Skip to content
conftrace_

reward feedback learning

3 papers

Explore in graph

Also known as

REFL

Co-occurring keywords · papers mentioning both

reward model (2) negative embedding learning (1) human preference learning (1) negative embedding (1) asynchronous policy conflict (1) cross-model transfer (1) reward guidance (1) clip text encoder (1) text-to-image evaluation (1) visual autoregressive model (1)

Papers

VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation CVPR 2026 ReNeg: Learning Negative Embedding with Reward Guidance CVPR 2025 ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation NeurIPS 2023