Chi Zhang

Quantum state discrimination errors are reduced by 2x by encoding auxiliary qubit readout signals and dynamically calibrating neural decoders to the evolving circuit environment.

Robot skills can be learned with significantly higher precision in critical phases by adaptively allocating DMP basis functions, outperforming existing methods in accuracy and generalization.

Forcing moving wrist cameras to predict future pixels actively degrades policy performance—decoupling static scene reconstruction from dynamic wrist latent prediction yields up to a 12.8% boost in contact-rich manipulation with zero inference cost.

Diffusion teachers and online score networks are no longer bottlenecks for distilling autoregressive video models: directly minimizing sample MMD against reference videos improves VBench scores while unlocking 14B post-training on just eight H200 GPUs.

Single-step diffusion models can outperform their multi-step teachers when distributional matching is reformulated as a Wasserstein gradient flow over Gaussian mixtures.