Ophthalmology

Tac-DINO: Learning Vision-Tactile Features with Patch Alignment

Touch is the primary medium through which humans interact with the environment. Currently, tactile learning mainly focuses on image-level pretraining or alignment. However, tactile signals correspond to local object contact, while research into scale alignment and holographic matching remains limited and proper datasets and benchmarks also lack. To bridge this gap, we first construct a data collec...

OpenMedReason: Scientific Reasoning Supervision for Medical Vision-Language Models

High-stakes clinical use of large vision-language models (LVLMs) requires reasoning that is grounded in visual evidence and clinical knowledge, not just correct final answers. We introduce OpenMedReason, a large-scale, open multimodal medical reasoning corpus comprising approximately 450K image-question-answer instances whose reasoning traces are primarily derived from curated biomedical, human-au...

Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models

Vision-language models (VLMs) project images into hundreds to thousands of visual tokens, making decoder inference expensive in both attention computa...

Vision-Assisted Foundation Model for Solving Multi-Task Vehicle Routing Problems

Multi-task vehicle routing problems play a critical role in enhancing efficiency across various industries and service sectors. These problems consist...

Beyond Model Size: Probing the Gaps in Visual in-Context Learning by Training a Tiny Model

Visual in-Context Learning (VICL) aims at making progress towards adaptive vision models, that can -- based on a few examples -- adapt to a new task a...

Quo Vadis, Visual In-Context Learning? A Unified Benchmark Across Domains and Tasks

Visual in-context learning has been proposed as a pathway towards dynamic models that can generate predictions based on a provided context and thereby...

GenEyePose: Patient-Free, Knowledge-Based Saccadic Eye Movement Modeling for Digital Neurophysiologic Biomarker Development

Eye movements, including saccades, are widely regarded as highly sensitive and objective biomarkers of neurophysiologic states. Detecting saccadic sig...

Late-Layer Fusion is Enough: Dual-Path Vision Token Routing for Multimodal Large Language Models under Visual Saturation

Multimodal large language models (MLLMs) commonly inherit the deep, symmetric Transformer backbone designed for unimodal text modeling, and apply the ...

DiffSight-Former: Modeling Structural Differences and Temporal Dynamics for Glaucoma Progression Prediction

Glaucoma is a leading cause of irreversible blindness worldwide, and early detection from fundus images is critical for effective disease management. ...

MAGIS: Evidence-Based Multi-Agent Reasoning for Interpretable Strabismus Clinical Decision-Making

Strabismus is a common ocular disorder that requires fine-grained subtype diagnosis for individualized treatment planning. However, existing deep lear...

CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning

Image and video captioning are fundamental tasks that bridge the visual and linguistic domains, playing a critical role in pre-training Large Vision-L...

Muon Learns More Robust and Transferable Features than Adam

Muon has recently emerged as a state-of-the-art optimizer for pretraining Large Language Models (LLMs) and vision classifiers. Despite its efficiency ...

GenEyePose: Patient-Free, Knowledge-Based Saccadic Eye Movement Modeling for Digital Neurophysiologic Biomarker Development

Eye movements, including saccades, are widely regarded as highly sensitive and objective biomarkers of neurophysiologic states. Detecting saccadic sig...

End-to-End Optimization of Incoherent Imaging for Classification Under Detector-Limited Readout

End-to-end co-optimization of optical front-ends (e.g. metasurfaces) and neural network back-ends has been widely applied to imaging tasks, yet a form...

CheXanatomy: Anatomy-Aware Vision-Language Modeling for Chest Radiographs

Vision-language models (VLMs) pretrained on large-scale image-text pairs demonstrate strong image-level understanding, but are primarily optimized for...

TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding

Chain-of-thought (CoT) reasoning has proven effective for enhancing problem-solving in large language models. However, when applied to multimodal LLMs...

Learnable Token Sparsification for Efficient Gigapixel Whole Slide Image Reasoning

The processing of gigapixel whole slide images within vision language models faces a major difficulty due to an excessive number of visual tokens. Exi...

Thinking Without Images: Internalizing Visual Manipulation with On-Policy Self-Distillation

''Thinking with Images'' has emerged as an effective paradigm for fine-grained visual reasoning: by explicitly zooming into relevant regions and reaso...

CSFlow: Aligning Flow Matching with Human Contrast Sensitivity

We introduce Contrast Sensitive Flow (CSFlow), a weighting scheme that connects the human eye's Contrast Sensitivity Function (CSF) to the iterative d...

Noise-Aware Visual Representation Learning for Medical Visual Question Answering

Medical visual question answering (Med-VQA) has strong potential for clinical decision support by enabling AI models to interpret medical images and a...