MaPO

university

https://mapo-t2i.github.io/

mapo-t2i

AI & ML interests

Diffusion models, alignment

Recent Activity

JW17 authored a paper about 2 months ago

AlphaPO -- Reward shape matters for LLM alignment

JW17 authored a paper about 2 months ago

Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning

JW17 authored a paper 3 months ago

When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research

View all activity

mapo-t2i 's models 7

mapo-t2i/SDXL-Pick-a-pic-v2-on-policy-beta1.0

Updated Oct 4, 2024

mapo-t2i/mapo-pick-safety

Text-to-Image • Updated Jun 12, 2024 • 3 • 2

mapo-t2i/mapo-pick-style-pixel-art

Text-to-Image • Updated Jun 11, 2024 • 3 • 1

mapo-t2i/mapo-pick-style-cartoon

Text-to-Image • Updated Jun 11, 2024 • 14 • 1

mapo-t2i/mapo-beta

Text-to-Image • Updated Jun 11, 2024 • 10 • 6

mapo-t2i/sdxl-orpo-large-beta_orpo-0.005-beta_inner-100-lr-1e-8-scaled-ema

Updated Apr 27, 2024 • 2

mapo-t2i/sdxl-orpo-large-beta_orpo-0.005-beta_inner-100-lr-1e-8-steps-scaled

Updated Apr 22, 2024 • 7