Sanja Fidler

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer

ChronoEdit: Towards Temporal Reasoning for In-Context Image Editing and World Simulation

Test-time scaling of diffusions with flow maps

Where is Motion From? Scalable Motion Attribution for Video Generation Models

UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting

OmniRe: Omni Urban Scene Reconstruction

Align Your Flow: Scaling Continuous-Time Flow Map Distillation

LuxDiT: Lighting Estimation with Video Diffusion Transformer

Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos

ReMatching Dynamic Reconstruction Flow

LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception

VideoPanda: Video Panoramic Diffusion With Multi-view Attention

Wolf: Accurate Video Captioning with a World Summarization Framework

Can Large Vision-Language Models Correct Grounding Errors By Themselves?

On Inherent 3D Reasoning of VLMs in Indoor Scene Layout Design