Mohit Parmar

mohit-essential's activity

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

upvoted a paper 2 months ago

Essential-Web v1.0: 24T tokens of organized web data

Paper • 2506.14111 • Published Jun 17 • 43

upvoted 2 papers 4 months ago

Practical Efficiency of Muon for Pretraining

Paper • 2505.02222 • Published May 4 • 39

Rethinking Reflection in Pre-Training

Paper • 2504.04022 • Published Apr 5 • 80