SimPB: A Single Model for 2D and 3D Object Detection from Multiple Cameras.- EMDM: Efficient Motion Diffusion Model for Fast, High-Quality Human Motion Generation.- Editable Image Elements for Controllable Synthesis.- Improving 2D Feature Representations by 3D-Aware Fine-Tuning.- Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection.- PCF-Lift: Panoptic Lifting by Probabilistic Contrastive Fusion.- SemGrasp: Semantic Grasp Generation via Language Aligned Discretization.- MANIKIN: Biomechanically Accurate Neural Inverse Kinematics for Human Motion Estimation.

- Simple Unsupervised Knowledge Distillation With Space Similarity.- DragAPart: Learning a Part-Level Motion Prior for Articulated Objects.- Diffusion Bridges for 3D Point Cloud Denoising.- Optimizing Illuminant Estimation in Dual-Exposure HDR Imaging.- BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos.- MarineInst: A Foundation Model for Marine Image Analysis with Instance Visual Description.- Superpixel-informed Implicit Neural Representation for Multi-Dimensional Data.- EgoPoser: Robust Real-Time Egocentric Pose Estimation from Sparse and Intermittent Observations Everywhere.

- Physics-Free Spectrally Multiplexed Photometric Stereo under Unknown Spectral Composition.- SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction.- VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models.- Alignist: CAD-Informed Orientation Distribution Estimation by Fusing Shape and Correspondences.- Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs.- Physics-Based Interaction with 3D Objects via Video Generation.- Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussians.- Deep Patch Visual SLAM.

- Surface Reconstruction for 3D Gaussian Splatting via Local Structural Hints.- HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splatting.- LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow.