RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback Paper • 2312.00849 • Published Dec 1, 2023 • 12
Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based Perspective Paper • 2502.17262 • Published Feb 24 • 20
MAGA: MAssive Genre-Audience Reformulation to Pretraining Corpus Expansion Paper • 2502.04235 • Published Feb 6 • 22