This work proposes Step-Aware Annealing (SAA), a plug-and-play reward sharpening mechanism that progressively increases reward curvature during training, amplifying subtle quality differences among high-scoring samples while preserving stability in early learning.
This work proposes Step-Aware Annealing (SAA), a plug-and-play reward sharpening mechanism that progressively increases reward curvature during training, amplifying subtle quality differences among high-scoring samples while preserving stability in early learning.
Yunhao Wang, Bing-Hong Wu, Zhenyu Huang et al.· 0 citations
RewardVerse, a rubric-based video reward framework that introduces a dynamic rubric as an intermediate representation between the evaluation query and the scorer, mitigates scalar drift, and provides a robust and interpretable reward signal for RL in video generation.
Zhen-Chen Tang, Yang Li, Songlin Yang et al.· 1 citation
Gradient-Aligned Reward (GAR), which operates in the policy's own gradient space: truncated backpropagation through the output projection layer extracts a compact gradient vector for each rollout, and cosine similarity with an expert-anchor gradient yields a dense, reasoning-aware reward with less than 9% wall-clock ov...
Le-Qi Zheng, Jin-Bo Su, Fang Niu et al.· 2 citations
DATPO (Difficulty-Adaptive Sentence-entropy-guided Tree-structured Policy Optimization) integrates difficulty-adaptive tree search with a sibling-diversity advantage term, explicitly promoting semantic diversity to expand reasoning coverage during training.
Young Kyu Yu, Sanghwan Jang, Hwanjo Yu· 2 citations
Two key components are introduced: Dual-Relative Policy Optimization (DRPO), a post-training policy optimization method for robust and risk-aware advantage estimation; and Long-term Reward Predictor (LRP), which estimates long-term outcomes by modeling population heterogeneity with disentangled representation learning...
Wei Zhang, Hong-Ji Li, Song Sun et al.· 0 citations
HISPO is introduced, a segment-level policy-optimization method that constructs rollout-time entropy-derived contiguous segments, assigns soft entropy-based saliency weights, and applies clipped importance-sampling correction at the segment granularity, suggesting that segment-level correction is a promising granularit...
Quoc-Vinh Lai-Dang, Hyo-Sang Shin· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
