Gaotang Li

gaotang

·

https://gaotangli.github.io/

GaotangLi

AI & ML interests

None yet

Recent Activity

upvoted a paper 11 days ago

Learning from Teacher Continuations at Student States

upvoted a paper 11 days ago

Selecting Diverse SFT Traces Improves Post-RL Generalization

upvoted a paper 30 days ago

Scaling Automatic Research Agents via World Models

View all activity

Organizations

None yet

gaotang 's datasets 40

gaotang/loopmoe-fineweb-edu-100bt-mcore

Viewer • Updated Sep 1 • 65 • 85

gaotang/knowledge_memorization_openbookqa

Updated May 28 • 7

gaotang/mix_magpie_evol_instruct_140k

Viewer • Updated May 28 • 140k • 10

gaotang/coder_sft

Viewer • Updated May 28 • 75.5k • 8

gaotang/low_resource_language

Updated May 28 • 18

gaotang/figlet_font

Viewer • Updated Sep 8, 2025 • 45k • 59

gaotang/figlet_font_train

Viewer • Updated Sep 8, 2025 • 5 • 15

gaotang/huatuo_medical_sft_processed

Viewer • Updated Sep 7, 2025 • 19.7k • 11

gaotang/medical_sft_processed

Viewer • Updated Sep 6, 2025 • 23.5k • 37

gaotang/ParaConflict

Viewer • Updated Aug 31, 2025 • 2.15k • 164

gaotang/numina-cot-subset-val

Viewer • Updated Aug 28, 2025 • 128 • 8

gaotang/numina-cot-subset-67k

Viewer • Updated Aug 28, 2025 • 67.6k • 28

gaotang/ParaConfilct

Viewer • Updated Jul 17, 2025 • 2.15k • 127

gaotang/RM-R1-Reasoning-RLVR

Viewer • Updated May 20, 2025 • 73k • 22 • 1

gaotang/RM-R1-Entire-RLVR-Train

Viewer • Updated May 20, 2025 • 73k • 28 • 2

gaotang/RM-R1-after-Distill-RLVR

Viewer • Updated May 20, 2025 • 64.2k • 29 • 1

gaotang/RM-R1-Distill-SFT

Viewer • Updated May 20, 2025 • 8.75k • 72 • 2

gaotang/filtered_sky_code_8k_math_10k_rubric_evidence_classify_weight_rest_0417

Viewer • Updated Apr 17, 2025 • 64.2k • 13

gaotang/filtered_sky_code_8k_math_10k_rubric_evidence_classify_weight

Viewer • Updated Apr 17, 2025 • 73k • 20

gaotang/filtered_sky_code_8k_math_10k_rubric_reasoning

Viewer • Updated Apr 14, 2025 • 73k • 21

gaotang/filtered_sky_code_8k_math_10k_rubric_sft

Viewer • Updated Apr 11, 2025 • 73k • 14

gaotang/filtered_sky_code_8k_math_10k_rubric_evidence_classify

Viewer • Updated Apr 11, 2025 • 73k • 30

gaotang/filtered_sky_code_5k_math_10k_rubric_evidence_classify

Viewer • Updated Apr 11, 2025 • 70k • 16

gaotang/filtered_sky_code_1_5k_small_model

Viewer • Updated Apr 9, 2025 • 55.7k • 4

gaotang/Olmo2_preference_dataset

Viewer • Updated Apr 9, 2025 • 378k • 22

gaotang/final_filtered_helpfulsteer

Viewer • Updated Apr 8, 2025 • 7k • 6

gaotang/sky_v02_filtered_2_5kcode_18kmath_evidence_evaluation_justify_rubric

Viewer • Updated Apr 7, 2025 • 75.4k • 18

gaotang/sky_v02_filtered_2_5kcode_18kmath_evidence_rubric

Viewer • Updated Apr 7, 2025 • 75.4k • 11

gaotang/filtered_orm_guideline

Viewer • Updated Apr 3, 2025 • 55.7k • 35

gaotang/entire_orm_guideline

Viewer • Updated Apr 3, 2025 • 76k • 13