Xiaodong Liu

FlowRL: Matching Reward Distributions for LLM Reasoning

Training Large Reasoning Models Efficiently via Progressive Thought Encoding

SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks

MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Stress-testing LLM Safety

Coupling Attention and Memory: A Dynamic Memory Module for Efficient Adapation with Pretrained LLMs

SAS: Simulated Attention Score

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

Model Tells Itself Where to Attend: Steerable Prompting for Reliable Reading Comprehension of LLM