TCNCA: Temporal Convolution Network with Chunked Attention for Scalable Sequence Processing
Paper
•
2312.05605
•
Published
•
2
architecture
-
-
VMamba: Visual State Space Model
Paper • 2401.10166 • Published • 38 -
Rethinking Patch Dependence for Masked Autoencoders
Paper • 2401.14391 • Published • 23 -
Deconstructing Denoising Diffusion Models for Self-Supervised Learning
Paper • 2401.14404 • Published • 17 -
LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation
Paper • 2403.12019 • Published • 9 -
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Paper • 2404.02905 • Published • 65 -
On the Scalability of Diffusion-based Text-to-Image Generation
Paper • 2404.02883 • Published • 17 -
ViTAR: Vision Transformer with Any Resolution
Paper • 2403.18361 • Published • 52 -
When Do We Not Need Larger Vision Models?
Paper • 2403.13043 • Published • 25 -
Phased Consistency Model
Paper • 2405.18407 • Published • 46 -
An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
Paper • 2406.09415 • Published • 50 -
MambaVision: A Hybrid Mamba-Transformer Vision Backbone
Paper • 2407.08083 • Published • 28 -
FAN: Fourier Analysis Networks
Paper • 2410.02675 • Published • 25 -
Differential Transformer
Paper • 2410.05258 • Published • 169