |
| Outcome: | The proposed framework improves video understanding across various benchmarks and on long-video benchmarks. |
ViPE: Visual Perception in Parameter Space for Efficient Video-Language Understanding (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing video-language models rely on concatenating visual tokens with textual inputs for joint modeling, but this method suffers from significant inefficiency when scaling to long videos with dense visual inputs. |
| Approach: | They propose a video-to-parameter efficiency paradigm called ViPE that transforms video content into visual perceptual weights, which are directly injected into the LLM’s parameters. |
| Outcome: | The proposed model reduces FLOPs by 85% and inference time by up to 65% while reducing FLOP and FLOP inference times by up-to-65%. |
Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs (2025.acl-short)
Copied to clipboard
| Challenge: | Recent advances in Video Large Language Models (Video-LLMs) have achieved exceptional performance on tasks like video question answering and captioning. |
| Approach: | They propose a decoding strategy that leverages sparse top-K attention and dense full attention to accelerate Video-LLMs without loss. |
| Outcome: | The proposed approach achieves a 1.94 walltime speedup in video processing. |
PruneVid: Visual Token Pruning for Efficient Video Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to video token pruning face significant computational challenges due to the redundancy inherent in video data. |
| Approach: | They propose a training-free visual token pruning method that reduces the redundancy inherent in video data and leverages LLMs’ inherent ability to selectively prune visual tokens irrelevant to specific queries. |
| Outcome: | The proposed method can prune over 80% of tokens while maintaining competitive performance when combined with different video LLMs. |
MoPrune: Scene-Guided Motion-Aware Token Pruning for Efficient Video Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Prior approaches to token pruning ignore video dynamics and the fact that different scenes exhibit different redundancy patterns. |
| Approach: | They propose a token pruning framework that is train-free and scene-guided to accelerate VideoLLMs by removing redundant visual information from video frames. |
| Outcome: | MoPrune is a training-free, scene-guided and motion-centric token pruning framework for accelerating VideoLLMs. |
TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | ChatGPT and GPT-4 are commercial large language models (LLMs) however, they may produce vague responses or incorrect answers in certain specialized domains. |
| Approach: | They propose a token compression scheme that uses summarization and semantic compression to reduce the token size of LLMs. |
| Outcome: | The proposed method reduces token size by doing summarization and semantic compression while reducing token size with only 1.6% accuracy drop. |
Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects (2026.findings-acl)
Copied to clipboard
Jun Zhang, Yicheng Ji, Feiyang Ren, Yihang Li, Bowen Zeng, Zonghao Chen, Ke Chen, Lidan Shou, Gang Chen, Huan Li
| Challenge: | Large Vision-Language Models are hindered by a systemic efficiency barrier known as visual token dominance. |
| Approach: | They propose a systematic taxonomy of efficiency techniques structured around the inference lifecycle . they examine visual encoding, prefilling, and decoding to understand bottlenecks . |
| Outcome: | The proposed techniques reveal how upstream decisions dictate downstream bottlenecks . the proposed techniques include hybrid compression and modality-aware decoding . |
Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods (2026.acl-long)
Copied to clipboard
Chenfei Liao, Wensong Wang, Zichen Wen, Xu Zheng, Yiyu Wang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Xin Zou, Yuqian Fu, Bin Ren, Linfeng Zhang, Xuming Hu
| Challenge: | Recent efforts to accelerate inference in Multimodal Large Language Models have focused on visual token compression. |
| Approach: | They propose a framework that leverages downsampling as a discriminator to denoise existing benchmarks. |
| Outcome: | The proposed evaluation framework leverages downsampling as a discriminator to denoise existing benchmarks. |
METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understanding (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in Video Large Language Models (VLLMs) have significantly enhanced their ability to understand video content. |
| Approach: | They propose a training-free, Multi-stage Event-based Token compression framework that eliminates redundant visual tokens across three critical stages . |
| Outcome: | The proposed framework reduces FLOPs and KV Cache memory consumption while maintaining comparable or even superior accuracy. |