Haoxi Li

Towards Understanding Metacognition in Large Reasoning Models

ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping

DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning

Causally Motivated Sycophancy Mitigation for Large Language Models

Cross-modal Mitigation of Spurious Correlation for Prompt-tuning in VLMs with Causally Motivated Logic Alignment