SeongWan Kim

idgmatrix's activity

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

upvoted 5 papers 1 day ago

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published 22 days ago • 92

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation

Paper • 2512.24551 • Published 9 days ago • 18

AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents

Paper • 2512.23343 • Published 10 days ago • 25

Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling

Paper • 2512.23959 • Published 10 days ago • 94

DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models

Paper • 2512.24165 • Published 9 days ago • 46

upvoted a paper 3 days ago

K-EXAONE Technical Report

Paper • 2601.01739 • Published 4 days ago • 71

upvoted 6 papers 4 days ago

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

Paper • 2512.20848 • Published 16 days ago • 32

NVIDIA Nemotron 3: Efficient and Open Intelligence

Paper • 2512.20856 • Published 16 days ago • 31

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

Paper • 2512.21643 • Published 14 days ago • 11

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

Paper • 2512.23705 • Published 10 days ago • 44

Web World Models

Paper • 2512.23676 • Published 10 days ago • 23

mHC: Manifold-Constrained Hyper-Connections

Paper • 2512.24880 • Published 8 days ago • 227

upvoted 2 papers 16 days ago

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

Paper • 2512.19693 • Published 17 days ago • 62

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

Paper • 2512.17351 • Published 20 days ago • 25

upvoted 2 papers 18 days ago

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

Paper • 2512.16767 • Published 21 days ago • 4

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

Paper • 2512.15603 • Published 22 days ago • 60

upvoted a paper 23 days ago

EgoX: Egocentric Video Generation from a Single Exocentric Video

Paper • 2512.08269 • Published about 1 month ago • 116

upvoted 2 papers 27 days ago

Multi-view Pyramid Transformer: Look Coarser to See Broader

Paper • 2512.07806 • Published about 1 month ago • 20

Voxify3D: Pixel Art Meets Volumetric Rendering

Paper • 2512.07834 • Published about 1 month ago • 43

upvoted a paper 28 days ago

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

Paper • 2512.10881 • Published 28 days ago • 29