Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
Filtering here covers the 2,000 most recent papers, as much as one page can hold in memory. See the full index of 22,663 papers.
1 Jun 2026
We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture.
Xiaobin Hu, Xianfang Zeng, DaCheng Tao et al. · 19 May 2026
A large-scale UHR image-text dataset and evaluation benchmark are introduced to advance ultra-high-resolution text-to-image generation capabilities.
6 Oct 2026
Flow and diffusion models suffer from slow inference due to computationally expensive numerical integration. Distillation provides a promising way for a student model to learn from a teacher's dynamics, enabling one-step or few-step generation.
1 Oct 2026
Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated target and student scores, so it must keep an auxiliary diffusion model fitted to the student's evolving distribution at extra memory and computation cost.