Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts Paper • 2608.20061 • Published 5 days ago • 38
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling Paper • 2606.02578 • Published Jun 1 • 6