Collection by
Aug 28
Aug 28Collections
Discover the best community collections!
Collections including paper arxiv:2504.20966
Collection by
14 days ago
14 days ago-
FAN: Fourier Analysis Networks
Paper • 2410.02675 • Published • 28 -
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
Collection by
4 days ago
4 days ago-
Depth Anything V2
Paper • 2406.09414 • Published • 103 -
An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
Paper • 2406.09415 • Published • 51 -
Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
Paper • 2406.04338 • Published • 39 -
SAM 2: Segment Anything in Images and Videos
Paper • 2408.00714 • Published • 116
Collection by
May 8
May 8-
Beyond Language Models: Byte Models are Digital World Simulators
Paper • 2402.19155 • Published • 53 -
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Paper • 2402.19427 • Published • 56 -
VisionLLaMA: A Unified LLaMA Interface for Vision Tasks
Paper • 2403.00522 • Published • 46 -
Resonance RoPE: Improving Context Length Generalization of Large Language Models
Paper • 2403.00071 • Published • 24
Collection by
Aug 25
Aug 25-
Byte Latent Transformer: Patches Scale Better Than Tokens
Paper • 2412.09871 • Published • 108 -
Causal Diffusion Transformers for Generative Modeling
Paper • 2412.12095 • Published • 23 -
Tensor Product Attention Is All You Need
Paper • 2501.06425 • Published • 89 -
TransMLA: Multi-head Latent Attention Is All You Need
Paper • 2502.07864 • Published • 58
Collection by
Sep 7
Sep 7-
MambaVision: A Hybrid Mamba-Transformer Vision Backbone
Paper • 2407.08083 • Published • 32 -
Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
Paper • 2408.11039 • Published • 63 -
The Mamba in the Llama: Distilling and Accelerating Hybrid Models
Paper • 2408.15237 • Published • 42 -
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
Paper • 2409.11355 • Published • 31
Collection by
10 days ago
10 days ago-
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper • 2404.15653 • Published • 29 -
MoDE: CLIP Data Experts via Clustering
Paper • 2404.16030 • Published • 15 -
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Paper • 2405.12130 • Published • 50 -
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Paper • 2405.12981 • Published • 33
Collection by
Aug 28
Aug 28Collection by
Aug 25
Aug 25-
Byte Latent Transformer: Patches Scale Better Than Tokens
Paper • 2412.09871 • Published • 108 -
Causal Diffusion Transformers for Generative Modeling
Paper • 2412.12095 • Published • 23 -
Tensor Product Attention Is All You Need
Paper • 2501.06425 • Published • 89 -
TransMLA: Multi-head Latent Attention Is All You Need
Paper • 2502.07864 • Published • 58
Collection by
14 days ago
14 days ago-
FAN: Fourier Analysis Networks
Paper • 2410.02675 • Published • 28 -
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
Collection by
Sep 7
Sep 7-
MambaVision: A Hybrid Mamba-Transformer Vision Backbone
Paper • 2407.08083 • Published • 32 -
Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model
Paper • 2408.11039 • Published • 63 -
The Mamba in the Llama: Distilling and Accelerating Hybrid Models
Paper • 2408.15237 • Published • 42 -
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
Paper • 2409.11355 • Published • 31
Collection by
4 days ago
4 days ago-
Depth Anything V2
Paper • 2406.09414 • Published • 103 -
An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
Paper • 2406.09415 • Published • 51 -
Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion
Paper • 2406.04338 • Published • 39 -
SAM 2: Segment Anything in Images and Videos
Paper • 2408.00714 • Published • 116
Collection by
10 days ago
10 days ago-
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Paper • 2404.15653 • Published • 29 -
MoDE: CLIP Data Experts via Clustering
Paper • 2404.16030 • Published • 15 -
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
Paper • 2405.12130 • Published • 50 -
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Paper • 2405.12981 • Published • 33
Collection by
May 8
May 8-
Beyond Language Models: Byte Models are Digital World Simulators
Paper • 2402.19155 • Published • 53 -
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Paper • 2402.19427 • Published • 56 -
VisionLLaMA: A Unified LLaMA Interface for Vision Tasks
Paper • 2403.00522 • Published • 46 -
Resonance RoPE: Improving Context Length Generalization of Large Language Models
Paper • 2403.00071 • Published • 24