🔄 In a Training Loop
David Andrews
Broyojo
AI & ML interests
Tranformer models, diffusion models, reinforcement learning, AI accelerators, computer architecture, VSLI
Recent Activity
liked a dataset about 24 hours ago
zwhe99/DeepMath-103K liked a model 8 days ago
IFM/K2-Horizon-MoVA-36B-A4B upvoted a paper 8 days ago
Block Sparse Attention with Log-Linear ComplexityOrganizations
Problem Statement Availability
3
#1 opened over 1 year ago
by Broyojo
How to prevent degenerate output?
2
#2 opened almost 2 years ago
by 
nbroad