Imagen de Portada

Video-KTR: Reinforcing Video Reasoning via Key Token Attribution

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Ziyue, Jin, Sheng, Zuo, Zhongrong, Wu, Jiawei, Qiu, Han, She, Qi, Zhang, Hao, Jiang, Xudong
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models
por: Huang, Shiqi, et al.
Publicado: (2026)

Frame-Voyager: Learning to Query Frames for Video Large Language Models
por: Yu, Sicheng, et al.
Publicado: (2024)

Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning
por: Lin, Wang, et al.
Publicado: (2025)

TokenDial: Continuous Attribute Control in Text-to-Video via Spatiotemporal Token Offsets
por: Liu, Zhixuan, et al.
Publicado: (2026)

Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning
por: Wang, Chendong, et al.
Publicado: (2025)

VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
por: Wang, Qi, et al.
Publicado: (2025)

Video-R1: Reinforcing Video Reasoning in MLLMs
por: Feng, Kaituo, et al.
Publicado: (2025)

Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder
por: Jisheng, Dang, et al.
Publicado: (2025)

Generative Neural Video Compression via Video Diffusion Prior
por: Mao, Qi, et al.
Publicado: (2025)

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

STAR-Pose: Efficient Low-Resolution Video Human Pose Estimation via Spatial-Temporal Adaptive Super-Resolution
por: Jin, Yucheng, et al.
Publicado: (2025)

VILP: Imitation Learning with Latent Video Planning
por: Xu, Zhengtong, et al.
Publicado: (2025)

OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
por: Wang, Junke, et al.
Publicado: (2024)

Reinforcing Video Reasoning with Focused Thinking
por: Dang, Jisheng, et al.
Publicado: (2025)

VideoSeg-R1:Reasoning Video Object Segmentation via Reinforcement Learning
por: Xu, Zishan, et al.
Publicado: (2025)

Veda: Scalable Video Diffusion via Distilled Sparse Attention
por: Han, Shihao, et al.
Publicado: (2026)

Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization
por: Peng, Jingwei, et al.
Publicado: (2025)

Neural-Symbolic VideoQA: Learning Compositional Spatio-Temporal Reasoning for Real-world Video Question Answering
por: Liang, Lili, et al.
Publicado: (2024)

LoViC: Efficient Long Video Generation with Context Compression
por: Jiang, Jiaxiu, et al.
Publicado: (2025)

Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning
por: Wang, Shijian, et al.
Publicado: (2025)

PruneVid: Visual Token Pruning for Efficient Video Large Language Models
por: Huang, Xiaohu, et al.
Publicado: (2024)

GA2-CLIP: Generic Attribute Anchor for Efficient Prompt Tuningin Video-Language Models
por: Wang, Bin, et al.
Publicado: (2025)

AgentCVR: Active Multi-Agent Cross-Video Reasoning via Script-Simulated Reinforcement Learning
por: Qiu, Yilun, et al.
Publicado: (2026)

Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding
por: Xie, Yuan, et al.
Publicado: (2025)

VISD: Enhancing Video Reasoning via Structured Self-Distillation
por: Lin, Hao, et al.
Publicado: (2026)

KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs
por: Song, Baiyang, et al.
Publicado: (2026)

ViSS-R1: Self-Supervised Reinforcement Video Reasoning
por: Fang, Bo, et al.
Publicado: (2025)

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

MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding
por: Wu, Peiran, et al.
Publicado: (2025)

VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering
por: Meng, Yiran, et al.
Publicado: (2025)

FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning
por: Ge, Haonan, et al.
Publicado: (2025)

Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning
por: Zhang, Haoji, et al.
Publicado: (2025)

Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination
por: Tang, Yolo Y., et al.
Publicado: (2025)

ProTA: Probabilistic Token Aggregation for Text-Video Retrieval
por: Fang, Han, et al.
Publicado: (2024)

Token Merging via Spatiotemporal Information Mining for Surgical Video Understanding
por: Jiang, Xixi, et al.
Publicado: (2025)

Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos
por: Jiang, Songtao, et al.
Publicado: (2026)

Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
por: Huang, Zhe, et al.
Publicado: (2025)

TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
por: Shen, Leqi, et al.
Publicado: (2024)

Dynamic Token Compression for Efficient Video Understanding through Reinforcement Learning
por: Wang, Shida, et al.
Publicado: (2026)

VideoCuRL: Video Curriculum Reinforcement Learning with Orthogonal Difficulty Decomposition
por: Jin, Hongbo, et al.
Publicado: (2025)