SeongWan Kim

idgmatrix's activity

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

upvoted a paper 1 day ago

ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition

Paper • 2607.25565 • Published 2 days ago • 58

upvoted 2 papers 2 days ago

Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models

Paper • 2607.21936 • Published 6 days ago • 11

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 3 days ago • 365

upvoted 2 papers 3 days ago

LAMAR: An Open Language-Aware Multilingual Alignment Reranker

Paper • 2607.22042 • Published 6 days ago • 15

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

Paper • 2607.21461 • Published 7 days ago • 149

upvoted 2 papers 8 days ago

Generative World Renderer at the Speed of Play

Paper • 2607.18703 • Published 9 days ago • 80

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

Paper • 2607.18367 • Published 10 days ago • 57

upvoted a paper 9 days ago

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

Paper • 2607.13365 • Published 15 days ago • 20

upvoted a paper 10 days ago

On-Policy Delta Distillation

Paper • 2607.15161 • Published 14 days ago • 38

upvoted a paper 14 days ago

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

Paper • 2607.13285 • Published 16 days ago • 227

upvoted a paper 16 days ago

4D Human-Scene Reconstruction from Low-Overlap Captures

Paper • 2607.09125 • Published 20 days ago • 53

upvoted a paper 17 days ago

Video Generation Models are General-Purpose Vision Learners

Paper • 2607.09024 • Published 20 days ago • 85

upvoted 2 papers 20 days ago

Video-Oasis: Rethinking Evaluation of Video Understanding

Paper • 2603.29616 • Published 28 days ago • 65

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

Paper • 2601.16211 • Published 28 days ago • 54

upvoted 3 papers 21 days ago

SceneFrom3D: Geometry-Conditioned Outdoor 3D Scene Generation via View Scheduling with Object-Level Control

Paper • 2607.04540 • Published 25 days ago • 4

LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL

Paper • 2607.04412 • Published 25 days ago • 35

Gemma 4 Technical Report

Paper • 2607.02770 • Published 28 days ago • 75

upvoted a paper 22 days ago

3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance

Paper • 2606.31329 • Published about 1 month ago • 7

upvoted a paper 23 days ago

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Paper • 2606.29526 • Published Jun 28 • 170

upvoted a paper 27 days ago

Program-as-Weights: A Programming Paradigm for Fuzzy Functions

Paper • 2607.02512 • Published 28 days ago • 238