 Compass Control: Multi Object Orientation Control for Text-to-Image GenerationComputer Vision and Pattern Recognition (CVPR), 2025 |
 ERUPT: Efficient Rendering with Unposed Patch TransformerComputer Vision and Pattern Recognition (CVPR), 2025 |
 Moving Off-the-Grid: Scene-Grounded Video RepresentationsNeural Information Processing Systems (NeurIPS), 2024 |
 SPOT: Self-Training with Patch-Order Permutation for Object-Centric
Learning with Autoregressive TransformersComputer Vision and Pattern Recognition (CVPR), 2023 |
 SODA: Bottleneck Diffusion Models for Representation LearningComputer Vision and Pattern Recognition (CVPR), 2023 |
 DyST: Towards Dynamic Neural Scene Representations on Real-World VideosInternational Conference on Learning Representations (ICLR), 2023 |
 Viewpoint Textual Inversion: Unleashing Novel View Synthesis with
Pretrained 2D Diffusion ModelsEuropean Conference on Computer Vision (ECCV), 2023 |
