Violet Xiang's picture

Violet Xiang PRO

violetxi

·

violetxi

AI & ML interests

None yet

Recent Activity

updated a model 1 day ago

violetxi/opd_medical_qwen3-4b_forward_kl_teacher_step240_kl-0.1_bs256_lr5e-6

published a model 1 day ago

violetxi/opd_medical_qwen3-4b_forward_kl_teacher_step240_kl-0.1_bs256_lr5e-6

updated a model 1 day ago

violetxi/medical_teacher_grpo_qwen3-4b-no-thinking_kl-0.1

View all activity

Organizations

violetxi 's datasets 151

violetxi/Qwen8b-NoThink-Judge-int-qwen8b-multi-ref

Viewer • Updated 8 days ago • 1.08k • 56

violetxi/judge_calibration_int_qwen8b

Viewer • Updated 8 days ago • 1.08k • 54

violetxi/sciKnowEval-OE

Viewer • Updated 13 days ago • 5.38k • 26

violetxi/clbench-exploitable-poker-wm-sft-opponent-dynamics-thinking

Viewer • Updated 13 days ago • 49 • 41

violetxi/clbench-exploitable-poker-wm-sft-opponent-dynamics

Viewer • Updated 17 days ago • 1.12k • 41

violetxi/clbench-exploitable-poker-wm_summar-gemini-flash-3-1-lite

Viewer • Updated 19 days ago • 2.74k • 95

violetxi/clbench-exploitable-poker-step3-state-action-wm-labels

Viewer • Updated 19 days ago • 1.12k • 44

violetxi/single-turn-eval-int_qwen3-4b_distill_teacher_reverse_kl_lr1e-7-n32

Viewer • Updated 22 days ago • 566 • 69

violetxi/single-turn-eval-self_distill_lr1e-7_int_step90-n32

Viewer • Updated 22 days ago • 566 • 67

violetxi/single-turn-eval-meta_feedback_qwen3-4b_step2_gpt-5-nano_gepa-n32

Viewer • Updated May 5 • 1.01k • 44

violetxi/single-turn-eval-stage1_proof_pr_delta_variants-n32

Viewer • Updated May 5 • 1.01k • 36

violetxi/single-turn-eval-meta_feedback_qwen3-4b_step2_gpt-5.4_gepa-n32

Viewer • Updated May 5 • 1.01k • 37

violetxi/single-turn-eval-Qwen3-4B-Instruct-2507-n32

Viewer • Updated May 5 • 1.01k • 57

violetxi/stage1_proof-qwen3-4b-grpo-imoproofbench-summary-reasoning-graded

Viewer • Updated Apr 30 • 960 • 132

violetxi/stage1_proof-qwen3-4b-dense-process-rubric-imoproofbench-summary-graded

Viewer • Updated Apr 30 • 960 • 19

violetxi/stage1_proof-qwen3-4b-dense-process-imoproofbench-summary-reasoning-graded

Viewer • Updated Apr 30 • 960 • 13

violetxi/gemini_step_judge_variants

Viewer • Updated Apr 28 • 50 • 33

violetxi/stage1_proof-qwen3-4b-grpo-proofbench-summary-graded

Viewer • Updated Apr 27 • 2.32k • 17

violetxi/stage1_proof-qwen3-4b-dense-process-proofbench-summary-graded

Viewer • Updated Apr 27 • 2.32k • 56

violetxi/stage1_proof-qwen3-4b-dense-process-imoproofbench-summary-graded

Viewer • Updated Apr 27 • 960 • 8

violetxi/qwen3-4b-instruct-proofbench-summary-graded

Viewer • Updated Apr 27 • 2.32k • 5

violetxi/qwen3-4b-instruct-imoproofbench-summary-graded

Viewer • Updated Apr 27 • 960 • 6

violetxi/stage1_proof-qwen3-4b-sft-proofbench-summary-graded

Viewer • Updated Apr 27 • 2.32k • 17

violetxi/stage1_proof-qwen3-4b-sft-imoproofbench-summary-graded

Viewer • Updated Apr 27 • 960 • 14

violetxi/stage1_proof-qwen3-4b-self-distill-proofbench-summary-graded

Viewer • Updated Apr 27 • 2.32k • 21

violetxi/stage1_proof-qwen3-4b-self-distill-imoproofbench-summary-graded

Viewer • Updated Apr 27 • 960 • 62

violetxi/stage1_proof-qwen3-4b-grpo-imoproofbench-summary-graded

Viewer • Updated Apr 27 • 960 • 67

violetxi/stage1_proof-qwen3-4b-sft-imoproofbench-summary-graded-gemini3_pro

Viewer • Updated Apr 27 • 960 • 11

violetxi/FineProofs-Stage-1

Viewer • Updated Apr 22 • 650 • 16

violetxi/question_bank

Viewer • Updated Apr 20 • 60 • 13