Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs.- CoTracker: It is Better to Track Together.- SPHINX: A Mixer of Weights, Visual Embeddings and Image Scales for Multi-modal Large Language Models.- PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology.- Improving Adversarial Transferability via Model Alignment.- RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarios.- ADen: Adaptive Density Representations for Sparse-view Camera Pose Estimation.- Embodied Understanding of Driving Scenarios.

- Learning to Drive via Asymmetric Self-Play.- OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation.- ViLA: Efficient Video-Language Alignment for Video Question Answering.- Factorizing Text-to-Video Generation by Explicit Image Conditioning.- MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices.- Open-Set Biometrics: Beyond Good Closed-Set Models.- UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening.- Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution.

- Osmosis: RGBD Diffusion Prior for Underwater Image Restoration.- Towards Adaptive Pseudo-label Learning for Semi-Supervised Temporal Action Localization.- Computing the Lipschitz constant needed for fast scene recovery from CASSI measurements.- DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields.- Flowed Time of Flight Radiance Fields.- 3D-GOI: 3D GAN Omni-Inversion for Multifaceted and Multi-object Editing.- Fast Registration of Photorealistic Avatars for VR Facial Animation.- CoPT: Unsupervised Domain Adaptive Segmentation using Domain-Agnostic Text Embeddings.

- HiFi-Score: Fine-grained Image Description Evaluation with Hierarchical Parsing Graphs.- Image-to-Lidar Relational Distillation for Autonomous Driving Data.- Thinking Outside the BBox: Unconstrained Generative Object Compositing.