6 papers
Structured Latent Dynamics for Long-Horizon Embodied World Models
Kevin Chen, Yu-Wei Zhan, Haoran Liang +2
Reliable long-horizon prediction remains a central challenge for embodied world models. Although recent generative models can synthesize visually plausible action-conditioned futur…
AerialDojo-200K: A Large-Scale Benchmark Suite for Open-World Aerial Object-Goal Search
Tongtong Feng, Xin Wang, Haoran Hou +9
Open-world aerial object-goal search is a foundational yet challenging task, requiring aerial agents to autonomously explore large-scale, unstructured three-dimensional environment…
Modularized Dynamic-Granularity Video LLM for Multi-Event Long Video Understanding
Wei Feng, Xin Wang, Yu-Wei Zhan +2
Video Large Language Models (Video LLMs) have made significant advancements in various video understanding tasks. However, long-video scenarios remain challenging due to the tensio…
PhyVLLM: Physics-Guided Video Language Model with Motion-Appearance Disentanglement
Yu-Wei Zhan, Xin Wang, Hong Chen +6
Video Large Language Models (Video LLMs) have shown impressive performance across a wide range of video-language tasks. However, they often fail in scenarios requiring a deeper und…
BiTAgent: A Task-Aware Modular Framework for Bidirectional Coupling between Multimodal Large Language Models and World Models
Yu-Wei Zhan, Xin Wang, Pengzhe Mao +3
Building generalist embodied agents requires a unified system that can interpret multimodal goals, model environment dynamics, and execute reliable actions across diverse real-worl…
EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks
Tongtong Feng, Xin Wang, Zekai Zhou +5
Completing Long-Horizon (LH) tasks in open-ended worlds is an important yet difficult problem for embodied agents. Existing approaches suffer from two key challenges: (1) they heav…