KI-Forschungspapiere Täglich

Design2Code: How Far Are We From Automating Front-End Engineering?

Scaling Rectified Flow Transformers for High-Resolution Image Synthesis

OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on

MovieLLM: Enhancing Long Video Understanding with AI-Generated Movies

AtomoVideo: High Fidelity Image-to-Video Generation

DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models

InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding

ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models

TripoSR: Fast 3D Object Reconstruction from a Single Image

RT-H: Action Hierarchies Using Language

ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models

Tuning-Free Noise Rectification for High Fidelity Image-to-Video Generation

Twisting Lids Off with Two Hands

3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos