Ryan Wang

ryanyxw's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 9 hours ago

EMO: Pretraining Mixture of Experts for Emergent Modularity

Paper • 2605.06663 • Published 2 days ago • 5

submitted a paper to Daily Papers about 9 hours ago

EMO: Pretraining Mixture of Experts for Emergent Modularity

Paper • 2605.06663 • Published 2 days ago • 5

upvoted a collection about 11 hours ago

EMO

Collection

8 items • Updated about 16 hours ago • 9

published a model about 11 hours ago

allenai/EMO

Text Generation • 14B • Updated about 17 hours ago • 10 • 3

upvoted an article about 16 hours ago

view article

Article

EMO: Pretraining mixture of experts for emergent modularity

• 

about 17 hours ago

•

17

updated a model about 17 hours ago

allenai/EMO

Text Generation • 14B • Updated about 17 hours ago • 10 • 3

updated 2 models 1 day ago

allenai/StdMoE_1b14b_1T_EmoAnnealed

Text Generation • 14B • Updated 1 day ago • 12 • 1

allenai/StdMoE_1b14b_1T_Preanneal

Text Generation • 14B • Updated 1 day ago • 14 • 1

New activity in allenai/StdMoE_1b14b_1T 1 day ago

Create README.md

#1 opened 1 day ago by

ryanyxw

New activity in allenai/StdMoE_1b14b_130B 1 day ago

Create README.md

#1 opened 1 day ago by

ryanyxw

New activity in allenai/StdMoE_1b4b_130B 1 day ago

Create README.md

#1 opened 1 day ago by

ryanyxw

New activity in allenai/Emo_1b14b_130B 1 day ago

Create README.md

#1 opened 1 day ago by

ryanyxw

New activity in allenai/Emo_1b14b_1T 1 day ago

Create README.md

#1 opened 1 day ago by

ryanyxw

New activity in allenai/Dense_1b_130B 1 day ago

Create README.md

#1 opened 1 day ago by

ryanyxw

authored 2 papers 12 months ago

Proving membership in LLM pretraining data via data watermarks

Paper • 2402.10892 • Published Feb 16, 2024 • 1

Teaching Models to Understand (but not Generate) High-risk Data

Paper • 2505.03052 • Published May 5, 2025 • 6

upvoted a paper 12 months ago

Teaching Models to Understand (but not Generate) High-risk Data

Paper • 2505.03052 • Published May 5, 2025 • 6

upvoted a paper about 1 year ago

Promote, Suppress, Iterate: How Language Models Answer One-to-Many Factual Queries

Paper • 2502.20475 • Published Feb 27, 2025 • 3

updated a model about 1 year ago

ryanyxw/1B_20B_perturbed_nogqa

Updated Feb 28, 2025

published a model about 1 year ago

ryanyxw/1B_20B_perturbed_nogqa

Updated Feb 28, 2025