Leng Sicong's picture

Leng Sicong PRO

Sicong

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning

updated a model 18 days ago

Sicong/Qwen2-VL-2B-InstructAlign-SFT

updated a model 18 days ago

Sicong/Qwen2-VL-2B-SFT

View all activity

Organizations

Papers 3

arxiv:2501.13106

arxiv:2406.07476

arxiv:2311.16922

models 2

Sicong/Qwen2-VL-2B-InstructAlign-SFT

Image-Text-to-Text • 2B • Updated 18 days ago • 4

Sicong/Qwen2-VL-2B-SFT

Image-Text-to-Text • 2B • Updated 18 days ago • 3

datasets 11

Sicong/caption_rl

Viewer • Updated Jun 4 • 3.93k • 5

Sicong/GRPO_val_benchmark

Viewer • Updated Apr 3 • 846 • 4

Sicong/RL_toy_math_5_sft

Viewer • Updated Mar 10 • 5.78k • 14

Sicong/RL_toy_math_7

Viewer • Updated Mar 7 • 22.5k • 20

Sicong/RL_toy_math_6

Viewer • Updated Mar 7 • 12.3k • 21

Sicong/EasyR1

Viewer • Updated Mar 5 • 20 • 42

Sicong/RL_toy_math_5

Viewer • Updated Mar 5 • 7.23k • 18

Sicong/RL_toy_math_4

Viewer • Updated Mar 4 • 7.23k • 12

Sicong/RL_toy_math_3

Viewer • Updated Mar 4 • 7.29k • 17

Sicong/RL_toy_math_2

Viewer • Updated Mar 4 • 7.36k • 9

View 11 datasets