HanSaem Kim

kensaem's activity

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

upvoted 6 papers 3 days ago

SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers

Paper • 2506.00830 • Published 11 days ago • 7

SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

Paper • 2506.05301 • Published 7 days ago • 56

Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

Paper • 2506.05176 • Published 7 days ago • 55

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis

Paper • 2506.06276 • Published 6 days ago • 18

Teller: Real-Time Streaming Audio-Driven Portrait Animation with Autoregressive Motion Generation

Paper • 2503.18429 • Published Mar 24 • 2

OmniTalker: Real-Time Text-Driven Talking Head Generation with In-Context Audio-Visual Style Replication

Paper • 2504.02433 • Published Apr 3 • 1

upvoted 7 papers 7 days ago

RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers

Paper • 2506.02528 • Published 9 days ago • 15

FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation

Paper • 2506.01144 • Published 11 days ago • 14

AnimeShooter: A Multi-Shot Animation Dataset for Reference-Guided Video Generation

Paper • 2506.03126 • Published 9 days ago • 22

TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models

Paper • 2506.03099 • Published 9 days ago • 8

LayerFlow: A Unified Model for Layer-aware Video Generation

Paper • 2506.04228 • Published 8 days ago • 13

Image Editing As Programs with Diffusion Models

Paper • 2506.04158 • Published 8 days ago • 22

MiMo-VL Technical Report

Paper • 2506.03569 • Published 8 days ago • 70

upvoted 2 papers 15 days ago

OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data

Paper • 2505.18445 • Published 19 days ago • 63

Alchemist: Turning Public Text-to-Image Data into Generative Gold

Paper • 2505.19297 • Published 18 days ago • 74

upvoted a paper 16 days ago

Training-Free Efficient Video Generation via Dynamic Token Carving

Paper • 2505.16864 • Published 21 days ago • 21

upvoted 2 papers 20 days ago

Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities

Paper • 2505.02567 • Published May 5 • 75

Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective

Paper • 2505.15045 • Published 22 days ago • 54

upvoted 2 papers 23 days ago

LightLab: Controlling Light Sources in Images with Diffusion Models

Paper • 2505.09608 • Published 29 days ago • 31

GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing

Paper • 2505.11493 • Published 27 days ago • 3