violetxi/single-turn-eval-meta_feedback_qwen3-4b_step2_gpt-5-nano_gepa-n32
Viewer • Updated • 1.01k • 22
Violet Xiang PRO
violetxi
AI & ML interests
None yet
Recent Activity
updated a model about 3 hours ago
violetxi/teacher_grpo_forward_kl-1_16k published a model about 3 hours ago
violetxi/teacher_grpo_forward_kl-1_16k updated a model about 3 hours ago
violetxi/teacher_grpo_kl-1_16kOrganizations
violetxi/single-turn-eval-stage1_proof_pr_delta_variants-n32
Viewer • Updated • 1.01k • 18
violetxi/single-turn-eval-meta_feedback_qwen3-4b_step2_gpt-5.4_gepa-n32
Viewer • Updated • 1.01k • 17
violetxi/single-turn-eval-Qwen3-4B-Instruct-2507-n32
Viewer • Updated • 1.01k • 24
violetxi/stage1_proof-qwen3-4b-grpo-imoproofbench-summary-reasoning-graded
Viewer • Updated • 960 • 23
violetxi/stage1_proof-qwen3-4b-dense-process-rubric-imoproofbench-summary-graded
Viewer • Updated • 960 • 23
violetxi/stage1_proof-qwen3-4b-dense-process-imoproofbench-summary-reasoning-graded
Viewer • Updated • 960 • 23
violetxi/gemini_step_judge_variants
Viewer • Updated • 50 • 21
violetxi/stage1_proof-qwen3-4b-grpo-proofbench-summary-graded
Viewer • Updated • 2.32k • 34
violetxi/stage1_proof-qwen3-4b-dense-process-proofbench-summary-graded
Viewer • Updated • 2.32k • 28
violetxi/stage1_proof-qwen3-4b-dense-process-imoproofbench-summary-graded
Viewer • Updated • 960 • 28
violetxi/qwen3-4b-instruct-proofbench-summary-graded
Viewer • Updated • 2.32k • 17
violetxi/qwen3-4b-instruct-imoproofbench-summary-graded
Viewer • Updated • 960 • 19
violetxi/stage1_proof-qwen3-4b-sft-proofbench-summary-graded
Viewer • Updated • 2.32k • 29
violetxi/stage1_proof-qwen3-4b-sft-imoproofbench-summary-graded
Viewer • Updated • 960 • 32
violetxi/stage1_proof-qwen3-4b-self-distill-proofbench-summary-graded
Viewer • Updated • 2.32k • 31
violetxi/stage1_proof-qwen3-4b-self-distill-imoproofbench-summary-graded
Viewer • Updated • 960 • 29
violetxi/stage1_proof-qwen3-4b-grpo-imoproofbench-summary-graded
Viewer • Updated • 960 • 87
violetxi/stage1_proof-qwen3-4b-sft-imoproofbench-summary-graded-gemini3_pro
Viewer • Updated • 960 • 24
violetxi/FineProofs-Stage-1
Viewer • Updated • 650 • 23
violetxi/question_bank
Viewer • Updated • 60 • 54
violetxi/stage2-qwen3-4b-sft-proofbench-summary-graded
Viewer • Updated • 2.32k • 9 • 1
violetxi/stage2-qwen3-4b-self-distill-proofbench-summary-graded
Viewer • Updated • 2.32k • 11
violetxi/stage2-qwen3-4b-grpo-proofbench-summary-graded
Viewer • Updated • 2.32k • 13
violetxi/stage2-qwen3-4b-dense-process-proofbench-summary-graded
Viewer • Updated • 2.32k • 6
violetxi/stage2-qwen3-4b-dense-outcome-proofbench-summary-graded
Viewer • Updated • 2.32k • 14
violetxi/stage2-qwen3-4b-sft-imoproofbench-summary-graded
Viewer • Updated • 960 • 8
violetxi/stage2-qwen3-4b-dense-outcome-imoproofbench-summary-graded
Viewer • Updated • 960 • 11
violetxi/stage2-qwen3-4b-self-distill-imoproofbench-summary-graded
Viewer • Updated • 960 • 9
violetxi/stage2-qwen3-4b-grpo-imoproofbench-summary-graded
Updated • 9