Ophthalmology

The Limits of Learning from Pictures and Text: Vision-Language Models and Embodied Scene Understanding

What information is sufficient to learn the full richness of human scene understanding? The distributional hypothesis holds that the statistical co-occurrence of language and images captures the conceptual knowledge underlying visual cognition. Vision-language models (VLMs) are trained on massive paired text-image corpora but lack embodied experience, making them an ideal test of the distributiona...

ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?

Beneath the stunning visual fidelity of modern AIGC models lies a "logical desert", where systems fail tasks that require physical, causal, or complex spatial reasoning. Current evaluations largely rely on superficial metrics or fragmented benchmarks, creating a ``performance mirage'' that overlooks the generative process. To address this, we introduce ViGoR Vision-G}nerative Reasoning-centric Ben...

Can Vision Foundation Models Navigate? Zero-Shot Real-World Evaluation and Lessons Learned

Visual Navigation Models (VNMs) promise generalizable, robot navigation by learning from large-scale visual demonstrations. Despite growing real-world...

Interpretable Zero-shot Referring Expression Comprehension with Query-driven Scene Graphs

Zero-shot referring expression comprehension (REC) aims to locate target objects in images given natural language queries without relying on task-spec...

Vision Hopfield Memory Networks

Recent vision and multimodal foundation backbones, such as Transformer families and state-space models like Mamba, have achieved remarkable progress, ...

Towards Comprehensive Real-Time Scene Understanding in Ophthalmic Surgery through Multimodal Image Fusion

Purpose: The integration of multimodal imaging into operating rooms paves the way for comprehensive surgical scene understanding. In ophthalmic surger...

LanteRn: Latent Visual Structured Reasoning

While language reasoning models excel in many tasks, visual reasoning remains challenging for current large multimodal models (LMMs). As a result, mos...

MuRF: Unlocking the Multi-Scale Potential of Vision Foundation Models

Vision Foundation Models (VFMs) have become the cornerstone of modern computer vision, offering robust representations across a wide array of tasks. W...

VOLMO: Versatile and Open Large Models for Ophthalmology

Vision impairment affects millions globally, and early detection is critical to preventing irreversible vision loss. Ophthalmology workflows require c...

ReDiPrune: Relevance-Diversity Pre-Projection Token Pruning for Efficient Multimodal LLMs

Recent multimodal large language models are computationally expensive because Transformers must process a large number of visual tokens. We present \t...

LLaVA-LE: Large Language-and-Vision Assistant for Lunar Exploration

Recent advances in multimodal vision-language models (VLMs) have enabled joint reasoning over visual and textual information, yet their application to...

Gaze patterns predict preference and confidence in pairwise AI image evaluation

Preference learning methods, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on pairwise huma...

Attention-aware Inference Optimizations for Large Vision-Language Models with Memory-efficient Decoding

Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significa...

Revealing Multi-View Hallucination in Large Vision-Language Models

Large vision-language models (LVLMs) are increasingly being applied to multi-view image inputs captured from diverse viewpoints. However, despite this...

VOLMO: Versatile and Open Large Models for Ophthalmology

Vision impairment affects millions globally, and early detection is critical to preventing irreversible vision loss. Ophthalmology workflows require c...

Machine vision with small numbers of detected photons per inference

Machine vision, including object recognition and image reconstruction, is a central technology in many consumer devices and scientific instruments. Th...

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification

Object hallucination in Large Vision-Language Models (LVLMs) severely compromises their reliability in real-world applications, posing a critical barr...

Retinal Layer Segmentation in OCT Images With 2.5D Cross-slice Feature Fusion Module for Glaucoma Assessment

For accurate glaucoma diagnosis and monitoring, reliable retinal layer segmentation in OCT images is essential. However, existing 2D segmentation meth...

Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection

Current Large Vision Language Models (LVLMs) excel at many zero-shot tasks like image captioning, visual question answering and OCR. However, these sa...

Connecting Meteorite Spectra to Lunar Surface Composition Using Hyperspectral Imaging and Machine Learning

We present an innovative, cost-effective framework integrating laboratory Hyperspectral Imaging (HSI) of the Bechar010 Lunar meteorite with ground-bas...