6 papers
Reinforced Context Order Recovery for Adaptive Reasoning and Planning
Long Ma, Fangwei Zhong, Yizhou Wang
Modern causal language models, followed by rapid developments in discrete diffusion models, can now produce a wide variety of interesting and useful content. However, these familie…
VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models
Kui Wu, Shuhang Xu, Hao Chen +4
We introduce a novel self-improving framework that enhances Embodied Visual Tracking (EVT) with Vision-Language Models (VLMs) to address the limitations of current active visual tr…
Hierarchical Instruction-aware Embodied Visual Tracking
Kui Wu, Hao Chen, Churan Wang +4
User-Centric Embodied Visual Tracking (UC-EVT) presents a novel challenge for reinforcement learning-based models due to the substantial gap between high-level user instructions an…
DyWA: Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation
Jiangran Lyu, Ziming Li, Xuesong Shi +3
Nonprehensile manipulation is crucial for handling objects that are too thin, large, or otherwise ungraspable in unstructured environments. While conventional planning-based approa…
UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI
Fangwei Zhong, Kui Wu, Churan Wang +4
We introduce UnrealZoo, a collection of over 100 photo-realistic 3D virtual worlds built on Unreal Engine, designed to reflect the complexity and variability of open-world environm…
Simulating Human-like Daily Activities with Desire-driven Autonomy
Yiding Wang, Yuxuan Chen, Fangwei Zhong +2
Desires motivate humans to interact autonomously with the complex world. In contrast, current AI agents require explicit task specifications, such as instructions or reward functio…