Foundation Models

Depth Prompting for Sensor-Agnostic Depth Estimation CVPR 2024 GLID: Pre-training a Generalist Encoder-Decoder Vision Model CVPR 2024 InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD NeurIPS 2024 Recognize Any Regions NeurIPS 2024 Towards a "Universal Translator" for Neural Dynamics at Single-Cell, Single-Spike Resolution NeurIPS 2024 Towards Global Optimal Visual In-Context Learning Prompt Selection NeurIPS 2024 Uncertainty-aware Fine-tuning of Segmentation Foundation Models NeurIPS 2024 Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly NeurIPS 2024 An Inverse Scaling Law for CLIP Training NeurIPS 2023 CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics AAAI 2023 DynIBaR: Neural Dynamic Image-Based Rendering CVPR 2023 EVA: Exploring the Limits of Masked Visual Representation Learning at Scale CVPR 2023 Hint-Aug: Drawing Hints From Foundation Vision Transformers Towards Boosted Few-Shot Parameter-Efficient Tuning CVPR 2023 HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork NeurIPS 2023 Open-Vocabulary Attribute Detection CVPR 2023 An Explainable Toolbox for Evaluating Pre-trained Vision-Language Models EMNLP 2022 Could Giant Pre-trained Image Models Extract Universal Representations? NeurIPS 2022 Masked Autoencoders Are Scalable Vision Learners CVPR 2022 Playable Environments: Video Manipulation in Space and Time CVPR 2022 SOLQ: Segmenting Objects by Learning Queries NeurIPS 2021 A Flexible and Easy-to-use Semantic Role Labeling Framework for Different Languages COLING 2018