Latest AI and machine learning research in ophthalmology for healthcare professionals.
Vision-Language Models (VLMs) have demonstrated impressive performance across a versatile set of tasks. A key challenge in accelerating VLMs is storing and accessing the large Key-Value (KV) cache that encodes long visual contexts, such as images or videos. While existing KV cache compression methods are effective for Large Language Models (LLMs), directly migrating them to VLMs yields suboptima...
Multimedia file fragment classification (MFFC) aims to identify file fragment types, e.g., image/video, audio, and text without system metadata. It is of vital importance in multimedia storage and communication. Existing MFFC methods typically treat fragments as 1D byte sequences and emphasize the relations between separate bytes (interbytes) for classification. However, the more informative rel...
In vision-based robot localization and SLAM, Visual Place Recognition (VPR) is essential. This paper addresses the problem of VPR, which involves ac...
While visuomotor policy learning has advanced robotic manipulation, precisely executing contact-rich tasks remains challenging due to the limitation...
Vision science imposes rigorous requirements for the design and execution of psychophysical studies and experiments. These requirements ensure preci...
Operationalizing AI ethics and safety principles and frameworks is essential to realizing the potential benefits and mitigating potential harms caus...
Despite the remarkable success of deep neural networks (DNNs) in computer vision, they fail to remain high-performing when facing distribution shift...
Hallucination poses a challenge to the deployment of large vision-language models (LVLMs) in applications. Unlike in large language models (LLMs), h...
Autonomous surgical robots have demonstrated significant potential to standardize surgical outcomes, driving innovations that enhance safety and con...
This article aims to cover pupillography, and its potential use in a number of ophthalmological diagnostic applications in biomedical space. With th...
Federated prompt learning benefits federated learning with CLIP-like Vision-Language Model's (VLM's) robust representation learning ability through ...
In an era where societal narratives are increasingly shaped by algorithmic curation, investigating the political neutrality of LLMs is an important ...
Neuromorphic computing has emerged as a promising energy-efficient alternative to traditional artificial intelligence, predominantly utilizing spiki...
We explore the transformative potential of SAM 2, a vision foundation model, in advancing gaze estimation and eye tracking technologies. By signific...
Inherited retinal diseases (IRDs) are a diverse group of genetic disorders that lead to progressive vision loss and are a major cause of blindness i...
We present the first study of the Public Register of Licensed Persons and Registered Institutions maintained by the Hong Kong Securities and Futures...
In this work we propose a novel joint training method for Visual Place Recognition (VPR), which simultaneously learns a global descriptor and a pair...
Recent developments of vision large language models (LLMs) have seen remarkable progress, yet still encounter challenges towards multimodal generali...
Ground to aerial matching is a crucial and challenging task in outdoor robotics, particularly when GPS is absent or unreliable. Structures like buil...
As large engineering efforts go towards improving the resolution of mobile, AR and VR displays, it is important to know the maximum resolution at wh...