Data and models for the paper: Computer Environments Elicit General Agentic Intelli. Feel free to open an issue if you have any questions or problems!
Daixuan Cheng
daixuancheng
AI & ML interests
I study LLMs, from Pre-Training to Agent.
Recent Activity
updated a model about 8 hours ago
daixuancheng/4b-0404-2k published a model about 8 hours ago
daixuancheng/4b-0404-2k updated a model 10 days ago
daixuancheng/Qwen3-4B-Instruct-2507-LLM-in-Sandbox-RLOrganizations
None yet
models 138
daixuancheng/4b-0404-2k
4B • Updated
daixuancheng/Qwen3-4B-Instruct-2507-LLM-in-Sandbox-RL
4B • Updated • 1.46k • 1
daixuancheng/Qwen3-VL-8B-Thinking_stage1_MixAllRL
9B • Updated • 1
daixuancheng/Qwen3-VL-8B-Thinking_stage3_MixAllRL_and_dataMixRatio_and_easy2hard
9B • Updated • 1
daixuancheng/Qwen3-VL-8B-Thinking_stage2_MixAllRL_and_dataMixRatio
9B • Updated • 1
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step20
9B • Updated • 6
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step36
9B • Updated • 2
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step4
9B • Updated • 6
daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step10
9B • Updated • 1
daixuancheng/ppo_sac_static0.1_constrainbyadv_step-80_actor
Text Generation • 8B • Updated • 1