AIConfPaper
← Search

Chengyang He

8 accepted papers

2026

Demystifying Robot Diffusion Policies: Action Memorization and a Simple Lookup Table Alternative

Chengyang He, Xu Liu, Gadiel Mark Sznaier Camps, Joseph Bruno, Guillaume Adrien Sartoretti, Mac Schwager
ICLR 2026poster

Diffusion policies for visuomotor robot manipulation tasks achieve remarkable dexterity and robustness while only training on a small number of task demonstrations. However, the reason for this performance remains a mystery. In this paper, we offer a surprising hypothesis: diffusion policies essent…

Cited by 18Source ↗code ↗Scholar ↗
2026

P3GASUS: Pre-Planned Path Execution Graphs for Multi-Agent Systems at Ultra-Large Scale

Tanishq Duhan, Chengyang He, Guillaume Sartoretti
RA-L 2026

Executing pre-planned paths in multi-agent systems is challenging, as a lack of synchronization can lead to collisions or live-/deadlocks, while enforcing strict synchronization may cause a widespread team delay in reaching goals. An Action Dependency Graph (ADG) solves this problem by identifying a

Cited by 1Source ↗code ↗Scholar ↗
2026

P3GASUS: Pre-Planned Path Execution Graphs for Multi-Agent Systems at Ultra-Large Scale

Tanishq Harish Duhan, Chengyang He, Guillaume Adrien Sartoretti
ICRA 2026poster

Executing pre-planned paths in multi-agent systems is challenging, as a lack of synchronization can lead to collisions or live-/deadlocks, while enforcing strict synchronization may cause a widespread team delay in reaching goals. An Action Dependency Graph (ADG) solves this problem by identifying a…

Cited by 0Source ↗Scholar ↗
2026

Social Behavior as a Key to Learning-Based Multi-Agent Pathfinding Dilemmas (Abstract Reprint)

Chengyang He, Tanishq Duhan, Parth Tulsyan, Patrick Kim, Guillaume Sartoretti
AAAI 2026technical

The Multi-agent Path Finding (MAPF) problem involves finding collision-free paths for a team of agents in a known, static environment, with important applications in warehouse automation, logistics, or last-mile delivery. To meet the needs of these large-scale applications, current learning-based me

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Enhancing Teacher Classroom Behavior Descriptions: A Spatio-Temporal Graph-Based Method for Video Captioning

Ting Cai, Chengyang He, Yu Xiong
ICASSP 2025accepted

Teacher behavior description is an objective record of teachers’ behaviors in the teaching process, aiming to provide evidence for reflection on teaching behavior. Although video captioning technology can automatically generate behavior description, existing research on teacher behavior description…

Cited by 0Source ↗Scholar ↗
2025

Latent Theory of Mind: A Decentralized Diffusion Architecture for Cooperative Manipulation

Chengyang He, Gadiel Mark Sznaier Camps, Xu Liu, Mac Schwager, Guillaume Adrien Sartoretti
CoRL 2025oral

We present Latent Theory of Mind (LatentToM), a decentralized diffusion policy architecture for collaborative robot manipulation. Our policy allows multiple manipulators with their own perception and computation to collaborate with each other towards a common task goal with or without explicit commu…

Cited by 0Source ↗Scholar ↗
2025

SIGMA: Sheaf-Informed Geometric Multi-Agent Pathfinding

Shuhao Liao, Weihang Xia, Yuhong Cao, Weiheng Dai, Chengyang He, Wenjun Wu +1
ICRA 2025

The Multi-Agent Path Finding (MAPF) problem aims to determine the shortest and collision-free paths for multiple agents in a known, potentially obstacle-ridden environment. It is the core challenge for robotic deployments in large-scale logistics and transportation. Decentralized learningbased appro

Cited by 5Source ↗code ↗Scholar ↗
2024

ALPHA: Attention-based Long-horizon Pathfinding in Highly-structured Areas

Chengyang He, Tianze Yang, Tanishq Duhan, Yutong Wang, Guillaume Sartoretti
ICRA 2024poster

The multi-agent pathfinding (MAPF) problem seeks collision-free paths for a team of agents from their current positions to their pre-set goals in a known environment, and is an essential problem found at the core of many logistics, transportation, and general robotics applications. Existing learning…

Cited by 13Source ↗Scholar ↗