3 39

Yang Ouyang

OriDragon2000

https://oyy2000.github.io/

AI & ML interests

Safety and Efficiency

Recent Activity

liked a dataset 9 days ago

hotpotqa/hotpot_qa

upvoted a paper 2 months ago

The Art of Efficient Reasoning: Data, Reward, and Optimization

liked a model 4 months ago

google/gemma-2-2b-it

View all activity

Organizations

None yet

liked a dataset 9 days ago

hotpotqa/hotpot_qa

Viewer • Updated Aug 11, 2025 • 203k • 93.9k • 291

upvoted a paper 2 months ago

The Art of Efficient Reasoning: Data, Reward, and Optimization

Paper • 2602.20945 • Published Feb 24 • 7

liked a model 4 months ago

google/gemma-2-2b-it

Text Generation • 3B • Updated Aug 27, 2024 • 375k • • 1.35k

liked a dataset 5 months ago

EleutherAI/hendrycks_math

Viewer • Updated Jan 12, 2025 • 12.5k • 108k • 100

liked a model 6 months ago

kevinpro/R-PRM-7B-DPO

Text Generation • 8B • Updated Mar 28, 2025 • 39 • 3

updated a dataset 9 months ago

OriDragon2000/wanda_weightonly

Viewer • Updated Aug 27, 2025 • 4.03k • 364

published a dataset 9 months ago

OriDragon2000/wanda_weightonly

Viewer • Updated Aug 27, 2025 • 4.03k • 364

published a model 9 months ago

OriDragon2000/Wanda_Score_Llama2-7b

Updated Aug 27, 2025

liked 2 models 11 months ago

moiduy04/Llama-3-6.6B-R-Pruned

Text Generation • Updated Feb 28, 2025 • 1

moiduy04/Llama-3-6.6B-LLM-Pruned

Text Generation • Updated Feb 28, 2025 • 1

upvoted a paper 11 months ago

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense

Paper • 2501.02629 • Published Jan 5, 2025 • 1

updated 2 models about 1 year ago

OriDragon2000/mistral_instruct_v3_Layer_AdvPatched

7B • Updated Feb 21, 2025 • 10

OriDragon2000/mistral_instruct_v3_attacked

7B • Updated Feb 21, 2025 • 3 • 1

authored a paper about 1 year ago