Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models Paper • 2607.04461 • Published Jul 5 • 10
When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation Paper • 2602.16763 • Published Jun 29
CinePile: A Long Video Question Answering Dataset and Benchmark Paper • 2405.08813 • Published May 14, 2024 • 1