Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective Paper • 2505.15045 • Published May 21 • 55
PHYSICS: Benchmarking Foundation Models on University-Level Physics Problem Solving Paper • 2503.21821 • Published Mar 26 • 18
MMVU: Measuring Expert-Level Multi-Discipline Video Understanding Paper • 2501.12380 • Published Jan 21 • 86