Yeho Gwon PRO

yehogwon's activity

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

upvoted a paper 29 days ago

Few-Step Generation via Data-Space Iteration

Paper • 2610.12102 • Published Oct 8 • 5

upvoted 4 papers about 1 month ago

Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing

Paper • 2609.37334 • Published Sep 29 • 33

Empirical Variational Autoencoder

Paper • 2610.06545 • Published Oct 5 • 6

PointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation

Paper • 2610.02840 • Published Oct 2 • 53

Scaling and Distilling Text Embeddings for Better Diffusibility

Paper • 2610.01016 • Published Oct 1 • 25

upvoted a paper about 2 months ago

HuRo: Robotizing Human Videos for Scalable VLA Pretraining

Paper • 2609.10706 • Published Sep 18 • 25

upvoted a paper 2 months ago

GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling

Paper • 2608.29335 • Published Aug 29 • 73

upvoted 4 papers 3 months ago

HelloWorld: Enabling Socially Interactive Characters in Video World Models

Paper • 2608.05070 • Published Aug 5 • 34

Scaling Properties of Text Conditioning in Visual Generation

Paper • 2607.29679 • Published Jul 31 • 31

Wonder: Video World Model Done Better

Paper • 2607.26037 • Published Jul 28 • 19

dRAE: Representation Autoencoder with Hyper-Spherical Codes

Paper • 2607.22148 • Published Jul 24 • 11

upvoted 2 papers 4 months ago

ACID: Action Consistency via Inverse Dynamics for Planning with World Models

Paper • 2607.02403 • Published Jul 2 • 21

Optimizing Visual Generative Models via Distribution-wise Rewards

Paper • 2607.02291 • Published Jul 2 • 17

upvoted 3 papers 6 months ago

JLT: Clean-Latent Prediction in Latent Diffusion Transformers

Paper • 2605.27102 • Published May 26 • 30

Normalizing Trajectory Models

Paper • 2605.08078 • Published May 8 • 14

Representation Fréchet Loss for Visual Generation

Paper • 2604.28190 • Published Apr 30 • 30

upvoted 2 papers 8 months ago

Cog3DMap: Multi-View Vision-Language Reasoning with 3D Cognitive Maps

Paper • 2603.23023 • Published Mar 24 • 22

Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model

Paper • 2603.05438 • Published Mar 5 • 41

upvoted 2 papers 12 months ago

SAM 3D: 3Dfy Anything in Images

Paper • 2511.16624 • Published Nov 20, 2025 • 119

Back to Basics: Let Denoising Generative Models Denoise

Paper • 2511.13720 • Published Nov 17, 2025 • 72