Hacker News new | ask | show | jobs
user: timshel1
created: 2022-04-03
karma: 5

ml engineer and research scientist at groundlight.ai

submissions:

0 points | 0 comments
Reducing VRAM Footprint in PPO and GRPO Using Selective Log-Softmax
1 points | 0 comments
An Extension to Badge Active Learning for Variable-Sized Batches
1 points | 0 comments
Direct Preference Optimization Explained In-Depth
1 points | 0 comments