12 papers
Aging in a spin glass with logarithmic correlations
Aser Cortines, Oren Louidor, Heng Ma +1
We consider a continuous-time random walk on the discrete two dimensional box, driven by the discrete Gaussian Free Field (DGFF) acting as potential: When at a vertex, the walk wai…
AutoIntervene: Calibrated Intervention for Action-Chunking Imitation Learning Policies
Jinhe Tang, Weiming Zhi
Action-chunking visuomotor policies learn from demonstrations and improve temporal consistency by predicting short action sequences rather than single-step commands. Yet perception…
Tri-Manual Visuomotor Imitation Learning of Robot Policies
James Zhao, Mingyuan Ba, Weiming Zhi
The paper introduces TriManPolicy, a system that lets a single operator demonstrate tasks for three robot arms by offline retiming the demonstrations with a Dependency-Aware Tri-Ar…
BayesFP: Posterior Estimation for Flow-Based Policies via Feynman-Kac Sampling
Sreevardhan Sirigiri, Weiming Zhi, Fabio Ramos
Robots must generate trajectories that remain faithful to learned expert behavior while satisfying safety constraints and task-specific objectives specified only at inference time.…
TRACE: Trajectory-Routed Causal Memory for Delayed-Evidence Visuomotor Imitation
Zihao Li, Ranpeng Qiu, Yincong Chen +2
Robots under autonomous operation may require decisions based on evidence that is no longer visible. We study delayed-evidence tasks, where an early cue disappears before a later d…
PATCH: Action-Chunk-Conditioned Latent Patch Innovation Monitoring for Robot Manipulation
Yanan Zhou, Ranpeng Qiu, Yincong Chen +2
Learning-based manipulation policies have made substantial progress in real-world robot manipulation, particularly for short-horizon action generation. However, deployment in open…