Ishaan SHARMA

sharma-ishaan's activity

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

upvoted a paper 20 days ago

Recovering Reliable Supervision via Critique-Guided On-Policy Distillation

Paper • 2610.20572 • Published 22 days ago • 27

updated a dataset 27 days ago

sharma-ishaan/math-image-depth-v2

Updated 27 days ago • 42

published a dataset 27 days ago

sharma-ishaan/math-image-depth-v2

Updated 27 days ago • 42

upvoted 2 papers 27 days ago

LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches

Paper • 2610.06647 • Published about 1 month ago • 36

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

Paper • 2609.38169 • Published Sep 29 • 37