10 papers
GuardPIBT: Counterfactually Gated Neural Guidance for Ultra-Large-Scale 3D Multi-Agent Path Finding
Yuan Zhou, Zhenyu Hou, Guangtong Xu +4
Large-scale 3D multi-agent path finding becomes increasingly difficult under dense traffic. Priority Inheritance with Backtracking (PIBT) scales well, but its one-step goal-directe…
CometVLA: Co-Training on an Embodied Data Pyramid towards Physical Understanding
Hanwen Wan, Dafeng Chi, Linbo Zhai +6
Vision-language-action (VLA) models remain brittle in manipulation tasks that require physical commonsense. Current physical VQA data is typically disembodied and misaligned with r…
ResemBrick: Brick Reconstruction from Photographs with Perceptual Fidelity and Buildability
Xilun Chen, Hanwen Wan, Yusong Zhao +3
Producing a hand-buildable, colored brick model of a 3D object from a few casual photographs is a clean testbed for a broader challenge: generating 3D content that meets hard physi…
CoWork-X: Experience-Optimized Co-Evolution for Multi-Agent Collaboration System
Zexin Lin, Jiachen Yu, Haoyang Zhang +5
Large language models are enabling language-conditioned agents in interactive environments, but highly cooperative tasks often impose two simultaneous constraints: sub-second real-…
Efficient Coordination with the System-Level Shared State: An Embodied-AI Native Modular Framework
Yixuan Deng, Tongrun Wu, Donghao Wu +5
As Embodied AI systems move from research prototypes to real world deployments, they tend to evolve rapidly while remaining reliable under workload changes and partial failures. In…
A Learning-based Control Methodology for Transitioning VTOL UAVs
Zexin Lin, Yebin Zhong, Hanwen Wan +3
Transition control poses a critical challenge in Vertical Take-Off and Landing Unmanned Aerial Vehicle (VTOL UAV) development due to the tilting rotor mechanism, which shifts the c…
Value-Guided Iterative Refinement and the DIQ-H Benchmark for Evaluating VLM Robustness
Hanwen Wan, Zexin Lin, Yixuan Deng +1
Vision-Language Models (VLMs) are essential for embodied AI and safety-critical applications, such as robotics and autonomous systems. However, existing benchmarks primarily focus…
Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data
Deng Yixuan, Ji Xiaoqiang
Large Language Models (LLMs) often exhibit implicit biases and discriminatory tendencies that reflect underlying social stereotypes. While recent alignment techniques such as RLHF…
GenTe: Generative Real-world Terrains for General Legged Robot Locomotion Control
Hanwen Wan, Mengkang Li, Donghao Wu +4
Developing bipedal robots capable of traversing diverse real-world terrains presents a fundamental robotics challenge, as existing methods using predefined height maps and static e…
EmbodiedAgent: A Scalable Hierarchical Approach to Overcome Practical Challenge in Multi-Robot Control
Hanwen Wan, Yifei Chen, Yixuan Deng +6
This paper introduces EmbodiedAgent, a hierarchical framework for heterogeneous multi-robot control. EmbodiedAgent addresses critical limitations of hallucination in impractical ta…