Efstathios Karypidis

Sta8is's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a collection 3 days ago

Latent-Foresight

Collection

Latent-Foresight: end-to-end learning of predictable latent representations for world models. Cityscapes and Cityscapes+nuScenes+CoVLA checkpoints. • 2 items • Updated 3 days ago

updated a model 3 days ago

Sta8is/Latent-Foresight_csnscovla

Image Feature Extraction • Updated 3 days ago

published 2 models 3 days ago

Sta8is/Latent-Foresight_csnscovla

Image Feature Extraction • Updated 3 days ago

Sta8is/Latent-Foresight_cs

Image Feature Extraction • Updated 3 days ago

updated a model 3 days ago

Sta8is/Latent-Foresight_cs

Image Feature Extraction • Updated 3 days ago

upvoted a paper 5 days ago

Decoding Looped Transformers Better for (Almost) Free

Paper • 2610.02185 • Published 7 days ago • 45

authored a paper 5 days ago

Latent-Foresight: End-to-End Learning Predictable Representations for Latent World Models

Paper • 2610.01942 • Published 7 days ago • 9

upvoted a paper 5 days ago

Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes

Paper • 2610.02117 • Published 7 days ago • 22

submitted a paper to Daily Papers 6 days ago

Latent-Foresight: End-to-End Learning Predictable Representations for Latent World Models

Paper • 2610.01942 • Published 7 days ago • 9

upvoted 3 papers 8 days ago

HiRAE: Hierarchical Representation Autoencoding with Residual Budgets

Paper • 2609.37775 • Published 9 days ago • 25

EVO-WAM: Evolving World Action Models through Video-Action Verification

Paper • 2609.38057 • Published 9 days ago • 48

What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling

Paper • 2609.34981 • Published 9 days ago • 136

upvoted 2 papers 14 days ago

The Past Frames the Future: Memory for Autoregressive Video Generation

Paper • 2609.28466 • Published 15 days ago • 64

On the Diffusibility of High-Dimensional Latents

Paper • 2609.28473 • Published 15 days ago • 19

upvoted a paper 15 days ago

GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation

Paper • 2609.24981 • Published 17 days ago • 76

upvoted a paper 16 days ago

Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms

Paper • 2609.23658 • Published 18 days ago • 30

updated a model about 1 month ago

Sta8is/Re2Pix_cityscapes_40k

Updated Sep 6

published a model about 1 month ago

Sta8is/Re2Pix_cityscapes_40k

Updated Sep 6

published a dataset about 1 month ago

Sta8is/cityscapes_seq_video

Viewer • Updated Sep 5 • 3.48k • 805