5 papers
JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts
Zheyuan Zhang, Suyu Ye, Nakul Agarwal +5
World models enable agents to plan by predicting future states of the environment, but their predictions can become unreliable when test-time dynamics differ from those seen during…
3D-Belief: Embodied Belief Inference via Generative 3D World Modeling
Yifan Yin, Zehao Wen, Suyu Ye +10
Recent advances in visual generative models have highlighted the promise of learning generative world models. However, most existing approaches frame world modeling as novel-view s…
Safe and Interpretable Multimodal Path Planning for Multi-Agent Cooperation
Haojun Shi, Suyu Ye, Katherine M. Guerrerio +5
Successful cooperation among decentralized agents requires each agent to quickly adapt its plan to the behavior of other agents. In scenarios where agents cannot confidently predic…
RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users
Suyu Ye, Haojun Shi, Darren Shih +3
To achieve successful assistance with long-horizon web-based tasks, AI agents must be able to sequentially follow real-world user instructions over a long period. Unlike existing w…
MuMA-ToM: Multi-modal Multi-Agent Theory of Mind
Haojun Shi, Suyu Ye, Xinyu Fang +4
Understanding people's social interactions in complex real-world scenarios often relies on intricate mental reasoning. To truly understand how and why people interact with one anot…