Imagen de Portada

Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Haoji, Gu, Xin, Li, Jiawen, Ma, Chixiang, Bai, Sule, Zhang, Chubin, Zhang, Bowen, Zhou, Zhichao, He, Dongliang, Tang, Yansong
Formato:	Preprint
Publicado:	2025
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

UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning
por: Bai, Sule, et al.
Publicado: (2025)

VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning
por: Wang, Yuji, et al.
Publicado: (2025)

Hierarchical Memory for Long Video QA
por: Wang, Yiqin, et al.
Publicado: (2024)

Flash-VStream: Efficient Real-Time Understanding for Long Video Streams
por: Zhang, Haoji, et al.
Publicado: (2025)

Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation
por: Bai, Sule, et al.
Publicado: (2024)

Thinking With Bounding Boxes: Enhancing Spatio-Temporal Video Grounding via Reinforcement Fine-Tuning
por: Gu, Xin, et al.
Publicado: (2025)

Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams
por: Zhang, Haoji, et al.
Publicado: (2024)

Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding
por: Chen, Houlun, et al.
Publicado: (2026)

VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning
por: Ding, Yang, et al.
Publicado: (2025)

Reinforcing Video Reasoning Segmentation to Think Before It Segments
por: Gong, Sitong, et al.
Publicado: (2025)

CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos
por: Zhang, Chubin, et al.
Publicado: (2026)

LongVideoAgent: Multi-Agent Reasoning with Long Videos
por: Liu, Runtao, et al.
Publicado: (2025)

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
por: Yang, Zuhao, et al.
Publicado: (2025)

Ponder & Press: Advancing Visual GUI Agent towards General Computer Control
por: Wang, Yiqin, et al.
Publicado: (2024)

Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm
por: Tong, Jingqi, et al.
Publicado: (2025)

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

Narrative Action Evaluation with Prompt-Guided Multimodal Interaction
por: Zhang, Shiyi, et al.
Publicado: (2024)

DreamFoley: Scalable VLMs for High-Fidelity Video-to-Audio Generation
por: Li, Fu, et al.
Publicado: (2025)

MedScope: Incentivizing "Think with Videos" for Clinical Reasoning via Coarse-to-Fine Tool Calling
por: Li, Wenjie, et al.
Publicado: (2026)

DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding
por: Zhang, Peng, et al.
Publicado: (2026)

VCoME: Verbal Video Composition with Multimodal Editing Effects
por: Gong, Weibo, et al.
Publicado: (2024)

Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation
por: Zhu, Tianrui, et al.
Publicado: (2025)

Thinking with Spatial Code for Physical-World Video Reasoning
por: Chen, Jieneng, et al.
Publicado: (2026)

VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
por: Lu, Guanxing, et al.
Publicado: (2025)

LOGO: A Long-Form Video Dataset for Group Action Quality Assessment
por: Zhang, Shiyi, et al.
Publicado: (2024)

UVCG: Leveraging Temporal Consistency for Universal Video Protection
por: Li, KaiZhou, et al.
Publicado: (2024)

VideoExplorer: Think With Videos For Agentic Long-Video Understanding
por: Yuan, Huaying, et al.
Publicado: (2025)

Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning
por: Cheng, Qianjia, et al.
Publicado: (2026)

VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoning
por: Wang, Zikang, et al.
Publicado: (2025)

VTimeCoT: Thinking by Drawing for Video Temporal Grounding and Reasoning
por: Zhang, Jinglei, et al.
Publicado: (2025)

Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding
por: Shen, Xiaoqian, et al.
Publicado: (2025)

WorldQA: Multimodal World Knowledge in Videos through Long-Chain Reasoning
por: Zhang, Yuanhan, et al.
Publicado: (2024)

Thinking Isn't an Illusion: Overcoming the Limitations of Reasoning Models via Tool Augmentations
por: Song, Zhao, et al.
Publicado: (2025)

TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models
por: Chen, Harold Haodong, et al.
Publicado: (2025)

VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning
por: Gao, Zhe, et al.
Publicado: (2026)

GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation
por: Zhang, Chubin, et al.
Publicado: (2024)

Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings
por: Jiang, Haonan, et al.
Publicado: (2026)

Towards Video Thinking Test: A Holistic Benchmark for Advanced Video Reasoning and Understanding
por: Zhang, Yuanhan, et al.
Publicado: (2025)

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

Open-Vocabulary Segmentation with Semantic-Assisted Calibration
por: Liu, Yong, et al.
Publicado: (2023)