Amy Zhang

Iterative reasoning with Vision-Language Models can drastically improve mapless navigation success rates by dynamically identifying and refining relevant environmental cues.

Prefix failure in on-policy distillation can be effectively mitigated by correcting problematic prefixes, leading to significant improvements in reasoning coverage and accuracy.

Forget policy gradients: Value Gradient Flow (VGF) offers a simpler, more scalable way to align LLMs by directly optimizing value functions via optimal transport.