SeongWan Kim

idgmatrix's activity

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

upvoted 2 papers about 5 hours ago

Generative World Renderer at the Speed of Play

Paper • 2607.18703 • Published 1 day ago • 60

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

Paper • 2607.18367 • Published 2 days ago • 43

upvoted a paper 1 day ago

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

Paper • 2607.13365 • Published 8 days ago • 13

upvoted a paper 2 days ago

On-Policy Delta Distillation

Paper • 2607.15161 • Published 7 days ago • 32

upvoted a paper 6 days ago

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

Paper • 2607.13285 • Published 9 days ago • 209

upvoted a paper 8 days ago

4D Human-Scene Reconstruction from Low-Overlap Captures

Paper • 2607.09125 • Published 13 days ago • 53

upvoted a paper 9 days ago

Video Generation Models are General-Purpose Vision Learners

Paper • 2607.09024 • Published 13 days ago • 83

upvoted 2 papers 12 days ago

Video-Oasis: Rethinking Evaluation of Video Understanding

Paper • 2603.29616 • Published 21 days ago • 64

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

Paper • 2601.16211 • Published 21 days ago • 54

upvoted 4 papers 14 days ago

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

Paper • 2607.04540 • Published 18 days ago • 4

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

Paper • 2607.04412 • Published 18 days ago • 34

Gemma 4 Technical Report

Paper • 2607.02770 • Published 21 days ago • 69

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

Paper • 2606.31329 • Published 23 days ago • 7

upvoted a paper 15 days ago

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

Paper • 2606.29526 • Published 25 days ago • 168

upvoted 2 papers 19 days ago

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

Paper • 2607.02512 • Published 21 days ago • 122

Morphing into Hybrid Attention Models

Paper • 2606.30562 • Published 24 days ago • 51

upvoted a paper 20 days ago

Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts

Paper • 2607.00666 • Published 22 days ago • 24

upvoted 3 papers 21 days ago

Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning

Paper • 2606.29985 • Published 24 days ago • 20

DOPD: Dual On-policy Distillation

Paper • 2606.30626 • Published 24 days ago • 112

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

Paper • 2503.15558 • Published Mar 18, 2025 • 52