Jianwei Zhang

GEAR accelerates image synthesis convergence by up to 10x while enhancing feature coherence, challenging the traditional decoupling of tokenizers and generators.

MTP acceptance rates can be dramatically improved by addressing entropy fluctuations, leading to up to 1.8x faster RL training.

Forget coding skills, the future of education is teaching "intellectual stewardship"—a framework for humans to responsibly govern AI-augmented knowledge creation.

Ditch slow, iterative ODE solvers for robot control: this method distills flow-based policies into a single-step model that's fast enough for real-time replanning without sacrificing multi-modal action diversity.

A robot can now achieve 90% success in peg-in-hole tasks, even with only 0.1mm clearance, by intelligently fusing vision and tactile feedback when visual occlusion occurs.

Humanoid robots can now perform complex loco-manipulation tasks with more natural and stable movements by decomposing control into VLM-orchestrated expert policies trained with human motion priors.