arxiv:2602.18940
Changhao
lichangh20
AI & ML interests
RL, Agent, Efficient ML
Recent Activity
upvoted a paper 23 days ago
Revisiting DAgger in the Era of LLM-Agents submitted a paper 23 days ago
Revisiting DAgger in the Era of LLM-Agents updated a model about 1 month ago
lichangh20/qwen3-8b-online-dagger-aggrevate-iter3Organizations
models 29
lichangh20/qwen3-8b-online-dagger-aggrevate-iter3
Text Generation • 8B • Updated • 6
lichangh20/qwen3-8b-online-dagger-aggrevate-iter2
Text Generation • 8B • Updated • 6
lichangh20/externel_0505_ckpts_2
Updated
lichangh20/externel_0505_results
Updated
lichangh20/externel_0505_ckpts_1
Updated
lichangh20/externel_0505
Updated
lichangh20/external_2
Updated
lichangh20/external
Updated
lichangh20/qwen3-4b-online-dagger
Updated
lichangh20/qwen3-8b-rope5m-64k-distcp
Updated
datasets 20
lichangh20/stacx-swe-online-dagger-data
Viewer • Updated • 4.98k • 32
lichangh20/stacx-skyrl-swe-train-293
Viewer • Updated • 285 • 26
lichangh20/stacx-iter-sft-corpus-qwen30bcoder
Updated • 31
lichangh20/qwen3-coder-30b-swegym-train-eval-100-kl-cache
Updated • 417
lichangh20/stacx-eval-data
Viewer • Updated • 19.5k • 11
lichangh20/s1K_initial_filtered_for_llama8b
Viewer • Updated • 1k • 3
lichangh20/olympiadbench
Viewer • Updated • 674 • 25
lichangh20/minervamath
Viewer • Updated • 272 • 10
lichangh20/s1K_simplified_filtered_for_adapter
Viewer • Updated • 927 • 4
lichangh20/s1K_initial_filtered_for_qwen7b_simplified_summarized
Viewer • Updated • 997 • 5