Taekyung Ki

taekyungki's activity

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

upvoted 4 papers about 16 hours ago

Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length

Paper • 2512.04677 • Published 4 days ago • 150

Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation

Paper • 2512.04678 • Published 4 days ago • 37

EditThinker: Unlocking Iterative Reasoning for Any Image Editor

Paper • 2512.05965 • Published 3 days ago • 30

World Models That Know When They Don't Know: Controllable Video Generation with Calibrated Uncertainty

Paper • 2512.05927 • Published 3 days ago • 8

upvoted a paper 6 days ago

WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning

Paper • 2512.02425 • Published 7 days ago • 22

upvoted a paper 11 days ago

Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks

Paper • 2511.15065 • Published 20 days ago • 74

upvoted a paper 15 days ago

DoPE: Denoising Rotary Position Embedding

Paper • 2511.09146 • Published 26 days ago • 92

upvoted a paper 17 days ago

Back to Basics: Let Denoising Generative Models Denoise

Paper • 2511.13720 • Published 21 days ago • 64

upvoted a paper 25 days ago

TiDAR: Think in Diffusion, Talk in Autoregression

Paper • 2511.08923 • Published 27 days ago • 111

upvoted a paper 27 days ago

Adaptive Multi-Agent Response Refinement in Conversational Systems

Paper • 2511.08319 • Published 27 days ago • 40

upvoted a paper 28 days ago

Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models

Paper • 2511.03317 • Published Nov 5 • 6

upvoted 6 papers about 1 month ago

Visual Diffusion Models are Geometric Solvers

Paper • 2510.21697 • Published Oct 24 • 18

WithAnyone: Towards Controllable and ID Consistent Image Generation

Paper • 2510.14975 • Published Oct 16 • 84

VISTA: A Test-Time Self-Improving Video Generation Agent

Paper • 2510.15831 • Published Oct 17 • 20

Latent Diffusion Model without Variational Autoencoder

Paper • 2510.15301 • Published Oct 17 • 48

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

Paper • 2510.15870 • Published Oct 17 • 89

NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks

Paper • 2510.15019 • Published Oct 16 • 63

upvoted 3 papers about 2 months ago

Diffusion Transformers with Representation Autoencoders

Paper • 2510.11690 • Published Oct 13 • 165

TAG:Tangential Amplifying Guidance for Hallucination-Resistant Diffusion Sampling

Paper • 2510.04533 • Published Oct 6 • 47

Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs

Paper • 2510.09201 • Published Oct 10 • 49