daixuancheng/Qwen3-Coder-30B-A3B-Instruct-LLM-in-Sandbox-RL
31B • Updated
Daixuan Cheng
daixuancheng
AI & ML interests
I work on LLMs across pre-training, post-training, and agents.
Recent Activity
upvoted a paper about 18 hours ago
Harness Scaling for Generalizable Agentic Reinforcement Learning updated a model about 19 hours ago
daixuancheng/Qwen3-Coder-30B-A3B-Instruct-LLM-in-Sandbox-RL published a model about 19 hours ago
daixuancheng/Qwen3-Coder-30B-A3B-Instruct-LLM-in-Sandbox-RLOrganizations
daixuancheng/Qwen3-4B-Instruct-2507-LLM-in-Sandbox-RL-Context-in-Prompt
4B • Updated
daixuancheng/Qwen3-4B-Instruct-2507-LLM-in-Sandbox-RL-SWE
4B • Updated
daixuancheng/Qwen3-4B-Instruct-2507-LLM-in-Sandbox-RL-Math
4B • Updated
daixuancheng/Qwen3-4B-Instruct-2507-LLM-in-Sandbox-RL
4B • Updated • 13 • 1
daixuancheng/4-26-debugAdv_docker_rbs8_temp0.7_model-30BA3B-Sft_step99
31B • Updated • 5
daixuancheng/4-26-debugAdv_docker_rbs8_temp0.7_model-30BA3B-Sft_step39
31B • Updated • 8
daixuancheng/4-26-debugAdv_docker_rbs8_temp0.7_model-30BA3B-Sft_step9
31B • Updated • 6
daixuancheng/4-24-30BA3B-s233-final
31B • Updated • 6
daixuancheng/4-23_docker_rbs32_model-Coder_step15
Text Generation • 31B • Updated • 8
daixuancheng/0418_17K_filtered_10K_reward0.5_4b_inst
4B • Updated • 6
daixuancheng/4b-0404-2k
4B • Updated • 5
daixuancheng/Qwen3-VL-8B-Thinking_stage1_MixAllRL
9B • Updated • 9
daixuancheng/Qwen3-VL-8B-Thinking_stage3_MixAllRL_and_dataMixRatio_and_easy2hard
9B • Updated • 6
daixuancheng/Qwen3-VL-8B-Thinking_stage2_MixAllRL_and_dataMixRatio
9B • Updated • 6
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step20
9B • Updated • 9
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step36
9B • Updated • 10
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step4
9B • Updated • 8
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step10
9B • Updated • 7