Xiaoyun Wang

Treating on-policy distillation as value-based RL slashes rollout compute by 75% while actively preserving the generation diversity needed for high-k reasoning.

KeepAD achieves a 7.9× speedup in zero-shot anomaly detection while preserving crucial defect information, challenging the trade-off between efficiency and accuracy.

A single elastic model can adapt to multiple sparsity configurations without re-optimization, revolutionizing LLM deployment efficiency.

Achieve state-of-the-art gait recognition by dynamically fusing body shape and motion features, even when people are wearing coats.