Taekyung Ki

tkkitkki's activity

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

upvoted a paper 3 days ago

One-Minute Video Generation with Test-Time Training

Paper • 2504.05298 • Published 17 days ago • 98

upvoted 2 papers 15 days ago

T1: Tool-integrated Self-verification for Test-time Compute Scaling in Small Language Models

Paper • 2504.04718 • Published 17 days ago • 39

Gaussian Mixture Flow Matching Models

Paper • 2504.05304 • Published 17 days ago • 12

upvoted a paper 17 days ago

Audio-visual Controlled Video Diffusion with Masked Selective State Spaces Modeling for Natural Talking Head Generation

Paper • 2504.02542 • Published 21 days ago • 41

upvoted a paper 23 days ago

MoCha: Towards Movie-Grade Talking Character Synthesis

Paper • 2503.23307 • Published 25 days ago • 129

upvoted 2 papers 29 days ago

Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models

Paper • 2503.18352 • Published Mar 24 • 6

CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models

Paper • 2503.18886 • Published about 1 month ago • 21

upvoted 2 papers about 1 month ago

Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models

Paper • 2503.09669 • Published Mar 12 • 36

FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updates

Paper • 2503.07216 • Published Mar 10 • 32

upvoted a paper about 2 months ago

Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching

Paper • 2503.05179 • Published Mar 7 • 46

upvoted 3 papers 5 months ago

One Shot, One Talk: Whole-body Talking Avatar from a Single Image

Paper • 2412.01106 • Published Dec 2, 2024 • 20

Steering Rectified Flow Models in the Vector Field for Controlled Image Generation

Paper • 2412.00100 • Published Nov 27, 2024 • 16

FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait

Paper • 2412.01064 • Published Dec 2, 2024 • 30