Hugging Face's logo

CompVis
/
myriad

Other
English
Model card Files
xet
 Community
1
tommymarto commited on
Commit
5410f2b
·
verified ·
1 Parent(s): 973ec77

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -9,9 +9,11 @@ pipeline_tag: other
9
 
10
  [![Project Page](https://img.shields.io/badge/Project-Page-blue)](https://compvis.github.io/myriad)
11
  [![Paper](https://img.shields.io/badge/arXiv-paper-b31b1b)](https://arxiv.org/abs/2604.09527)
 
12
  [![GitHub](https://img.shields.io/badge/GitHub-Code-black)](https://github.com/CompVis/flow-poke-transformer)
13
  [![OWM-95](https://img.shields.io/badge/HuggingFace-Dataset-yellow)](https://huggingface.co/datasets/CompVis/owm-95)
14
- [![Paper](https://img.shields.io/badge/Huggingface-Papers-yellow)](https://huggingface.co/papers/2604.09527)
 
15
 
16
  MYRIAD (Motion hYpothesis Reasoning via Iterative Autoregressive Diffusion) is an autoregressive diffusion model that predicts open-set future scene dynamics as step-wise inference over sparse point trajectories. Starting from a single image, it can efficiently explore thousands of plausible future outcomes, maintaining physical plausibility.
17
 
 
9
 
10
  [![Project Page](https://img.shields.io/badge/Project-Page-blue)](https://compvis.github.io/myriad)
11
  [![Paper](https://img.shields.io/badge/arXiv-paper-b31b1b)](https://arxiv.org/abs/2604.09527)
12
+ [![Paper](https://img.shields.io/badge/Huggingface-Papers-yellow)](https://huggingface.co/papers/2604.09527)
13
  [![GitHub](https://img.shields.io/badge/GitHub-Code-black)](https://github.com/CompVis/flow-poke-transformer)
14
  [![OWM-95](https://img.shields.io/badge/HuggingFace-Dataset-yellow)](https://huggingface.co/datasets/CompVis/owm-95)
15
+ [![MYRIAD-Physics Benchmark](https://img.shields.io/badge/Related-MYRIAD--physics-green)](https://huggingface.co/datasets/CompVis/myriad-physics)
16
+
17
 
18
  MYRIAD (Motion hYpothesis Reasoning via Iterative Autoregressive Diffusion) is an autoregressive diffusion model that predicts open-set future scene dynamics as step-wise inference over sparse point trajectories. Starting from a single image, it can efficiently explore thousands of plausible future outcomes, maintaining physical plausibility.
19