FAN: Fourier Analysis Networks
Paper • 2410.02675 • Published • 29
interesting architecture
-
-
Tensor Product Attention Is All You Need
Paper • 2501.06425 • Published • 90 -
Scalable-Softmax Is Superior for Attention
Paper • 2501.19399 • Published • 25 -
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
Paper • 2502.09509 • Published • 9 -
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 • 164 -
Large Language Diffusion Models
Paper • 2502.09992 • Published • 127 -
ObjectMover: Generative Object Movement with Video Prior
Paper • 2503.08037 • Published • 5 -
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Paper • 2503.09573 • Published • 77 -
Transformers without Normalization
Paper • 2503.10622 • Published • 172 -
RWKV-7 "Goose" with Expressive Dynamic State Evolution
Paper • 2503.14456 • Published • 154 -
Scaling Vision Pre-Training to 4K Resolution
Paper • 2503.19903 • Published • 41 -
Multi-Token Attention
Paper • 2504.00927 • Published • 56 -
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 • 31 -
MMaDA: Multimodal Large Diffusion Language Models
Paper • 2505.15809 • Published • 98 -
MiniCPM4: Ultra-Efficient LLMs on End Devices
Paper • 2506.07900 • Published • 96 -
Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation
Paper • 2506.19852 • Published • 42 -
Representing Speech Through Autoregressive Prediction of Cochlear Tokens
Paper • 2508.11598 • Published • 17 -
DINOv3
Paper • 2508.10104 • Published • 303 -
2D Gaussian Splatting with Semantic Alignment for Image Inpainting
Paper • 2509.01964 • Published • 7 -
Sequential Diffusion Language Models
Paper • 2509.24007 • Published • 47 -
BitNet Distillation
Paper • 2510.13998 • Published • 59 -
AnyUp: Universal Feature Upsampling
Paper • 2510.12764 • Published • 12 -
Latent Diffusion Model without Variational Autoencoder
Paper • 2510.15301 • Published • 50 -
Stronger Normalization-Free Transformers
Paper • 2512.10938 • Published • 22 -
Bolmo: Byteifying the Next Generation of Language Models
Paper • 2512.15586 • Published • 17 -
ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation
Paper • 2601.03955 • Published • 3 -
AnyDepth: Depth Estimation Made Easy
Paper • 2601.02760 • Published • 10 -
ViTNT-FIQA: Training-Free Face Image Quality Assessment with Vision Transformers
Paper • 2601.05741 • Published • 2 -
Extending the Context of Pretrained LLMs by Dropping Their Positional Embeddings
Paper • 2512.12167 • Published • 5 -
Implicit Neural Representation Facilitates Unified Universal Vision Encoding
Paper • 2601.14256 • Published • 7 -
Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding
Paper • 2506.16035 • Published • 89 -
Scaling Embeddings Outperforms Scaling Experts in Language Models
Paper • 2601.21204 • Published • 102 -
Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection
Paper • 2602.03216 • Published • 13 -
dLLM: Simple Diffusion Language Modeling
Paper • 2602.22661 • Published • 152 -
Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model
Paper • 2603.21986 • Published • 121