Yihe Deng's picture

Yihe Deng PRO

ydeng9

·

https://yihe-deng.notion.site/Yihe-Deng-167ab2d2c1fb80b3a76dfb120f716c84

Yihe__Deng

AI & ML interests

LLM post-training

Organizations

ydeng9 's datasets 15

ydeng9/aime2024-val

Viewer • Updated Aug 26 • 960 • 30

ydeng9/s1-rd

Viewer • Updated Jul 16 • 2.3k • 21

ydeng9/smith_rd_editonly

Viewer • Updated Jul 15 • 82.8k • 17

ydeng9/rd_looped

Viewer • Updated Jul 7 • 1.76k • 18

ydeng9/rd_self

Viewer • Updated Jul 7 • 1.32k • 13

ydeng9/rd_direct

Viewer • Updated Jul 7 • 789 • 10

ydeng9/rd_loop

Viewer • Updated Jul 7 • 6 • 11

ydeng9/swe-smith-rl-distill

Viewer • Updated May 22 • 7.81k • 8

ydeng9/OpenVLThinker-grpo-hard

Viewer • Updated May 6 • 6.25k • 389 • 1

ydeng9/OpenVLThinker-sft-iter3

Viewer • Updated May 5 • 3.28k • 35

ydeng9/OpenVLThinker-grpo-medium

Viewer • Updated Apr 24 • 3.3k • 52

ydeng9/OpenVLThinker_sft_iter2

Viewer • Updated Mar 23 • 5.54k • 16

ydeng9/captioned-data-subsetv1

Viewer • Updated Mar 19 • 59.3k • 14

ydeng9/llavaone_grpo_v2

Viewer • Updated Mar 15 • 3.11k • 32 • 1

ydeng9/llavaone_grpo_v1

Viewer • Updated Mar 6 • 5.87k • 11 • 1