HanSaem Kim

kensaem's activity

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

upvoted 2 papers 17 days ago

UltraGen: High-Resolution Video Generation with Hierarchical Attention

Paper • 2510.18775 • Published 19 days ago • 16

UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation

Paper • 2510.18701 • Published 19 days ago • 66

upvoted 3 papers 18 days ago

MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generation

Paper • 2510.18692 • Published 19 days ago • 39

Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

Paper • 2510.15742 • Published 23 days ago • 49

Latent Diffusion Model without Variational Autoencoder

Paper • 2510.15301 • Published 23 days ago • 48

upvoted 2 papers 19 days ago

BLIP3o-NEXT: Next Frontier of Native Image Generation

Paper • 2510.15857 • Published 23 days ago • 22

Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback

Paper • 2510.16888 • Published 21 days ago • 18

upvoted 8 papers 3 months ago

FLARE: Fast Low-rank Attention Routing Engine

Paper • 2508.12594 • Published Aug 18 • 7

Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

Paper • 2508.14811 • Published Aug 20 • 42

FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation

Paper • 2508.11255 • Published Aug 15 • 11

DINOv3

Paper • 2508.10104 • Published Aug 13 • 275

Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

Paper • 2508.07901 • Published Aug 11 • 39

Story2Board: A Training-Free Approach for Expressive Storyboard Generation

Paper • 2508.09983 • Published Aug 13 • 68

NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

Paper • 2508.10711 • Published Aug 14 • 142

PUSA V1.0: Surpassing Wan-I2V with $500 Training Cost by Vectorized Timestep Adaptation

Paper • 2507.16116 • Published Jul 22 • 11

upvoted 5 papers 4 months ago

StreamDiT: Real-Time Streaming Text-to-Video Generation

Paper • 2507.03745 • Published Jul 4 • 31

Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation

Paper • 2507.05963 • Published Jul 8 • 12

4KAgent: Agentic Any Image to 4K Super-Resolution

Paper • 2507.07105 • Published Jul 9 • 104

Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection

Paper • 2507.07994 • Published Jul 10 • 2

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Paper • 2507.06261 • Published Jul 7 • 63