Jingwen Gu

JingwenGu

5

·

JingwenGu

AI & ML interests

None yet

Recent Activity

upvoted a paper about 1 hour ago

Learning from Teacher Continuations at Student States

upvoted a paper about 1 hour ago

Selecting Diverse SFT Traces Improves Post-RL Generalization

updated a model 9 days ago

JingwenGu/qwen3-1.7b-rloo-sft-all

View all activity

Organizations

None yet

models 5

JingwenGu/qwen3-1.7b-rloo-sft-all

2B • Updated 9 days ago • 13

JingwenGu/qwen3-1.7b-grpo-sft-all

2B • Updated 12 days ago • 14

JingwenGu/qwen3-1.7b-maxrl-sft-all

2B • Updated 12 days ago • 16

JingwenGu/qwen3-4b-maxrl-sft-all

4B • Updated 17 days ago • 21

JingwenGu/qwen3-4b-maxrl-sft-all-shuffled

4B • Updated 21 days ago • 20

datasets 6

JingwenGu/maze-17x17-maxrl-rollouts

Viewer • Updated 27 days ago • 23.6M • 167

JingwenGu/knk-rollouts

Preview • Updated 27 days ago • 63

JingwenGu/imagenet-maxrl-online-rollouts

Updated 27 days ago • 24

JingwenGu/Self_correction_sft_1_300-600

Viewer • Updated May 14, 2025 • 900 • 7

JingwenGu/Self_correction_sft_2

Viewer • Updated May 9, 2025 • 12k • 4

JingwenGu/Self_correction_sft_1

Viewer • Updated May 9, 2025 • 1.2k • 3 • 1