R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging
Paper • 2602.06763 • Published
ZeroLoss-Lab
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
Jasaxion
authored 3
papers 8 days ago
tanfei2007
authored 6
papers about 2 months ago
CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models
Paper • 2407.17467 • Published
SynthDoc: Bilingual Documents Synthesis for Visual Document Understanding
Paper • 2408.14764 • Published
Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model
Paper • 2404.10306 • Published • 1
Cultivating Helpful, Personalized, and Creative AI Tutors: A Framework for Pedagogical Alignment using Reinforcement Learning
Paper • 2507.20335 • Published
MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy
Paper • 2508.05592 • Published • 6
ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning
Paper • 2508.19996 • Published
Jasaxion
authored 2
papers about 2 months ago