Latest AI and machine learning research in ophthalmology for healthcare professionals.
Vision-language models (VLMs) are increasingly used as zero-shot controllers, but successful trajectories do not necessarily show that decisions are grounded in visual input: simulator dynamics and conservative action priors can produce favourable scores without meaningful perception. We investigate this with an input-ablation battery: blind-image controls, repeated identical inputs, lane-axis ref...
Picture books and comics have long been used to disseminate hateful narratives because they are easily understood even by children, as exemplified by the notorious Nazi propaganda picture book \emph{Der Giftpilz}. Recently, frontier text-to-image (T2I) systems such as Gemini and GPT-Image have enabled conversational generation with consistent characters and scenes across turns, making hateful visu...
Contrastive vision-language models such as CLIP and BLIP are typically trained on short image captions, limiting their ability to retrieve images from...
Vision transformers (ViTs) have become the de facto standard for image encoding across many perception tasks. Despite their empirical success, it rema...
Prompt tuning, a leading parameter-efficient adaptation paradigm in NLP, has recently been extended to computer vision. Visual prompt tuning (VPT) ada...
Vision-Language Models (VLMs) often lose visual grounding during multi-step reasoning: as reasoning chains grow longer, later inference steps rely inc...
The development of foundation models (FMs) is crucial for advancing endoscopic image analysis. However, existing endoscopy FMs mainly rely on self-sup...
Vision-language models (VLMs) process an image as a sequence of visual tokens, which creates a substantial computational bottleneck during inference. ...
Visual inputs in vision-language models (VLMs) are often encoded into substantially longer token sequences than text, making visual tokens a major bot...
Vision-language models excel in many multimodal tasks but remain prone to a subtle yet impactful failure mode: they tend to overestimate dominant visu...
Predicting item difficulty from content can provide an initial estimate for newly developed questions before sufficient student responses are availabl...
Similes provide a compact and expressive way to describe visual characteristics in text prompts. Recent text-to-image models (t2i models) can produce ...
Vision transformers (ViTs) have become the de facto standard for image encoding across many perception tasks. Despite their empirical success, it rema...
High-resolution images and long videos provide vision-language models with rich context for multimodal reasoning and fine-grained perception, but the ...
Multimodal large language models (MLLMs) make grounded predictions in real-world scenes by combining visual and textual cues, yet existing benchmarks ...
Large Multimodal Models (LMMs) have achieved remarkable success on images and short videos, yet scaling them to long videos remains challenging due to...
GUI grounding maps natural-language instructions to click locations and is essential for reliable GUI agents. The task remains difficult on high-resol...
While Vision-Language Models (VLMs) have demonstrated remarkable performance in processing and understanding both text and images, their large paramet...
Fewer visual tokens do not guarantee lower end-to-end latency. We evaluate break-even with a reproducible protocol that accounts for decision overhead...
Remote-sensing videos enable real-time observation of changes in target attributes, short-term activities, and scene evolution. They record motion, ac...