m-a-p/OProver-32B-Round1
33B β’ Updated β’ 16
AI & ML interests
None defined yet.
Recent Activity
Papers
A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation
m-a-p/OProver-8B-Round2
8B β’ Updated β’ 19
m-a-p/OProver-8B-Round1
8B β’ Updated β’ 18
m-a-p/OProver-32B
33B β’ Updated β’ 17
m-a-p/OProver-8B
8B β’ Updated β’ 20
m-a-p/OProver-8B-Base
8B β’ Updated β’ 19
m-a-p/OProver-32B-Base
33B β’ Updated β’ 22
m-a-p/TerminalTraj-32B
33B β’ Updated β’ 9
m-a-p/TerminalTraj-7B
8B β’ Updated β’ 2 β’ 2
m-a-p/TerminalTraj-14B
15B β’ Updated β’ 6 β’ 1
m-a-p/CoDiQ-Gen-8B
8B β’ Updated β’ 2
m-a-p/TreePO-Qwen2.5-7B
Text Generation β’ 8B β’ Updated β’ 7 β’ 2
m-a-p/transformer_340M_baseline
0.3B β’ Updated β’ 8
m-a-p/transformer_1.3B_baseline
1B β’ Updated β’ 683
m-a-p/TreePO-Qwen2.5-7B_Naive2Low_Scheduler
8B β’ Updated β’ 2
m-a-p/TreePO-Qwen2.5-7B_Low_Prob_Encourage
8B β’ Updated β’ 1
m-a-p/TreePO-Qwen2.5-7B_GRPO-TreePO-Sampling
8B β’ Updated β’ 4
m-a-p/TreePO-Qwen2.5-7B_fixed-div
8B β’ Updated β’ 2
m-a-p/CriticLeanGPT-Qwen2.5-32B-RL
33B β’ Updated β’ 1
m-a-p/CriticLeanGPT-Qwen2.5-14B-RL
15B β’ Updated β’ 1 β’ 1
m-a-p/CriticLeanGPT-Qwen2.5-7B-RL
15B β’ Updated β’ 6 β’ 1
m-a-p/CriticLeanGPT-Qwen2.5-7B-Instruct-SFT-RL
8B β’ Updated β’ 1 β’ 1
m-a-p/CriticLeanGPT-Qwen2.5-32B-Instruct-SFT-RL
33B β’ Updated β’ 1
m-a-p/CriticLeanGPT-Qwen2.5-32B-Instruct-SFT
Text Generation β’ Updated β’ 5
m-a-p/CriticLeanGPT-Qwen2.5-14B-Instruct-SFT-RL
15B β’ Updated β’ 3 β’ 1
m-a-p/CriticLeanGPT-Qwen2.5-14B-Instruct-SFT
Text Generation β’ 15B β’ Updated β’ 5 β’ 1
m-a-p/CriticLeanGPT-Qwen2.5-7B-Instruct-SFT
Text Generation β’ 8B β’ Updated β’ 5 β’ 1
m-a-p/CriticLeanGPT-Qwen3-32B-RL
33B β’ Updated β’ 15
m-a-p/CriticLeanGPT-Qwen3-14B-RL
15B β’ Updated β’ 26
m-a-p/CriticLeanGPT-Qwen3-8B-RL
8B β’ Updated β’ 7 β’ 4