Process Reward Modeling with Entropy-Driven Uncertainty.

Boosting Tool Use of Large Language Models via Iterative Reinforced Fine-Tuning.

ToolACE: Winning the Points of LLM Function Calling.

PAII: A Pose Alignment Network with Information Interaction for Person Re-identification.

Joint Attention-Driven Domain Fusion and Noise-Tolerant Learning for Multi-Source Domain Adaptation.

A multi-branch attention and alignment network for person re-identification.