arxiv:2510.08308
Xiao Yao
YaoYX
AI & ML interests
NLP
Recent Activity
upvoted a paper 2 days ago
Weak-to-Strong On-Policy Distillation upvoted a paper 5 days ago
FrontierChallenge: Evaluating Scientific Workflow Completion upvoted a paper 5 months ago
MiroEval: Benchmarking Multimodal Deep Research Agents in Process and OutcomeOrganizations
models 29
YaoYX/Llama-3.1-8B-Instruct-14k
8B • Updated • 4
YaoYX/Qwen2.5-7B-Instruct-1M-14k
8B • Updated • 3
YaoYX/Qwen2.5-7B-Instruct-1M-30k
8B • Updated • 5
YaoYX/llama-fac-qwen-7b-math-base-v9-packing-26k-5e5-e2-then-no-packing
8B • Updated • 2
YaoYX/llama-fac-qwen-7b-math-base-v9-no-packing-1e6-stage2
8B • Updated • 3
YaoYX/llama-fac-qwen-7b-math-base-v11-2node-packing-26k-5e5-16node
8B • Updated • 3
YaoYX/llama-fac-qwen-7b-math-base-v9-no-packing-from-e3-5e6-stage2
Updated
YaoYX/llama-fac-qwen-7b-math-base-v9-no-packing-from-e3-2e6-stage2
Updated
YaoYX/llama-fac-qwen-7b-math-base-v9-no-packing-from-e2-1e5-stage2
Updated
YaoYX/llama-fac-qwen-7b-math-base-v9-no-packing-5e6-nowarmup-stage2
Updated
datasets 20
YaoYX/reconstruction_validation
Viewer • Updated • 500 • 31
YaoYX/R1-Distill-Llama-70B-0-50000-1-50
Viewer • Updated • 40.3k • 13
YaoYX/R1-Distill-Llama-70B-0-50000-1-48
Viewer • Updated • 40.3k • 10
YaoYX/R1-Distill-Llama-70B-0-50000-1-46
Viewer • Updated • 40.3k • 13
YaoYX/R1-Distill-Llama-70B-0-50000-1-44
Viewer • Updated • 40.3k • 11
YaoYX/R1-Distill-Llama-70B-0-50000-1-42
Viewer • Updated • 40.3k • 15
YaoYX/R1-Distill-Llama-70B-0-50000-1-40
Viewer • Updated • 40.3k • 12
YaoYX/R1-Distill-Llama-70B-0-50000-1-38
Viewer • Updated • 40.3k • 6
YaoYX/R1-Distill-Llama-70B-0-50000-1-36
Viewer • Updated • 40.3k • 14
YaoYX/R1-Distill-Llama-70B-0-50000-1-34
Viewer • Updated • 40.3k • 11