Seongchan Kim

Seongchan's activity

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

upvoted 3 papers 3 days ago

Long-WAM: Scaling the Context of World-Action Models

Paper • 2610.10528 • Published 5 days ago • 104

Tetris3D: 3D Scene Generation With Objects That Fit Together

Paper • 2610.10539 • Published 5 days ago • 45

GRACE: Generation-aware latent compression for efficient video generation

Paper • 2610.10524 • Published 5 days ago • 76

upvoted a paper 10 days ago

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published 12 days ago • 120

upvoted a paper 11 days ago

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

Paper • 2609.38177 • Published 13 days ago • 74

upvoted 2 papers 4 months ago

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published Jun 11 • 115

ZipSplat: Fewer Gaussians, Better Splats

Paper • 2606.05102 • Published Jun 3 • 22

upvoted a paper 5 months ago

WorldKV: Efficient World Memory with World Retrieval and Compression

Paper • 2605.22718 • Published May 21 • 41

upvoted a paper 7 months ago

DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models

Paper • 2603.23499 • Published Mar 24 • 52

liked a dataset 7 months ago

nvidia/dynpose-100k

Updated May 12, 2025 • 301 • 57

upvoted 2 papers 7 months ago

WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation

Paper • 2603.16871 • Published Mar 17 • 61

Grounding World Simulation Models in a Real-World Metropolis

Paper • 2603.15583 • Published Mar 16 • 156

liked 4 datasets 8 months ago

builddotai/Egocentric-100K

Viewer • Updated Feb 16 • 1.95M • 181k • 146

naplab/AVMeme-Exam

Updated Jan 28 • 35 • 25

DAGroup-PKU/RoVid-X

Preview • Updated May 21 • 6.49k • 72

facebook/action100m-preview

Viewer • Updated Jan 29 • 120k • 988 • 150

upvoted a paper 12 months ago

Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation

Paper • 2510.23581 • Published Oct 27, 2025 • 42

authored 3 papers about 1 year ago

Multi-Granularity Video Object Segmentation

Paper • 2412.01471 • Published Dec 2, 2024

InterRVOS: Interaction-aware Referring Video Object Segmentation

Paper • 2506.02356 • Published Jun 3, 2025 • 1

MATRIX: Mask Track Alignment for Interaction-aware Video Generation

Paper • 2510.07310 • Published Oct 8, 2025 • 36