An Zhang

7 papers University of Science and Technology of China

• AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
• Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation
• On Reasoning Strength Planning in Large Reasoning Models
• RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
• Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
• Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning
• The Emergence of Abstract Thought in Large Language Models Beyond Any Language