Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
purbeshmitra
's Collections
Semantic Soft Bootstrapping
MOTIF paper
MOTIF paper
updated
8 days ago
MOTIF trained model and Vanilla GRPO trained model, compared in the paper.
Upvote
1
purbeshmitra/MOTIF
Text Generation
•
Updated
Jul 7
•
23
•
1
purbeshmitra/vanillaGRPO
Text Generation
•
Updated
Jul 7
•
11
MOTIF: Modular Thinking via Reinforcement Fine-tuning in LLMs
Paper
•
2507.02851
•
Published
Jul 3
Upvote
1
Share collection
View history
Collection guide
Browse collections