Linchao Zhu

Multi-step flow-matching policies can achieve single-step control latencies by pipelining partially denoised action trajectories through an asynchronous rolling buffer.

Increased availability of verifiers often comes at the cost of their credibility, revealing a critical trade-off in robot policy evaluation.

VISTA achieves a remarkable accuracy increase in GUI grounding tasks by leveraging multiple views, transforming how models learn from visual data.