activity
20242026
collaborators

9 papers

cs.CV2026

HarmoniDPO: Video-guided Audio Generation via Preference-Optimized Diffusion

Wenshuo Peng, Kaipeng Zhang

Video-to-audio (V2A) generation faces significant challenges in achieving precise temporal synchronization and high perceptual quality due to the complex, ambiguous relationship be…

cs.CV2026

Sekai2: From World Exploration to Interactive World Modeling

Kang He, Wenshuo Peng, Zihui Gao +3

Video world models must capture how scenes evolve over time and across viewpoints. Training them for long-horizon generation and camera control therefore benefits from long videos…

cs.CL2026

GraphWalker: Agentic Knowledge Graph Question Answering via Synthetic Trajectory Curriculum

Shuwen Xu, Yao Xu, Jiaxiang Liu +4

Agentic knowledge graph question answering (KGQA) requires an agent to iteratively interact with knowledge graphs (KGs), posing challenges in both training data scarcity and reason…

cs.CV2026

SVBench: Evaluation of Video Generation Models on Social Reasoning

Wenshuo Peng, Gongxuan Wang, Tianmeng Yang +4

Recent text-to-video generation models have made remarkable progress in visual realism, motion fidelity, and text-video alignment, yet they still struggle to produce socially coher…

cs.CV2026

WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG

Zhen Li, Zian Meng, Shuwei Shi +5

Dynamical systems theory and reinforcement learning view world evolution as latent-state dynamics driven by actions, with visual observations providing partial information about th…

cs.AI2026

PyVision-RL: Forging Open Agentic Vision Models via RL

Shitian Zhao, Shaoheng Lin, Ming Li +4

Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefit…