KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | Song, Baiyang, Peng, Jun, Zhang, Yuxin, Chen, Guangyao, Yang, Feidiao, Guo, Jianyuan |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs
by: Han, Kai, et al.
Published: (2024)
by: Han, Kai, et al.
Published: (2024)
AdaFlow: Efficient Long Video Editing via Adaptive Attention Slimming And Keyframe Selection
by: Zhang, Shuheng, et al.
Published: (2025)
by: Zhang, Shuheng, et al.
Published: (2025)
KeyVideoLLM: Towards Large-scale Video Keyframe Selection
by: Liang, Hao, et al.
Published: (2024)
by: Liang, Hao, et al.
Published: (2024)
FOCUS: Efficient Keyframe Selection for Long Video Understanding
by: Zhu, Zirui, et al.
Published: (2025)
by: Zhu, Zirui, et al.
Published: (2025)
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
by: Fang, Bo, et al.
Published: (2025)
by: Fang, Bo, et al.
Published: (2025)
Training-Free Efficient Video Generation via Dynamic Token Carving
by: Zhang, Yuechen, et al.
Published: (2025)
by: Zhang, Yuechen, et al.
Published: (2025)
Agentic Keyframe Search for Video Question Answering
by: Fan, Sunqi, et al.
Published: (2025)
by: Fan, Sunqi, et al.
Published: (2025)
Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding
by: Wang, Shaoguang, et al.
Published: (2026)
by: Wang, Shaoguang, et al.
Published: (2026)
From Captions to Keyframes: KeyScore for Multimodal Frame Scoring and Video-Language Understanding
by: Lin, Shih-Yao, et al.
Published: (2025)
by: Lin, Shih-Yao, et al.
Published: (2025)
Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing
by: Liu, Lin, et al.
Published: (2026)
by: Liu, Lin, et al.
Published: (2026)
Efficient Event Stream Super-Resolution with Recursive Multi-Branch Fusion
by: Liang, Quanmin, et al.
Published: (2024)
by: Liang, Quanmin, et al.
Published: (2024)
KeyVID: Keyframe-Aware Video Diffusion for Audio-Synchronized Visual Animation
by: Wang, Xingrui, et al.
Published: (2025)
by: Wang, Xingrui, et al.
Published: (2025)
MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs
by: Ma, Junpeng, et al.
Published: (2025)
by: Ma, Junpeng, et al.
Published: (2025)
STORM: Token-Efficient Long Video Understanding for Multimodal LLMs
by: Jiang, Jindong, et al.
Published: (2025)
by: Jiang, Jindong, et al.
Published: (2025)
FlexSelect: Flexible Token Selection for Efficient Long Video Understanding
by: Zhang, Yunzhu, et al.
Published: (2025)
by: Zhang, Yunzhu, et al.
Published: (2025)
KFFocus: Highlighting Keyframes for Enhanced Video Understanding
by: Nie, Ming, et al.
Published: (2025)
by: Nie, Ming, et al.
Published: (2025)
SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control
by: Zhang, Zhida, et al.
Published: (2026)
by: Zhang, Zhida, et al.
Published: (2026)
Identity-Preserving Text-to-Video Generation via Training-Free Prompt, Image, and Guidance Enhancement
by: Gao, Jiayi, et al.
Published: (2025)
by: Gao, Jiayi, et al.
Published: (2025)
Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation
by: Zhou, Jinxing, et al.
Published: (2025)
by: Zhou, Jinxing, et al.
Published: (2025)
ID-Selection: Importance-Diversity Based Visual Token Selection for Efficient LVLM Inference
by: Huang, Zhaohong, et al.
Published: (2026)
by: Huang, Zhaohong, et al.
Published: (2026)
Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs
by: Dorovatas, Vaggelis, et al.
Published: (2025)
by: Dorovatas, Vaggelis, et al.
Published: (2025)
DreamFrame: Enhancing Video Understanding via Automatically Generated QA and Style-Consistent Keyframes
by: Song, Zhende, et al.
