arxiv:2611.16009
Zefan Wang
ZefanW
AI & ML interests
None yet
Recent Activity
authored a paper about 11 hours ago
JustRUA: A Controlled Study of GPT-6 Robot-Use Agents authored a paper about 11 hours ago
DRIFT: Data Selection for LLM Instruction Tuning via On-Policy Attribution upvoted a paper about 17 hours ago
JustRUA: A Controlled Study of GPT-6 Robot-Use AgentsOrganizations
None yet
models 7
ZefanW/webinst_vrQwen2.5Base_VRAccFilter0.03-0.97_clip0.27_WebInst_b768_mbs192_lr1e-6_r3_n8_e100-4node
Updated
ZefanW/simpo-baseline-1e-7
Text Generation • 8B • Updated • 1
ZefanW/simpo-baseline
Text Generation • 8B • Updated • 2
ZefanW/simpo-baseline-448
8B • Updated • 1
ZefanW/dpo-baseline-448
8B • Updated • 1
ZefanW/dpo-baseline
Text Generation • 8B • Updated • 1
ZefanW/dpo-prm
8B • Updated • 18