Aviral Kumar

aviralku's activity

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

published a model 6 days ago

aviralku/mr9b-noveltybonus-sft-8node-215

Updated 6 days ago

updated a model 6 days ago

aviralku/mr9b-noveltybonus-sft-8node-215

Updated 6 days ago

published a model 9 days ago

aviralku/mr9b-layeraudit-8node-215

Updated 9 days ago

updated a model 9 days ago

aviralku/mr9b-layeraudit-8node-215

Updated 9 days ago

liked a model 15 days ago

thinkingmachines/Inkling

Image-Text-to-Text • 952B • Updated 7 days ago • 39.1k • • 1.64k

updated a dataset 30 days ago

aviralku/swe-qa-episodes

Preview • Updated 30 days ago • 59

published a dataset 30 days ago

aviralku/swe-qa-episodes

Preview • Updated 30 days ago • 59

upvoted an article 4 months ago

view article

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

• 
• 
• +7

aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, nouamanetazi, lvwerra, sergiopaniego

•

Mar 10

• 173

liked a model 4 months ago

nvidia/Nemotron-Cascade-2-30B-A3B

Text Generation • 32B • Updated 20 days ago • 53.8k • 520

liked a dataset 5 months ago

microsoft/webgym_tasks

Viewer • Updated Feb 10 • 293k • 3.95k • 19

liked a model 5 months ago

CMU-AIRe/e3-1.7B

2B • Updated Jun 11, 2025 • 6 • 1

liked a Space 5 months ago

Running

Featured

81

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

📝

81

Who needs 1T parameters? Olympiad proofs with a 4B model

liked a model 6 months ago

lm-provers/QED-Nano

Text Generation • 4B • Updated Mar 23 • 879 • • 88

updated a Space 6 months ago

Running

Featured

81

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

📝

81

Who needs 1T parameters? Olympiad proofs with a 4B model

updated a model 6 months ago

lm-provers/QED-Nano

Text Generation • 4B • Updated Mar 23 • 879 • • 88

upvoted 2 collections 6 months ago

InT

Collection

7 items • Updated Feb 4 • 1

POPE

Collection

5 items • Updated Mar 2 • 2

published a model about 1 year ago

CMU-AIRe/e3-1.7B

2B • Updated Jun 11, 2025 • 6 • 1

upvoted a paper over 1 year ago

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

Paper • 2503.07572 • Published Mar 10, 2025 • 48

authored a paper over 1 year ago

Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models

Paper • 2310.10639 • Published Oct 16, 2023 • 3