Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States
Paper • 2603.19987 • Published • 9
Yurun Yuan
RyanYr
AI & ML interests
None yet
Recent Activity
updated a model about 6 hours ago
RyanYr/asyncrl-sync_mb8_kimi_truncneg1_replay_ev128-gs20 updated a model about 6 hours ago
RyanYr/asyncrl-async_s5_mb8_grpg_kloldref_truncneg1_ev128-gs20 updated a model about 6 hours ago
RyanYr/asyncrl-async_s5_mb8_grpg_klref_truncneg1_ev128-gs20Organizations
None yet
upvoted 2
papers 7 months ago