SeongWan Kim

idgmatrix's activity

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

upvoted 2 papers about 6 hours ago

Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Paper • 2512.20848 • Published 12 days ago • 30

NVIDIA Nemotron 3: Efficient and Open Intelligence

Paper • 2512.20856 • Published 12 days ago • 29

upvoted 4 papers about 7 hours ago

Omni-Weather: Unified Multimodal Foundation Model for Weather Generation and Understanding

Paper • 2512.21643 • Published 11 days ago • 11

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

Paper • 2512.23705 • Published 7 days ago • 43

Web World Models

Paper • 2512.23676 • Published 7 days ago • 22

mHC: Manifold-Constrained Hyper-Connections

Paper • 2512.24880 • Published 5 days ago • 193

upvoted 2 papers 13 days ago

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

Paper • 2512.19693 • Published 14 days ago • 61

Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers

Paper • 2512.17351 • Published 17 days ago • 24

upvoted 2 papers 14 days ago

Make-It-Poseable: Feed-forward Latent Posing Model for 3D Humanoid Character Animation

Paper • 2512.16767 • Published 18 days ago • 4

Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition

Paper • 2512.15603 • Published 19 days ago • 59

upvoted a paper 20 days ago

EgoX: Egocentric Video Generation from a Single Exocentric Video

Paper • 2512.08269 • Published 27 days ago • 116

upvoted 4 papers 24 days ago

Multi-view Pyramid Transformer: Look Coarser to See Broader

Paper • 2512.07806 • Published 28 days ago • 20

Voxify3D: Pixel Art Meets Volumetric Rendering

Paper • 2512.07834 • Published 28 days ago • 43

MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos

Paper • 2512.10881 • Published 25 days ago • 29

StereoWorld: Geometry-Aware Monocular-to-Stereo Video Generation

Paper • 2512.09363 • Published 26 days ago • 71

upvoted 5 papers about 1 month ago

SIMA 2: A Generalist Embodied Agent for Virtual Worlds

Paper • 2512.04797 • Published Dec 4, 2025 • 24

RELIC: Interactive Video World Model with Long-Horizon Memory

Paper • 2512.04040 • Published Dec 3, 2025 • 23

Qwen3-VL Technical Report

Paper • 2511.21631 • Published Nov 26, 2025 • 148

Constructor Theory of Thermodynamics

Paper • 1608.02625 • Published Jul 21, 2016 • 1

Deep Unsupervised Learning using Nonequilibrium Thermodynamics

Paper • 1503.03585 • Published Mar 12, 2015 • 6