SeongWan Kim

idgmatrix's activity

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

upvoted a paper about 8 hours ago

On-Policy Delta Distillation for Multilingual Math Reasoning

Paper • 2608.05802 • Published 5 days ago • 29

upvoted 2 papers 4 days ago

K-EXAONE 2.0 Technical Report

Paper • 2608.04505 • Published 6 days ago • 22

NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap

Paper • 2608.04397 • Published 6 days ago • 20

upvoted a paper 6 days ago

Mental World Modeling

Paper • 2607.27201 • Published 13 days ago • 103

upvoted a paper 7 days ago

Meshy T2: Fast Native Mesh Generation with Flow Matching

Paper • 2607.28675 • Published 14 days ago • 55

upvoted a paper 10 days ago

Explicit Layer Modeling for Video Object Insertion and Layer Decomposition

Paper • 2607.25802 • Published 14 days ago • 8

upvoted a paper 12 days ago

ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition

Paper • 2607.25565 • Published 14 days ago • 65

upvoted 2 papers 13 days ago

Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models

Paper • 2607.21936 • Published 18 days ago • 11

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 15 days ago • 486

upvoted 2 papers 14 days ago

LAMAR: An Open Language-Aware Multilingual Alignment Reranker

Paper • 2607.22042 • Published 18 days ago • 16

AREX: Towards a Recursively Self-Improving Agent for Deep Research

Paper • 2607.21461 • Published 19 days ago • 152

upvoted 2 papers 19 days ago

Generative World Renderer at the Speed of Play

Paper • 2607.18703 • Published 20 days ago • 83

AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report

Paper • 2607.18367 • Published 21 days ago • 60

upvoted a paper 20 days ago

DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generation

Paper • 2607.13365 • Published 27 days ago • 21

upvoted a paper 21 days ago

On-Policy Delta Distillation

Paper • 2607.15161 • Published 26 days ago • 38

upvoted a paper 25 days ago

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

Paper • 2607.13285 • Published 28 days ago • 232

upvoted a paper 27 days ago

4D Human-Scene Reconstruction from Low-Overlap Captures

Paper • 2607.09125 • Published Jul 10 • 53

upvoted a paper 28 days ago

Video Generation Models are General-Purpose Vision Learners

Paper • 2607.09024 • Published Jul 10 • 87

upvoted 2 papers about 1 month ago

Video-Oasis: Rethinking Evaluation of Video Understanding

Paper • 2603.29616 • Published Jul 2 • 65

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

Paper • 2601.16211 • Published Jul 2 • 54