-
Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
Paper • 2311.06243 • Published • 17 -
FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
Paper • 2311.05908 • Published • 11 -
PolyMaX: General Dense Prediction with Mask Transformer
Paper • 2311.05770 • Published • 6 -
SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
Paper • 2311.07575 • Published • 10
Collections
Discover the best community collections!
Collections including paper arxiv:2401.14404
-
FreeU: Free Lunch in Diffusion U-Net
Paper • 2309.11497 • Published • 63 -
Imagic: Text-Based Real Image Editing with Diffusion Models
Paper • 2210.09276 • Published -
On Architectural Compression of Text-to-Image Diffusion Models
Paper • 2305.15798 • Published • 3 -
Wuerstchen: Efficient Pretraining of Text-to-Image Models
Paper • 2306.00637 • Published • 11