GeoCalib: Learning Single-image Calibration with Geometric Optimization.- 3D Open-Vocabulary Panoptic Segmentation with 2D-3D Vision-Language Distillation.- Semicalibrated Relative Pose from an Affine Correspondence and Monodepth.- Global Structure-from-Motion Revisited.- MobileNetV4: Universal Models for the Mobile Ecosystem.- Gravity-aligned Rotation Averaging with Circular Regression.- MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation.- Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments.

- Quanta Video Restoration.- Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models.- CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model.- ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image.- POCA: Post-training Quantization with Temporal Alignment for Codec Avatars.- HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts.- Finding Meaning in Points: Weakly Supervised Semantic Segmentation for Event Cameras.- Unsupervised Dense Prediction using Differentiable Normalized Cuts.

- Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training.- Scaling Up Personalized Image Aesthetic Assessment via Task Vector Customization.- AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion.- Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers.- EINet: Point Cloud Completion via Extrapolation and Interpolation.- Personalized Video Relighting With an At-Home Light Stage.- Temporal Residual Guided Diffusion Framework for Event-Driven Video Reconstruction.- A Secure Image Watermarking Framework with Statistical Guarantees via Adversarial Attacks on Secret Key Networks.

- SPIRE: Semantic Prompt-Driven Image Restoration.- Free-ATM: Harnessing Free Attention Masks for Representation Learning on Diffusion-Generated Images.- HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution.