Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States
Paper • 2603.19987 • Published • 9
Yurun Yuan PRO
RyanYr
AI & ML interests
None yet
Recent Activity
updated a dataset about 3 hours ago
RyanYr/grpo-dapo_shuffled-0_offline-grpo-dapo-qwen3-1.7B-Base-mbs128-n4-mbs128-n4_matheval updated a model about 5 hours ago
RyanYr/DAPO-Math-17k-grpo-dapo-qwen3-4B-Base-mbs128-n4_sft published a model about 5 hours ago
RyanYr/DAPO-Math-17k-grpo-dapo-qwen3-4B-Base-mbs128-n4_sftOrganizations
None yet
upvoted 2
papers about 1 month ago