Datasets used in the paper
🤝 Open to Collab
Jiayu (Mila) Wang
MilaWang
AI & ML interests
Large Language Model, Multimodal Large Language Model, Agentic System, Reasoning, Efficiency
Recent Activity
upvoted a paper 1 day ago
Register Tokens for Bounded-State Reasoning in Diffusion Language Models upvoted a paper 3 days ago
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight upvoted a paper 30 days ago
EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?Organizations
models 76
MilaWang/grpo-fullparam-qwen2-5-math-7b-answeronly01-onpolicy-nokl-lr2e-6-t1-n8
Updated
MilaWang/grpo-fullparam-qwen3-4b-base-answeronly01-onpolicy-nokl-lr2e-6-t1-n8
Updated
MilaWang/lirpg-lora-intrinsic-fullparam-qwen2-5-math-7b-4000-olympiads-spk-a-rin05-rex10-lrin5e-6-rank16
Updated
MilaWang/lirpg-lora-intrinsic-fullparam-qwen2-5-math-7b-4000-40k-spk-h-rin05-rex10-lrin1e-5-rank16-handro
Updated
MilaWang/lirpg-lora-intrinsic-fullparam-qwen2-5-math-7b-4000-40k-spk-a-rin05-rex10-lrin5e-6-rank16-handro
Updated
MilaWang/lirpg-lora-intrinsic-fullparam-qwen2-5-math-7b-4000-40k-spk-a-rin05-rex10-lrin1e-5-rank16-handro
Updated
MilaWang/lirpg-lora-intrinsic-fullparam-qwen2-5-math-7b-4000-40k-spk-a-rin01-rex10-lrin1e-5-rank16-handro
Updated
MilaWang/lirpg-fullparam-olmo-3-7b-instruct-sciknoweval-biology-lr5e-6-rin05-rex10-lrin2e-5-rank16-zeroin
Updated
MilaWang/grpo-fullparam-qwen2-5-math-7b-4000-40k-spk-a01-onpolicy-nokl-lr2e-6
Updated
MilaWang/lirpg-lora-intrinsic-fullparam-qwen2-5-math-7b-4000-math-spk-a-rin05-rex10-lrin5e-6-rank16-handr
Updated
datasets 213
MilaWang/amc-test-23
Viewer • Updated • 40 • 24
MilaWang/math500-test
Viewer • Updated • 197 • 18
MilaWang/math500-validation
Viewer • Updated • 300 • 11
MilaWang/amc-validation-22
Viewer • Updated • 43 • 13
MilaWang/aime-test-24
Viewer • Updated • 30 • 15
MilaWang/amc-validation-2223
Viewer • Updated • 83 • 47
MilaWang/aime-validation-2223
Viewer • Updated • 60 • 24
MilaWang/qa_validation_qwen
Viewer • Updated • 700 • 72
MilaWang/qa_test_qwen
Viewer • Updated • 4.26k • 57
MilaWang/qa-dataset-qwen
Viewer • Updated • 14.2k • 21