FAN: Fourier Analysis Networks
Paper
•
2410.02675
•
Published
•
28
interesting architecture
-
-
Tensor Product Attention Is All You Need
Paper • 2501.06425 • Published • 89 -
Scalable-Softmax Is Superior for Attention
Paper • 2501.19399 • Published • 22 -
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
Paper • 2502.09509 • Published • 8 -
YOLOv12: Attention-Centric Real-Time Object Detectors
Paper • 2502.12524 • Published • 12 -
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper • 2502.14786 • Published • 146 -
Large Language Diffusion Models
Paper • 2502.09992 • Published • 122 -
ObjectMover: Generative Object Movement with Video Prior
Paper • 2503.08037 • Published • 4 -
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Paper • 2503.09573 • Published • 73 -
Transformers without Normalization
Paper • 2503.10622 • Published • 168 -
RWKV-7 "Goose" with Expressive Dynamic State Evolution
Paper • 2503.14456 • Published • 153 -
Scaling Vision Pre-Training to 4K Resolution
Paper • 2503.19903 • Published • 42 -
Multi-Token Attention
Paper • 2504.00927 • Published • 55 -
TransMamba: Flexibly Switching between Transformer and Mamba
Paper • 2503.24067 • Published • 21 -
Softpick: No Attention Sink, No Massive Activations with Rectified Softmax
Paper • 2504.20966 • Published • 32 -
MMaDA: Multimodal Large Diffusion Language Models
Paper • 2505.15809 • Published • 95 -
MiniCPM4: Ultra-Efficient LLMs on End Devices
Paper • 2506.07900 • Published • 90 -
Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation
Paper • 2506.19852 • Published • 41 -
Representing Speech Through Autoregressive Prediction of Cochlear Tokens
Paper • 2508.11598 • Published • 16