Peng-Jun Xie

Cross-attentive MLLMs already solve the attribute-binding failures that cripple embedding models—and distilling their soft multi-level ranking distributions via Rank-KL unlocks that reasoning for bi-encoders without degrading standard recall.

Training agents on compressed contexts can lead to significant log-probability gaps, but innovative methods like LogitTree and SDCC offer a robust solution that maintains performance consistency.

ARISE-RL transforms agent training by enabling robust self-evolution through a novel rubric-mediated co-evolution framework, achieving state-of-the-art performance across diverse tasks.