Xuanjing Huang

Affiliations

Fudan University

papers

299

total citations

papers (14)

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

CVPR 2025arXiv

citations

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

ICML 2024arXiv

citations

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

AAAI 2025arXiv

citations

Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs

ICLR 2025arXiv

citations

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

ICCV 2025arXiv

citations

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

NEURIPS 2025arXiv

citations

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

AAAI 2025arXiv

citations

Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation

COLM 2025arXiv

citations

Regularized Molecular Conformation Fields

NEURIPS 2022

citations

Alleviating Shifted Distribution in Human Preference Alignment through Meta-Learning

AAAI 2025

citations

Xuanjing Huang

Affiliations

papers (14)

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

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

RMB: Comprehensively benchmarking reward models in LLM alignment

CoNT: Contrastive Neural Text Generation

Efficient and Effective Time-Series Forecasting with Spiking Neural Networks

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

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

Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs

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

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

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

Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation

Regularized Molecular Conformation Fields

Alleviating Shifted Distribution in Human Preference Alignment through Meta-Learning

papers (14)

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

Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

RMB: Comprehensively benchmarking reward models in LLM alignment

CoNT: Contrastive Neural Text Generation

Efficient and Effective Time-Series Forecasting with Spiking Neural Networks

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

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

Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs

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

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

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

Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation

Regularized Molecular Conformation Fields

Alleviating Shifted Distribution in Human Preference Alignment through Meta-Learning