Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal.- Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation.- Efficient Few-Shot Action Recognition via Multi-Level Post-Reasoning.- Text2Place: Affordance-aware Text Guided Human Placement.- OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations.- Zero-Shot Multi-Object Scene Completion.- Beta-Tuned Timestep Diffusion Model.- POA: Pre-training Once for Models of All Sizes.

- Taming Latent Diffusion Model for Neural Radiance Field Inpainting.- MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation.- ByteEdit: Boost, Comply and Accelerate Generative Image Editing.- ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion.- High-Resolution and Few-shot View Synthesis from Asymmetric Dual-lens Inputs.- Accelerating Image Super-Resolution Networks with Pixel-Level Classification.- LASS3D: Language-Assisted Semi-Supervised 3D Semantic Segmentation with Progressive Unreliable Data Exploitation.- Contourlet Residual for Prompt Learning Enhanced Infrared Image Super-Resolution.

- Click-Gaussian: Interactive Segmentation to Any 3D Gaussians.- Random Walk on Pixel Manifolds for Anomaly Segmentation of Complex Driving Scenes.- DySeT: a Dynamic Masked Self-distillation Approach for Robust Trajectory Prediction.- Track Everything Everywhere Fast and Robustly.- Towards Open-ended Visual Quality Comparison.- FreeInit: Bridging Initialization Gap in Video Diffusion Models.- DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs.- Eliminating Feature Ambiguity for Few-Shot Segmentation.

- Soft Prompt Generation for Domain Generalization.- Shedding More Light on Robust Classifiers under the lens of Energy-based Models.