user: ankeshanand
250 karma | created 12 years ago
recent submissions
1 pts|11 months ago|discuss
Gemini 1.5 Flash-8B
(simonwillison.net)
2 pts|1 year ago|discuss
1 year ago|discuss
2 years ago|discuss
2 years ago|discuss
3 years ago|discuss
4 years ago|discuss
4 years ago|discuss
4 years ago|discuss
Reinforcement Learning as a fine-tuning paradigm
(ankeshanand.com)
22 pts|4 years ago|7 comments
4 years ago|discuss
5 years ago|discuss
5 years ago|discuss
6 years ago|discuss
6 years ago|discuss
Contrastive Self-Supervised Learning
(ankeshanand.com)
97 pts|6 years ago|13 comments
6 years ago|discuss
6 years ago|discuss
6 years ago|discuss
6 years ago|discuss