Efstathios Karypidis

Sta8is's activity

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

upvoted a paper 1 day ago

SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices

Paper • 2601.08303 • Published 3 days ago • 12

upvoted a paper 2 days ago

DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving

Paper • 2601.01528 • Published 11 days ago • 17

upvoted 4 papers 3 days ago

AnyDepth: Depth Estimation Made Easy

Paper • 2601.02760 • Published 10 days ago • 9

Orient Anything V2: Unifying Orientation and Rotation Understanding

Paper • 2601.05573 • Published 7 days ago • 8

Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals

Paper • 2601.05848 • Published 6 days ago • 14

VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction

Paper • 2601.05966 • Published 6 days ago • 21

upvoted a paper 14 days ago

Guiding a Diffusion Transformer with the Internal Dynamics of Itself

Paper • 2512.24176 • Published 16 days ago • 7

upvoted 3 papers 16 days ago

YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection

Paper • 2512.23273 • Published 18 days ago • 13

Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation

Paper • 2512.23705 • Published 17 days ago • 44

Yume-1.5: A Text-Controlled Interactive World Generation Model

Paper • 2512.22096 • Published 20 days ago • 58

upvoted 3 papers 19 days ago

How Much 3D Do Video Foundation Models Encode?

Paper • 2512.19949 • Published 24 days ago • 9

Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning

Paper • 2512.20605 • Published 23 days ago • 60

Spatia: Video Generation with Updatable Spatial Memory

Paper • 2512.15716 • Published 29 days ago • 31

upvoted 3 papers 21 days ago

HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming

Paper • 2512.21338 • Published 22 days ago • 21

Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations

Paper • 2512.21004 • Published 23 days ago • 12

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published 29 days ago • 93

upvoted 2 papers 22 days ago

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

Paper • 2512.19693 • Published 24 days ago • 63

SemanticGen: Video Generation in Semantic Space

Paper • 2512.20619 • Published 23 days ago • 91

upvoted a paper 25 days ago

Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing

Paper • 2512.17909 • Published 27 days ago • 36

upvoted a paper 27 days ago

Next-Embedding Prediction Makes Strong Vision Learners

Paper • 2512.16922 • Published 28 days ago • 83