Latest AI and machine learning research in ophthalmology for healthcare professionals.
Large Vision-Language Models (VLMs) often answer classic visual illusions "correctly" on original images, yet persist with the same responses when illusion factors are inverted, even though the visual change is obvious to humans. This raises a fundamental question: do VLMs perceive visual changes or merely recall memorized patterns? While several studies have noted this phenomenon, the underlying ...
Recent research has shown that aligning fine-grained text descriptions with localized image patches can significantly improve the zero-shot performance of pre-trained vision-language models (e.g., CLIP). However, we find that both fine-grained text descriptions and localized image patches often contain redundant information, making text-visual alignment less effective. In this paper, we tackle thi...
We present DeepSeek-OCR 2 to investigate the feasibility of a novel encoder-DeepEncoder V2-capable of dynamically reordering visual tokens upon image ...
Medical image classification is a core task in computer-aided diagnosis (CAD), playing a pivotal role in early disease detection, treatment planning, ...
Prompt learning (PL) has emerged as an effective strategy to adapt vision-language models (VLMs), such as CLIP, for downstream tasks under limited sup...
"Compression Tells Intelligence", is supported by research in artificial intelligence, particularly concerning (multimodal) large language models (LLM...
Pro-Mist filters are widely used in cinematography for their ability to create soft halation, lower contrast, and produce a distinctive, atmospheric s...
Estimating uncertainty in deep learning models is critical for reliable decision-making in high-stakes applications such as medical imaging. Prior res...
The rectangular tokens common to vision transformer methods for visual recognition can strongly affect performance of these methods due to incorporati...
Glaucoma is a top cause of irreversible blindness globally, making early detection and longitudinal follow-up pivotal to preventing permanent vision l...
Images often communicate more than they literally depict: a set of tools can suggest an occupation and a cultural artifact can suggest a tradition. Th...
Large Vision-Language Models (LVLMs) incur high computational costs due to significant redundancy in their visual tokens. To effectively reduce this c...
Large Vision-Language Models (LVLMs) hold significant promise for medical applications, yet their deployment is often constrained by insufficient alig...
Electric field (EF) stimulation is an emerging neuromodulatory strategy for promoting the repair and functional recovery of degenerated neural network...
Retinal prostheses restore limited visual perception, but low spatial resolution and temporal persistence make reading difficult. In sequential letter...
Prevailing models aiming at explaining heading assume that humans need to recover the Focus of Expansion (FOE) while filtering out rotational flow (cu...
Few-Shot Anomaly Detection (FSAD) has emerged as a critical paradigm for identifying irregularities using scarce normal references. While recent metho...
Composed Video Retrieval (CoVR) facilitates video retrieval by combining visual and textual queries. However, existing CoVR frameworks typically fuse ...
While text-to-image (T2I) models have advanced considerably, their capability to associate colors with implicit concepts remains underexplored. To add...
This paper provides a fresh view of the neural network (NN) data flow problem, i.e., identifying the NN connections that are most important for the pe...