Angles Don't Lie: Unlocking Training-Efficient RL Through the Model's Own Signals
Paper
•
2506.02281
•
Published
•
3
AI & ML interests
Apply state of the art deep learning natural language processing methods to dharmic texts. Develop these where necessary. Dedicate the merit to all sentient beings.
Recent Activity
View all activity
kurtkeutzerÂ
authored
a
paper
about 1 month ago
snehrdichÂ
updated
a
model
about 2 months ago
snehrdichÂ
published
a
model
about 2 months ago
kurtkeutzerÂ
authored
a
paper
3 months ago
kurtkeutzerÂ
authored
2
papers
4 months ago
kurtkeutzerÂ
authored
a
paper
5 months ago
snehrdichÂ
updated
a
dataset
7 months ago
snehrdichÂ
updated
2
datasets
8 months ago
snehrdichÂ
updated
a
model
8 months ago
snehrdichÂ
updated
3
datasets
8 months ago
snehrdichÂ
updated
5
models
8 months ago
buddhist-nlp/buddhist-sentence-similarity
Feature Extraction
•
0.5B
•
Updated
•
373
•
2
buddhist-nlp/gemma-2-mitra-it-int8
Updated
buddhist-nlp/gemma-2-mitra-it-8int
Text Generation
•
9B
•
Updated
•
13
buddhist-nlp/gemma-2-mitra-it
Text Generation
•
9B
•
Updated
•
165
•
6
buddhist-nlp/gemma2-mitra-base
Text Generation
•
9B
•
Updated
•
1.11k
•
4
sumanthdÂ
authored
a
paper
9 months ago