Cover Image

Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yulin, Gui, Haokun, Fan, Ziyang, Wang, Junjie, Kang, Bin, Chen, Bin, Tian, Zhuotao
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
by: Fan, Ziyang, et al.
Published: (2026)

CalibCLIP: Contextual Calibration of Dominant Semantics for Text-Driven Image Retrieval
by: Kang, Bin, et al.
Published: (2025)

DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception
by: Wang, Junjie, et al.
Published: (2025)

KeyVideoLLM: Towards Large-scale Video Keyframe Selection
by: Liang, Hao, et al.
Published: (2024)

Referencing Where to Focus: Improving VisualGrounding with Referential Query
by: Wang, Yabing, et al.
Published: (2024)

Less is More: Improving Motion Diffusion Models with Sparse Keyframes
by: Bae, Jinseok, et al.
Published: (2025)

AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech
by: Kang, Bin, et al.
Published: (2026)

Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding
by: Guo, Weiyu, et al.
Published: (2025)

Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation
by: Wang, Zixin, et al.
Published: (2024)

Less is More: Token-Efficient Video-QA via Adaptive Frame-Pruning and Semantic Graph Integration
by: Wang, Shaoguang, et al.
Published: (2025)

Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding
by: Wang, Shaoguang, et al.
Published: (2026)

Efficient Whole Slide Pathology VQA via Token Compression
by: Lyu, Weimin, et al.
Published: (2025)

Less is More: High-value Data Selection for Visual Instruction Tuning
by: Liu, Zikang, et al.
Published: (2024)

Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective
by: Yue, Zihao, et al.
Published: (2024)

Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs
by: Song, Dingjie, et al.
Published: (2024)

DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding
by: Zhang, Hongzhi, et al.
Published: (2025)

Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception
by: Wang, Junjie, et al.
Published: (2025)

Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval
by: Shlapentokh-Rothman, Michal, et al.
Published: (2026)

Less Is More? Selective Visual Attention to High-Importance Regions for Multimodal Radiology Summarization
by: Naznin, Mst. Fahmida Sultana, et al.
Published: (2026)

An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes
by: Qi, Ji, et al.
Published: (2025)

KeyframeFace: Language-Driven Facial Animation via Semantic Keyframes
by: Wu, Jingchao, et al.
Published: (2025)

What They Saw, Not Just Where They Looked: Semantic Scanpath Similarity via VLMs and NLP metric
by: Kerkouri, Mohamed Amine, et al.
Published: (2026)

Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation
by: Wang, Junjie, et al.
Published: (2026)

Vision Token Reduction via Attention-Driven Self-Compression for Efficient Multimodal Large Language Models
by: Deniz, Omer Faruk, et al.
Published: (2026)

Vision-centric Token Compression in Large Language Model
by: Xing, Ling, et al.
Published: (2025)

Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style
by: Chen, Ziyang, et al.
Published: (2024)

Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More
by: Wen, Zichen, et al.
Published: (2025)

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
by: Liu, Chengzhi, et al.
Published: (2025)

Token Sequence Compression for Efficient Multimodal Computing
by: Omri, Yasmine, et al.
Published: (2025)

InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models
by: Liu, Xinxin, et al.
Published: (2026)

Less is More: Token Context-aware Learning for Object Tracking
by: Xu, Chenlong, et al.
Published: (2025)

Controllable Human-centric Keyframe Interpolation with Generative Prior
by: Guo, Zujin, et al.
Published: (2025)

MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets
by: Wei, Lai, et al.
Published: (2023)

More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding
by: Tang, Yuan, et al.
Published: (2024)

TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation
by: Lin, Haokun, et al.
Published: (2025)

Dynamic Token Reweighting for Robust Vision-Language Models
by: Jiang, Tanqiu, et al.
Published: (2025)

CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers
by: Shi, Dachuan, et al.
Published: (2023)

LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model
by: Luo, Yulin, et al.
Published: (2024)

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
by: Zhang, Yi-Fan, et al.
Published: (2025)

MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech
by: Wang, Chengyao, et al.
Published: (2025)