HanSaem Kim

kensaem's activity

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

upvoted 5 papers 1 day ago

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

Paper • 2504.02542 • Published 2 days ago • 13

SkyReels-A2: Compose Anything in Video Diffusion Transformers

Paper • 2504.02436 • Published 2 days ago • 18

GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation

Paper • 2504.02782 • Published 2 days ago • 39

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

Paper • 2503.18886 • Published 12 days ago • 20

Boost Your Own Human Image Generation Model via Direct Preference Optimization with AI Feedback

Paper • 2405.20216 • Published May 30, 2024 • 15

upvoted 3 papers 5 days ago

Qwen2.5-Omni Technical Report

Paper • 2503.20215 • Published 10 days ago • 118

Gemma 3 Technical Report

Paper • 2503.19786 • Published 11 days ago • 42

Wan: Open and Advanced Large-Scale Video Generative Models

Paper • 2503.20314 • Published 10 days ago • 46

upvoted a paper 16 days ago

Concat-ID: Towards Universal Identity-Preserving Video Synthesis

Paper • 2503.14151 • Published 18 days ago • 10

upvoted 10 papers 17 days ago

OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting

Paper • 2503.08677 • Published 25 days ago • 27

DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation

Paper • 2503.10618 • Published 23 days ago • 17

Distilling Diversity and Control in Diffusion Models

Paper • 2503.10637 • Published 23 days ago • 14

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Paper • 2503.11647 • Published 22 days ago • 129

FlowTok: Flowing Seamlessly Across Text and Image Tokens

Paper • 2503.10772 • Published 23 days ago • 18

Edit Transfer: Learning Image Editing via Vision In-Context Relations

Paper • 2503.13327 • Published 19 days ago • 28

Personalize Anything for Free with Diffusion Transformer

Paper • 2503.12590 • Published 20 days ago • 42

DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation

Paper • 2503.06053 • Published 28 days ago • 136

Impossible Videos

Paper • 2503.14378 • Published 18 days ago • 57

CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era

Paper • 2503.12329 • Published 20 days ago • 24

upvoted a paper 26 days ago

GHOST 2.0: generative high-fidelity one shot transfer of heads

Paper • 2502.18417 • Published Feb 25 • 65