On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification
Paper
•
2508.05629
•
Published
•
180
•
21
Vadim Kataev
vkataev
AI & ML interests
LLMs, all types of ASR models, methods to reduce model sizes, methods to improve generalization, methods to increase model capacity
Recent Activity
upvoted
an
article
24 days ago
We Got Claude to Fine-Tune an Open Source LLM
upvoted
a
paper
about 1 month ago
From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence
liked
a Space
2 months ago
HuggingFaceTB/smol-training-playbook
Organizations
commented
a
paper
5 months ago
commented
a
paper
6 months ago
commented
a
paper
8 months ago