Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models... show more

Tanishq Mathew Abraham, Ph.D.
21,813 Aufrufe • vor 1 Jahr
🚨Announcing our #ICLR2025 Oral! 🔥Diffusion LMs are on the... show more

Marianne Arriola @ICML
149,953 Aufrufe • vor 1 Jahr
(1/2) Check out "𝐏𝐨𝐥𝐲𝐃𝐢𝐟𝐟: Generating 3D Polygonal Meshes with... show more

Matthias Niessner
57,941 Aufrufe • vor 2 Jahren
🚀 Self-speculation brings 6.75x real speedup for LLM generation... show more

Pavlo Molchanov
66,519 Aufrufe • vor 1 Monat
DimensionX: Create Any 3D and 4D Scenes from a... show more

MrNeRF
17,047 Aufrufe • vor 1 Jahr
1/ Happy to share UniDisc - Unified Multimodal Discrete... show more

Mihir Prabhudesai
104,934 Aufrufe • vor 1 Jahr
Switti -- a new scale-wise transformer for text-to-image generation... show more

Gradio
29,314 Aufrufe • vor 1 Jahr
Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos... show more

MrNeRF
24,729 Aufrufe • vor 1 Jahr
You can now use Flux and other image generation... show more

PUBLC
648,867 Aufrufe • vor 1 Jahr
Wow. AI-generated animation from a video. This experiment combines... show more

Nathan Shipley
172,681 Aufrufe • vor 2 Jahren
Show-o One Single Transformer to Unify Multimodal Understanding and... show more

AK
124,048 Aufrufe • vor 1 Jahr
Most recent diffusion language model research (that I’ve seen)... show more

nathan (in sf)
40,440 Aufrufe • vor 6 Monaten
We are also releasing self-contained lecture notes that explain... show more

Peter Holderrieth
475,530 Aufrufe • vor 4 Monaten
We took a 30B model and split it in... show more

NVIDIA AI
757,925 Aufrufe • vor 20 Tagen
Introducing 📦𝗔𝗿𝘁𝗶𝗟𝗮𝘁𝗲𝗻𝘁🔧 (SIGGRAPH Asia 2025) — a high-quality 3D... show more

Xingang Pan
11,517 Aufrufe • vor 8 Monaten
Decentralized Diffusion Models power stronger models trained on more... show more

David McAllister
46,415 Aufrufe • vor 1 Jahr
Wonderland: Navigating 3D Scenes from a Single Image Contributions:... show more

MrNeRF
52,801 Aufrufe • vor 1 Jahr
World modeling and imitation learning have largely been considered... show more

Abhishek Gupta
11,430 Aufrufe • vor 1 Jahr
🚀New paper out - We present Video-MSG (Multimodal Sketch... show more

Jialu Li
35,060 Aufrufe • vor 1 Jahr
NVIDIA AI Released DiffusionRenderer: An AI Model for Editable,... show more

Marktechpost AI Dev News ⚡
104,741 Aufrufe • vor 1 Jahr
Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation paper page:... show more

AK
375,123 Aufrufe • vor 3 Jahren