Zejun MA

5 papers iscas

• Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
• General-Reasoner: Advancing LLM Reasoning Across All Domains
• Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models
• VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
• ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention