Xingyu Zhang

Robots can now learn complex manipulation skills from human videos by focusing on transferable causal dependencies, bypassing the need for direct motion imitation.

GUPO reveals that accounting for gradient uncertainty can dramatically improve policy optimization in post-training LLMs, leading to more effective reasoning capabilities.

Quantum simulations could revolutionize our understanding of molecular reaction dynamics, but they face critical theoretical challenges that could limit their effectiveness.

Over-smoothing in time series forecasts can be mitigated by a novel framework that preserves distinct dynamic modes, leading to more accurate and diverse predictions.

Models can learn to self-differentiate between tasks requiring rigorous planning versus direct generation in creative writing, unlocking a new level of meta-cognitive ability.