arxiv:2602.18940
Changhao
lichangh20
AI & ML interests
RL, Agent, Efficient ML
Recent Activity
updated a dataset 1 day ago
lichangh20/stacx-swe-online-dagger-data updated a model 1 day ago
lichangh20/qwen3-4b-instruct-sft-swegym-iter0 published a model 1 day ago
lichangh20/qwen3-4b-instruct-sft-swegym-iter0Organizations
models 14
lichangh20/qwen3-4b-instruct-sft-swegym-iter0
Text Generation • 4B • Updated • 14
lichangh20/qwen3-4b-instruct-sft-swegym-iter0-distcp
Updated
lichangh20/qwen3-4b-instruct-sft-swegym-iter2
Text Generation • 4B • Updated • 282
lichangh20/qwen3-4b-instruct-sft-swegym-iter2-distcp
Updated
lichangh20/qwen3-4b-instruct-sft-swegym-iter1-distcp
Updated
lichangh20/qwen3-4b-instruct-sft-swegym-iter1
Text Generation • 4B • Updated • 272
lichangh20/s1k_format_filtered_sft
8B • Updated • 15
lichangh20/Qwen3-Coder-30B-A3B-HF_sft_mle_execution_tree_and_analysis
31B • Updated • 1
lichangh20/Qwen3-Coder-30B-A3B-HF_sft_mle_execution
31B • Updated • 1
lichangh20/Qwen3-Coder-30B-A3B-HF_sft_mle_tree_and_analysis
31B • Updated • 2
datasets 17
lichangh20/stacx-swe-online-dagger-data
Viewer • Updated • 4.98k • 26
lichangh20/stacx-eval-data
Viewer • Updated • 19.5k • 6
lichangh20/s1K_initial_filtered_for_llama8b
Viewer • Updated • 1k • 7
lichangh20/olympiadbench
Viewer • Updated • 674 • 10
lichangh20/minervamath
Viewer • Updated • 272 • 10
lichangh20/s1K_simplified_filtered_for_adapter
Viewer • Updated • 927 • 3
lichangh20/s1K_initial_filtered_for_qwen7b_simplified_summarized
Viewer • Updated • 997 • 4
lichangh20/s1K_initial_filtered_for_qwen7b_summarized
Viewer • Updated • 997 • 7
lichangh20/s1K_filtered_for_qwen7b_sft
Viewer • Updated • 899 • 3
lichangh20/s1k_eval_sampled_1of12
Viewer • Updated • 77 • 9