Published: (2024)
by: Song, Zhende, et al.
Published: (2024)
The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection
by: He, Qingdong, et al.
Published: (2025)
by: He, Qingdong, et al.
Published: (2025)
Large Model based Sequential Keyframe Extraction for Video Summarization
by: Tan, Kailong, et al.
Published: (2024)
by: Tan, Kailong, et al.
Published: (2024)
Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
by: Hyun, Jeongseok, et al.
Published: (2025)
by: Hyun, Jeongseok, et al.
Published: (2025)
OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning
by: Li, Geng, et al.
Published: (2026)
by: Li, Geng, et al.
Published: (2026)
Beyond Boundary Frames: Context-Centric Video Interpolation with Audio-Visual Semantics
by: Deng, Yuchen, et al.
Published: (2025)
by: Deng, Yuchen, et al.
Published: (2025)
Video Evidence to Reasoning Efficient Video Understanding via Explicit Evidence Grounding
by: Huang, Yanxiang, et al.
Published: (2026)
by: Huang, Yanxiang, et al.
Published: (2026)
Learning Question-Aware Keyframe Selection with Synthetic Supervision for Video Question Answering
by: Kwon, Minchan, et al.
Published: (2026)
by: Kwon, Minchan, et al.
Published: (2026)
Video Token Sparsification for Efficient Multimodal LLMs in Autonomous Driving
by: Ma, Yunsheng, et al.
Published: (2024)
by: Ma, Yunsheng, et al.
Published: (2024)
VTAgent: Agentic Keyframe Anchoring for Evidence-Aware Video TextVQA
by: He, Haibin, et al.
Published: (2026)
by: He, Haibin, et al.
Published: (2026)
VSI: Visual Subtitle Integration for Keyframe Selection to enhance Long Video Understanding
by: He, Jianxiang, et al.
Published: (2025)
by: He, Jianxiang, et al.
Published: (2025)
Training-free Video Temporal Grounding using Large-scale Pre-trained Models
by: Zheng, Minghang, et al.
Published: (2024)
by: Zheng, Minghang, et al.
Published: (2024)
Video-KTR: Reinforcing Video Reasoning via Key Token Attribution
by: Wang, Ziyue, et al.
Published: (2026)
by: Wang, Ziyue, et al.
Published: (2026)
Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation
by: Wang, Xiaojuan, et al.
Published: (2024)
by: Wang, Xiaojuan, et al.
Published: (2024)
Range-Agnostic Multi-View Depth Estimation With Keyframe Selection
by: Conti, Andrea, et al.
Published: (2024)
by: Conti, Andrea, et al.
Published: (2024)
KS-APR: Keyframe Selection for Robust Absolute Pose Regression
by: Liu, Changkun, et al.
Published: (2023)
by: Liu, Changkun, et al.
Published: (2023)
Controllable Human-centric Keyframe Interpolation with Generative Prior
by: Guo, Zujin, et al.
Published: (2025)
by: Guo, Zujin, et al.
Published: (2025)
FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing
by: Li, Guangzhao, et al.
Published: (2025)
by: Li, Guangzhao, et al.
Published: (2025)
KeySG: Hierarchical Keyframe-Based 3D Scene Graphs
by: Werby, Abdelrhman, et al.
Published: (2025)
by: Werby, Abdelrhman, et al.
Published: (2025)
Similar Items
-
Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs
by: Han, Kai, et al.
Published: (2024) -
AdaFlow: Efficient Long Video Editing via Adaptive Attention Slimming And Keyframe Selection
by: Zhang, Shuheng, et al.
Published: (2025) -
KeyVideoLLM: Towards Large-scale Video Keyframe Selection
by: Liang, Hao, et al.
Published: (2024) -
FOCUS: Efficient Keyframe Selection for Long Video Understanding
by: Zhu, Zirui, et al.
Published: (2025) -
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
by: Fang, Bo, et al.
Published: (2025)