arxiv:2601.16206
Daixuan Cheng
daixuancheng
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 hours ago
SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
upvoted
a
paper
about 2 hours ago
SWE-World: Building Software Engineering Agents in Docker-Free Environments
upvoted
a
paper
about 23 hours ago
Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning
Organizations
None yet
models
137
daixuancheng/Qwen3-4B-Instruct-2507-LLM-in-Sandbox-RL
4B
•
Updated
•
6
daixuancheng/Qwen3-VL-8B-Thinking_stage1_MixAllRL
9B
•
Updated
daixuancheng/Qwen3-VL-8B-Thinking_stage3_MixAllRL_and_dataMixRatio_and_easy2hard
9B
•
Updated
daixuancheng/Qwen3-VL-8B-Thinking_stage2_MixAllRL_and_dataMixRatio
9B
•
Updated
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step20
9B
•
Updated
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step36
9B
•
Updated
•
16
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step4
9B
•
Updated
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step10
9B
•
Updated
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-80_actor
Text Generation
•
8B
•
Updated
•
1
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-20_actor
Text Generation
•
8B
•
Updated
•
1