GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper
âĒ
2601.05242
âĒ
Published
âĒ
203
âĒ
8
Alexander Radchenko
AlexRadch
AI & ML interests
I'm creating software engineering tips and tricks videos on my YouTube channel. If you are interested in everything related to .NET, check out ð my videos! Don't forget to comment ðŽ, like ð, and subscribe ð!
Recent Activity
commented on
a paper
14 days ago
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
liked
a model
10 months ago
openai/whisper-large-v3
liked
a Space
over 1 year ago
fffiloni/expression-editor
Organizations
commented
a
paper
14 days ago
liked
a
model
10 months ago
liked
a
Space
over 1 year ago
liked
a
model
over 1 year ago
liked
8
Spaces
over 1 year ago
Oryx
ðŽ
103
Generate detailed descriptions from images and videos
Tile Upscaler
ð
961
Enhance and upscale images with advanced controls
Voice Clone
ðĢ
2.57k
Clone a voice to say custom text
FLUX.1 RealismLora
ð
1.33k
FLUX.1 RealismLora
PuLID-FLUX
ðĪ
2.07k
Generate images from text prompts and ID images
Flux.1-dev Upscaler
ð
1.64k
Upscale low-resolution images to high resolution
Live Portrait
ðĪŠ
3.69k
Apply the motion of a video on a portrait
Whisper Turbo
ðĪŊ
999
Transcribe audio or YouTube videos into text
liked
2
models
about 2 years ago
