Sunghwan Hong

hongsunghwan's activity

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

upvoted 2 papers 11 days ago

Learning the 4D World through Point Trajectory Forecasting

Paper • 2610.28594 • Published 13 days ago • 54

Correction Training for Diffusion Models

Paper • 2610.14136 • Published 19 days ago • 48

upvoted a paper 18 days ago

GeoFix: Geometry Fixing for 4D Consistent Generation

Paper • 2610.14293 • Published 24 days ago • 24

upvoted a collection 25 days ago

DeskForge

Collection

Controllable desktop environment for computer-use agents: the DeskForge-1M dataset and GUI grounding models fine-tuned on it. • 5 items • Updated 23 days ago • 4

upvoted a paper 26 days ago

DeskForge: Dense Supervision from Desktop Environments for Computer-Use Agents

Paper • 2610.02320 • Published Oct 1 • 18

upvoted a paper about 1 month ago

Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering

Paper • 2609.38177 • Published Sep 29 • 51

upvoted a paper 4 months ago

Hoi! - A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation

Paper • 2512.04884 • Published Apr 15 • 3

upvoted 2 papers 5 months ago

Geometric Action Model for Robot Policy Learning

Paper • 2606.17046 • Published Jun 15 • 116

ZipSplat: Fewer Gaussians, Better Splats

Paper • 2606.05102 • Published Jun 3 • 22

upvoted a paper about 1 year ago

Visual Representation Alignment for Multimodal Large Language Models

Paper • 2509.07979 • Published Sep 9, 2025 • 84