Christian Rupprecht

What Happens Next? Anticipating Future Motion by Generating Point Trajectories

MaskInversion: Localized Embeddings via Optimization of Explainability Maps

S3OD: Towards Generalizable Salient Object Detection with Synthetic Data

Epipolar Geometry Improves Video Generation Models

Epipolar Geometry Improves Video Generation Models

CNS-Bench: Benchmarking Model Robustness Under Continuous Nuisance Shifts

MaskInversion: Localized Embeddings via Optimization of Explainability Maps

MAD-Sherlock: Multi-Agent Debates for Out-of-Context Misinformation Detection

RealTracker: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos

PuppetMaster: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics

Incrementally Adapting Generative Vision-Language Models with Task Codebook

Highlight: Learning Visual Prompts for Vision-Language Models

What Matters for In-Context Learning: A Balancing Act of Look-up and In-Weight Learning