An Zhang

Full Professor@University of Science and Technology of China·中国·OpenReview

研究方向

Safety of Large Language Model · Collaborative Filtering · Recommender System · Explainable · Trustable and Robust Algorithom · Causality · Causal Inference · Causal Discovery

An Zhang

AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint

Reinforced Preference Optimization for Recommendation

Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning

Denoising Neural Reranker for Recommender Systems

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning

Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents

bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs

SINGER: Leveraging Semantic Identifier Hierarchies for Generative Recommendation

Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning

Language Representations Can be What Recommenders Need: Findings and Potentials

On Reasoning Strength Planning in Large Reasoning Models

Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models

Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation

The Emergence of Abstract Thought in Large Language Models Beyond Any Language

Debiased Orthogonal Boundary-driven Efficient Noise Mitigation

Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment

RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards

Preference Diffusion for Recommendation

One-step Noisy Label Mitigation

Neuron-Level Sequential Editing for Large Language Models