Xuanjing Huang

9

Papers

3

Total Citations

Papers (9)

EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving

ObjectRelator: Enabling Cross-View Object Relation Understanding Across Ego-Centric and Exo-Centric Perspectives

Alleviating Shifted Distribution in Human Preference Alignment through Meta-Learning

COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism

Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks

LLMEval: A Preliminary Study on How to Evaluate Large Language Models

Efficient and Effective Time-Series Forecasting with Spiking Neural Networks

SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Models

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning