Accelerating Nash Learning from Human Feedback via Mirror Prox
Paper
•
2505.19731
•
Published
•
6
•
2
Daniil Tiapkin
dtiapkin
AI & ML interests
Reinforcement learning enjoyer
Recent Activity
upvoted
a
paper
22 days ago
T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground
upvoted
a
paper
2 months ago
GAS: Improving Discretization of Diffusion ODEs via Generalized
Adversarial Solver
upvoted
an
article
6 months ago
SmolLM3: smol, multilingual, long-context reasoner
Organizations
None yet
commented
a
paper
7 months ago
commented
a
paper
11 months ago