collaborators

5 papers

cs.CV2026

RescueBench: Can Embodied Agents Save Lives in the Wild ?

Kui Wu, Beiyu Guo, Hao Chen +6

Search-and-rescue (SAR) requires embodied agents to explore unfamiliar environments under multimodal uncertainty, perform multi-stage interactions, and retrieve spatial memory over…

cs.RO2026

AdaTracker: Learning Adaptive In-Context Policy for Cross-Embodiment Active Visual Tracking

Kui Wu, Hao Chen, Jinzhu Han +6

Realizing active visual tracking with a single unified model across diverse robots is challenging, as the physical constraints and motion dynamics vary drastically from one platfor…

cs.AI2025

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…

cs.CV2025

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…

cs.CV2025

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…