Kehai Chen

DualAnchor not only preserves language priors but also bridges the lexical fidelity gap in sign language translation, leading to significantly improved translation quality.

Emotional support chatbots can now learn to better understand and respond to your needs by actively probing for information, leading to more helpful and empathetic conversations.

RL fine-tuning can make your role-playing agent *worse* at embodying its character, unless you carefully balance task rewards with stylistic constraints.

LVLMs hallucinate in predictable bursts, and this self-rewarding decoding strategy slashes those errors in half.