Surgical Post-Training: Cutting Errors, Keeping Knowledge
Paper • 2603.01683 • Published • 12
Zhaoyang Zhang
Vacrs
·
AI & ML interests
None yet
Organizations
None yet
upvoted a paper 3 months ago
upvoted 3
papers 7 months ago
Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning
Paper • 2510.19338 • Published • 117
Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model
Paper • 2510.18855 • Published • 73
Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks
Paper • 2510.08002 • Published • 24