Ke Shen

Reformulation for Pretraining Data Augmentation

Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask Learning

Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective

Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning

AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection

CURE: Co-Evolving Coders and Unit Testers via Reinforcement Learning

ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs

MMaDA: Multimodal Large Diffusion Language Models