Artificial Intelligence Medical Compendium

Deep hashing is an effective approach for large-scale image retrieval. Current methods are typically classified by their supervision types: point-wise, pair-wise, and list-wise. Recent point-wise techniques (e.g., CSQ, MDS) have improved retrieval ... read more 

Prompt learning facilitates the efficient adaptation of Vision-Language Models (VLMs) to various downstream tasks. However, it faces two significant challenges: (1) inadequate modeling of class embedding distributions for unseen instances, leading ... read more 

Environmental sound recordings often contain intelligible speech, raising privacy concerns that limit analysis, sharing and reuse of data. In this paper, we introduce a method that renders speech unintelligible while preserving both the integrity o... read more 

Humans can naturally identify and mentally complete occluded objects in cluttered environments. However, imparting similar cognitive ability to robotics remains challenging even with advanced reconstruction techniques, which models scenes as undiff... read more 

Diffusion transformers have emerged as an alternative to U-net-based diffusion models for high-fidelity image and video generation, offering superior scalability. However, their heavy computation remains a major obstacle to real-world deployment. E... read more 

Radiance field methods, such as Neural Radiance Field or 3D Gaussian Splatting, have emerged as seminal 3D representations for synthesizing realistic novel views. For practical applications, there is ongoing research on flexible scene editing techn... read more 

Leveraging the powerful representations of pre-trained vision foundation models -- traditionally used for visual comprehension -- we explore a novel direction: building an image tokenizer directly atop such models, a largely underexplored area. Spe... read more 

3D reconstruction, which aims to recover the dense three-dimensional structure of a scene, is a cornerstone technology for numerous applications, including augmented/virtual reality, autonomous driving, and robotics. While traditional pipelines lik... read more 

Many document types use intrinsic, convention-driven structures that serve to encode precise and structured information, such as the conventions governing engineering drawings. However, state-of-the-art approaches treat document recognition as a me... read more 

F3-Net is a foundation model designed to overcome persistent challenges in clinical medical image segmentation, including reliance on complete multimodal inputs, limited generalizability, and narrow task specificity. Through flexible synthetic moda... read more