Cover Image

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yao, Linli, Li, Yicheng, Wei, Yuancheng, Li, Lei, Ren, Shuhuai, Liu, Yuanxin, Ouyang, Kun, Wang, Lean, Li, Shicheng, Li, Sida, Kong, Lingpeng, Liu, Qi, Zhang, Yuanxing, Sun, Xu
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
by: Ren, Shuhuai, et al.
Published: (2023)

TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
by: Yao, Linli, et al.
Published: (2026)

TEMPLE: Incentivizing Temporal Understanding of Video Large Language Models via Progressive Pre-SFT Alignment
by: Li, Shicheng, et al.
Published: (2025)

DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models
by: Yao, Linli, et al.
Published: (2024)

Temporal Reasoning Transfer from Text to Video
by: Li, Lei, et al.
Published: (2024)

VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models
by: Li, Shicheng, et al.
Published: (2023)

TempCompass: Do Video LLMs Really Understand Videos?
by: Liu, Yuanxin, et al.
Published: (2024)

RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction
by: Wang, Yuchi, et al.
Published: (2025)

Generative Frame Sampler for Long Video Understanding
by: Yao, Linli, et al.
Published: (2025)

StreamChat: Chatting with Streaming Video
by: Liu, Jihao, et al.
Published: (2024)

Towards Multimodal Video Paragraph Captioning Models Robust to Missing Modality
by: Chen, Sishuo, et al.
Published: (2024)

Federated Online Learning for Heterogeneous Multisource Streaming Data
by: Li, Jingmao, et al.
Published: (2025)

PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension
by: Ouyang, Kun, et al.
Published: (2024)

UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?
by: Liu, Yuanxin, et al.
Published: (2025)

Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
by: Ye, Bowen, et al.
Published: (2026)

Online Video Understanding: OVBench and VideoChat-Online
by: Huang, Zhenpeng, et al.
Published: (2024)

HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming
by: Qiu, Haonan, et al.
Published: (2025)

Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidence
by: Ouyang, Kun, et al.
Published: (2025)

Video Understanding Reward Modeling: A Robust Benchmark and Performant Reward Models
by: Wei, Yuancheng, et al.
Published: (2026)

VideoChat: Chat-Centric Video Understanding
by: Li, KunChang, et al.
Published: (2023)

StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding
by: Jin, Xinqi, et al.
Published: (2025)

StreamPro: From Reactive Perception to Proactive Decision-Making in Streaming Video
by: Li, Ao, et al.
Published: (2026)

VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning?
by: Liu, Yuanxin, et al.
Published: (2025)

Modal-adaptive Knowledge-enhanced Graph-based Financial Prediction from Monetary Policy Conference Calls with LLM
by: Ouyang, Kun, et al.
Published: (2024)

Strengthened upper bound on the third eigenvalue of graphs
by: Li, Sida
Published: (2025)

VideoOrion: Tokenizing Object Dynamics in Videos
by: Feng, Yicheng, et al.
Published: (2024)

Wasserstein Dependent Graph Attention Network for Collaborative Filtering with Uncertainty
by: Li, Haoxuan, et al.
Published: (2024)

SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
by: Ouyang, Kun, et al.
Published: (2025)

StreamForest: Efficient Online Video Understanding with Persistent Event Memory
by: Zeng, Xiangyu, et al.
Published: (2025)

Jailbreaking as a Reward Misspecification Problem
by: Xie, Zhihui, et al.
Published: (2024)

Thinking in Streaming Video
by: Liu, Zikang, et al.
Published: (2026)

Haste Makes Waste: Evaluating Planning Abilities of LLMs for Efficient and Feasible Multitasking with Time Constraints Between Actions
by: Wu, Zirui, et al.
Published: (2025)

ImgTrojan: Jailbreaking Vision-Language Models with ONE Image
by: Tao, Xijia, et al.
Published: (2024)

Proxy Compression for Language Modeling
by: Zheng, Lin, et al.
Published: (2026)

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation
by: Wang, Yuqing, et al.
Published: (2025)

VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models
by: Li, Lei, et al.
Published: (2024)

Letter on “Efficacy and Safety of Tenofovir Alafenamide ( TAF ) and Tenofovir Disoproxil Fumarate ( TDF ) Followed by TAF in Chronic Hepatitis B Patients of East Asian Ethnicity Following 5 Years of Treatment”
by: Yan Liu, et al.
Published: (2025)

RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs
by: Li, Hongliang, et al.
Published: (2025)

ChatVTG: Video Temporal Grounding via Chat with Video Dialogue Large Language Models
by: Qu, Mengxue, et al.
Published: (2024)

GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction
by: Chen, Leyang, et al.
Published: (2026)