conftrace_

reward model training

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

reward model (2) alignment framework (1) hybrid supervision (1) token-level policy (1) preference model (1) sequence-level optimization (1) model confidence (1) text-guided image editing (1) two-stage training (1) inference-time optimization (1)

Papers

Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing CVPR 2026 AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence ICML 2025 HAF-RM: A Hybrid Alignment Framework for Reward Model Training ACL 2025 Sing it, Narrate it: Quality Musical Lyrics Translation EMNLP 2024