Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal.- Unsupervised Moving Object Segmentation with Atmospheric Turbulence.- AccDiffusion: An Accurate Method for Higher-Resolution Image Generation.- Uncertainty-Driven Spectral Compressive Imaging with Spatial-Frequency Transformer.- CaesarNeRF: Calibrated Semantic Representation for Few-Shot Generalizable Neural Rendering.- MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping.- Image Demoireing in RAW and sRGB Domains.- LiDAR-Event Stereo Fusion with Hallucinations.

- X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs.- Learning Anomalies with Normality Prior for Unsupervised Video Anomaly Detection.- Revisiting Supervision for Continual Representation Learning.- FLAT: Flux-aware Imperceptible Adversarial Attacks on 3D Point Clouds.- MMBENCH: Is Your Multi-Modal Model an All-around Player?.- Implicit Filtering for Learning Neural Signed Distance Functions from 3D Point Clouds.- Unsupervised Exposure Correction.- Anytime Continual Learning for Open Vocabulary Classification.

- External Knowledge Enhanced 3D Scene Generation from Sketch.- G3R: Gradient Guided Generalizable Reconstruction.- DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting.- Frequency-Spatial Entanglement Learning for Camouflaged Object Detection.- VisionTrap: Vision-Augmented Trajectory Prediction Guided by Textual Descriptions.- Occluded Gait Recognition with Mixture of Experts: An Action Detection Perspective.- EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis.- Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models.

- On the Utility of 3D Hand Poses for Action Recognition.- DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding.- Operational Open-Set Recognition and PostMax Refinement.