Jun Xu

StyliTruth : Unlocking Stylized yet Truthful LLM Generation via Disentangled Steering

CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment

Mechanistic Detection and Mitigation of Hallucination in Large Reasoning Models

PureCover: Bridging the Gap in Re-ranking for Retrieval-Augmented Generation via Balancing Coverage and Noise

Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm

ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability

From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents

Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation

Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents

Length-Induced Embedding Collapse in Transformer-based Models