MEND: RL For Flow Models via Proximal Velocity Matching
Paper • 2610.05954 • Published • 3
University of Texas at Austin
university
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
MEND: RL For Flow Models via Proximal Velocity Matching
Allspark: Weak to Strong Transfer via Alternating Chain of Thought
shreshthsaini
submitted a
paper to Daily Papers 16 days ago
kz919
submitted a
paper to Daily Papers 24 days ago
lytang
authored a
paper about 2 months ago
cranial-xix
submitted a
paper to Daily Papers 2 months ago
FOGmiaow
submitted a
paper to Daily Papers 3 months ago
pbansal
submitted a
paper to Daily Papers 3 months ago
XCLiu
authored a
paper 4 months ago
reshmijspatel
updated 2
datasets 4 months ago
reshmijspatel
published a
dataset 4 months ago
reshmijspatel
updated a
dataset 4 months ago
ashwinnv
submitted a
paper to Daily Papers 4 months ago
JamesSand
submitted a
paper to Daily Papers 4 months ago
reshmijspatel
published 2
datasets 5 months ago
acnagle
submitted a
paper to Daily Papers 7 months ago
atutej
submitted a
paper to Daily Papers 9 months ago
Post
1,659
Are you familiar with reverse residual connections or looping in language models?
Excited to share my Looped-GPT blog post and codebase 🚀
https://github.com/sanyalsunny111/Looped-GPT
TL;DR: looping during pre-training improves generalization.
Plot shows GPT2 LMs pre-trained with 15.73B OWT tokens
P.S. This is my first post here — I have ~4 followers and zero expectations for reach 😄
Excited to share my Looped-GPT blog post and codebase 🚀
https://github.com/sanyalsunny111/Looped-GPT
TL;DR: looping during pre-training improves generalization.
Plot shows GPT2 LMs pre-trained with 15.73B OWT tokens
P.S. This is my first post here — I have ~4 followers and zero expectations for reach 😄
- 3 replies
abao
authored a
paper about 1 year ago
lytang
authored a
paper over 1 year ago