Daixuan Cheng's picture

Daixuan Cheng

daixuancheng

·

https://cdxeve.github.io

DaixuanC45443

AI & ML interests

I study LLMs, from Pre-Training to Agent.

Recent Activity

updated a dataset 1 day ago

daixuancheng/llm-in-sandbox-rl

updated a dataset 2 days ago

daixuancheng/llm-in-sandbox-bench

authored a paper 9 days ago

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training

View all activity

Organizations

None yet

daixuancheng 's models 136

daixuancheng/Qwen3-VL-8B-Thinking_stage1_MixAllRL

9B • Updated Dec 19, 2025

daixuancheng/Qwen3-VL-8B-Thinking_stage3_MixAllRL_and_dataMixRatio_and_easy2hard

9B • Updated Dec 19, 2025

daixuancheng/Qwen3-VL-8B-Thinking_stage2_MixAllRL_and_dataMixRatio

9B • Updated Dec 19, 2025

daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step20

9B • Updated Nov 29, 2025

daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step36

9B • Updated Nov 29, 2025

daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step4

9B • Updated Nov 29, 2025

daixuancheng/Qwen3-VL-8B-Thinking_multisub_kaiyuanTiankong_resplen8192_sp2_gentp2_step10

9B • Updated Nov 29, 2025

daixuancheng/ppo_sac_static0.1_constrainbyadv_step-80_actor

Text Generation • 8B • Updated Jun 26, 2025 • 1

daixuancheng/ppo_sac_static0.1_constrainbyadv_step-20_actor

Text Generation • 8B • Updated Jun 26, 2025 • 2

daixuancheng/ppo_sac_static0.1_constrainbyadv_step-80_critic

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/ppo_sac_static0.1_constrainbyadv_step-20_critic

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/ppo_sac_static0.1_constrainbyadv_step-60_critic

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/ppo_sac_static0.1_constrainbyadv_step-120_critic

Text Generation • 8B • Updated Jun 25, 2025 • 4

daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step80_crtic

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step20_crtic

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step120_crtic

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step60_crtic

Text Generation • 8B • Updated Jun 25, 2025 • 6

daixuancheng/ppo_sac_static0.1_constrainbyadv_step-120_actor

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/ppo_sac_static0.1_constrainbyadv_step-60_actor

Text Generation • 8B • Updated Jun 25, 2025 • 1

daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step120_actor

Text Generation • 8B • Updated Jun 25, 2025 • 1

daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step60_actor

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step20_actor

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/ppo_sample8_critic-warm10-lr2e-6_step80_actor

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/sac_static0.4_constrainbyAdv_step80

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step80

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/sac_static0.1_constrainbyAdv_step80

Text Generation • 8B • Updated Jun 25, 2025

daixuancheng/sac_static0.1_constrainbyAdv_step120

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/sac_static0.4_constrainbyAdv_step60

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/zero_7b_base_useTokenLoss_clipHigh_KLcoeff0_step60

Text Generation • 8B • Updated Jun 25, 2025 • 2

daixuancheng/sac_static0.1_constrainbyAdv_step60

Text Generation • 8B • Updated Jun 25, 2025 • 2