Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts Paper • 2608.20061 • Published Aug 20 • 47
Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling Paper • 2606.02578 • Published Jun 1 • 5