Jiwon Kang

Jiwon-Kang's activity

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

upvoted a paper 3 days ago

Speculative Forcing for Efficient Autoregressive Video Generation

Paper • 2610.22347 • Published 4 days ago • 78

upvoted a paper 9 days ago

Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction

Paper • 2610.12299 • Published 11 days ago • 72

upvoted 2 papers 11 days ago

GRACE: Generation-aware latent compression for efficient video generation

Paper • 2610.10524 • Published 12 days ago • 91

Tetris3D: 3D Scene Generation With Objects That Fit Together

Paper • 2610.10539 • Published 12 days ago • 49

upvoted a paper 16 days ago

World Observer: Joint Actor-Observer Generation for Persistent World Modeling

Paper • 2610.02162 • Published 18 days ago • 91

upvoted a paper 17 days ago

Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering

Paper • 2609.38177 • Published 20 days ago • 78

upvoted a paper 4 months ago

VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors

Paper • 2604.02486 • Published Apr 2 • 10

upvoted 2 papers 7 months ago

DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models

Paper • 2603.23499 • Published Mar 24 • 52

Grounding World Simulation Models in a Real-World Metropolis

Paper • 2603.15583 • Published Mar 16 • 156

upvoted 3 papers about 1 year ago

TAG:Tangential Amplifying Guidance for Hallucination-Resistant Diffusion Sampling

Paper • 2510.04533 • Published Oct 6, 2025 • 48

MATRIX: Mask Track Alignment for Interaction-aware Video Generation

Paper • 2510.07310 • Published Oct 8, 2025 • 36

Visual Representation Alignment for Multimodal Large Language Models

Paper • 2509.07979 • Published Sep 9, 2025 • 84

upvoted 2 papers over 1 year ago

Fine-Grained Perturbation Guidance via Attention Head Selection

Paper • 2506.10978 • Published Jun 12, 2025 • 25

URECA: Unique Region Caption Anything

Paper • 2504.05305 • Published Apr 7, 2025 • 35

upvoted a paper almost 2 years ago

A Noise is Worth Diffusion Guidance

Paper • 2412.03895 • Published Dec 5, 2024 • 29

upvoted a paper over 2 years ago

DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization

Paper • 2402.09812 • Published Feb 15, 2024 • 15