Models from the paper "LaSeR: Reinforcement Learning with Last-Token Self-Rewarding"
Wenkai Yang
Keven16
AI & ML interests
None yet
Recent Activity
upvoted a paper about 4 hours ago
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression upvoted a paper 3 months ago
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation authored a paper 3 months ago
Rethinking Continual Experience Internalization for Self-Evolving LLM AgentsOrganizations
None yet
models 18
Keven16/Qwen3-4B-Non-Thinking-RL-Code-Step1200
4B • Updated • 109
Keven16/Qwen3-4B-Non-Thinking-RL-Code-Step300
4B • Updated • 103 • 1
Keven16/Qwen3-4B-Non-Thinking-RL-Math-Step1200
4B • Updated • 392
Keven16/Qwen3-4B-Non-Thinking-RL-Math-Step500
4B • Updated • 617 • 1
Keven16/Qwen2.5-7B-LaSeR
8B • Updated • 6
Keven16/OctoThinker-3B-Short-LaSeR
4B • Updated • 6
Keven16/ORZ-7B-LaSeR
8B • Updated • 6
Keven16/DeepCritic-7B-RL1.5-PRM800K
8B • Updated • 4
Keven16/DeepCritic-7B-RL1.5-Numina
8B • Updated • 6
Keven16/Qwen2.5-32B-TOPS-Iter-DPO-Preview
33B • Updated • 2
datasets 6
Keven16/OPSD-Example-Data
Viewer • Updated • 49.1k • 37
Keven16/G-OPD-Training-Data
Viewer • Updated • 134k • 580 • 3
Keven16/LaSeR_training_data
Viewer • Updated • 104k • 39 • 2
Keven16/TOPS-Data
Preview • Updated • 60
Keven16/DeepCritic-RL-Data
Viewer • Updated • 55k • 24
Keven16/DeepCritic-4.5K
Preview • Updated • 11