Taekyung Ki

taekyungki's activity

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

authored a paper 1 day ago

Self-Refining Video Sampling

Paper • 2601.18577 • Published 2 days ago • 20

upvoted a paper 2 days ago

Self-Refining Video Sampling

Paper • 2601.18577 • Published 2 days ago • 20

upvoted a paper 5 days ago

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders

Paper • 2601.16208 • Published 6 days ago • 51

upvoted a paper 7 days ago

Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance

Paper • 2601.14171 • Published 8 days ago • 47

upvoted 2 papers 13 days ago

Transition Matching Distillation for Fast Video Generation

Paper • 2601.09881 • Published 14 days ago • 32

Inference-time Physics Alignment of Video Generative Models with Latent World Models

Paper • 2601.10553 • Published 13 days ago • 12

upvoted a paper 17 days ago

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice

Paper • 2601.05175 • Published 20 days ago • 34

upvoted a paper 19 days ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Paper • 2601.05242 • Published 20 days ago • 210

upvoted a paper 20 days ago

Plenoptic Video Generation

Paper • 2601.05239 • Published 20 days ago • 12

upvoted 5 papers 21 days ago

NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation

Paper • 2601.02204 • Published 23 days ago • 60

Digital Twin AI: Opportunities and Challenges from Large Language Models to World Models

Paper • 2601.01321 • Published 25 days ago • 18

NitroGen: An Open Foundation Model for Generalist Gaming Agents

Paper • 2601.02427 • Published 24 days ago • 43

SOP: A Scalable Online Post-Training System for Vision-Language-Action Models

Paper • 2601.03044 • Published 22 days ago • 28

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published 22 days ago • 138

upvoted a paper 23 days ago

K-EXAONE Technical Report

Paper • 2601.01739 • Published 24 days ago • 88

liked a model 23 days ago

LGAI-EXAONE/K-EXAONE-236B-A23B

Text Generation • 237B • Updated 3 days ago • 14.3k • 533

authored a paper 24 days ago

Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

Paper • 2601.00664 • Published 26 days ago • 56

upvoted a paper 24 days ago

Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

Paper • 2601.00664 • Published 26 days ago • 56

liked a model about 1 month ago

XiangpengYang/VideoCoF

Video-to-Video • Updated Dec 9, 2025 • 23 • 17

upvoted a paper about 1 month ago

Exploring MLLM-Diffusion Information Transfer with MetaCanvas

Paper • 2512.11464 • Published Dec 12, 2025 • 13