Cover Image

Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Du, Dazhao, Liu, Jian, Qin, Jialong, Han, Tao, Gu, Bohai, Zhu, Fangqi, Zhang, Yujia, Liu, Eric, Chen, Xi, Guo, Song
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues
by: Du, Dazhao, et al.
Published: (2026)

Place-it-R1: Unlocking Environment-aware Reasoning Potential of MLLM for Video Object Insertion
by: Gu, Bohai, et al.
Published: (2026)

Predicting the Future by Retrieving the Past
by: Du, Dazhao, et al.
Published: (2025)

WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models
by: Gu, Bohai, et al.
Published: (2026)

GUI Agents with Reinforcement Learning: Toward Digital Inhabitants
by: Hu, Junan, et al.
Published: (2026)

3D Generation for Embodied AI and Robotic Simulation: A Survey
by: Ye, Tianwei, et al.
Published: (2026)

Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention
by: Du, Junhao, et al.
Published: (2026)

Coherent Video Inpainting Using Optical Flow-Guided Efficient Diffusion
by: Gu, Bohai, et al.
Published: (2024)

From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
by: Wu, Jiafeng, et al.
Published: (2026)

Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning
by: Liu, Jian, et al.
Published: (2025)

Flow-Guided Diffusion for Video Inpainting
by: Gu, Bohai, et al.
Published: (2023)

Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting
by: Han, Tao, et al.
Published: (2024)

LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning
by: Chen, Xudong, et al.
Published: (2026)

R-Log: Incentivizing Log Analysis Capability in LLMs via Reasoning-based Reinforcement Learning
by: Liu, Yilun, et al.
Published: (2025)

Reinforcement Learning to Rank Using Coarse-grained Rewards
by: Tu, Yiteng, et al.
Published: (2022)

IRASim: A Fine-Grained World Model for Robot Manipulation
by: Zhu, Fangqi, et al.
Published: (2024)

Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency
by: Li, Hongyu, et al.
Published: (2025)

Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMs
by: Hua, Andong, et al.
Published: (2025)

REACH: Reinforcement Learning for Efficient Allocation in Community and Heterogeneous Networks
by: Yu, Zhiwei, et al.
Published: (2025)

Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learning
by: Xie, Yuankun, et al.
Published: (2026)

A Reinforcement Learning Method to Factual and Counterfactual Explanations for Session-based Recommendation
by: Zhou, Han, et al.
Published: (2025)

PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning
by: Ji, Sihui, et al.
Published: (2025)

Learning to Describe for Predicting Zero-shot Drug-Drug Interactions
by: Zhu, Fangqi, et al.
Published: (2024)

ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
by: Feng, Jiazhan, et al.
Published: (2025)

RLKD: Distilling LLMs' Reasoning via Reinforcement Learning
by: Xu, Shicheng, et al.
Published: (2025)

Counterfactually Safe Reinforcement Learning
by: Li, Jingyi, et al.
Published: (2026)

Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation Learning
by: Zhu, Minghao, et al.
Published: (2023)

Success is in the Details: Evaluate and Enhance Details Sensitivity of Code LLMs through Counterfactuals
by: Luo, Xianzhen, et al.
Published: (2025)

VIA: Unified Spatiotemporal Video Adaptation Framework for Global and Local Video Editing
by: Gu, Jing, et al.
Published: (2024)

MARS ‐Net: Multi‐Scale Attention Residual Spatiotemporal Network for Robust Left Ventricular Ejection Fraction Prediction in Echocardiography Videos
by: Shun Cheng, et al.
Published: (2025)

Explaining Reinforcement Learning: A Counterfactual Shapley Values Approach
by: Shi, Yiwei, et al.
Published: (2024)

Temporal-Aware GPU Resource Allocation for Distributed LLM Inference via Reinforcement Learning
by: Du, Chengze, et al.
Published: (2025)

A conjecture of Nadji, Ahmia and Ram\'ırez on congruences for biregular overpartitions
by: Tang, Dazhao
Published: (2025)

Simulation of lethal control and fertility control in a demographic model for Brandt's vole Microtus brandti. / Dazhao Shi
by: Shi, Dazhao
Published: (1995)

STRIVE: Structured Spatiotemporal Exploration for Reinforcement Learning in Video Question Answering
by: Bahrami, Emad, et al.
Published: (2026)

STEER: Structured Event Evidence for Video Reasoning via Multi-Objective Reinforcement Learning
by: Li, Zinuo, et al.
Published: (2026)

End-To-End Underwater Video Enhancement: Dataset and Model
by: Du, Dazhao, et al.
Published: (2024)

Counterfactually Fair Reinforcement Learning via Sequential Data Preprocessing
by: Wang, Jitao, et al.
Published: (2025)

Enhancing Efficiency and Exploration in Reinforcement Learning for LLMs
by: Liao, Mengqi, et al.
Published: (2025)

Efficient Medical VIE via Reinforcement Learning
by: Liu, Lijun, et al.
Published: (2025)