96 citations · 464 across the 30 of their papers we have counts for
8 papers · 1 filter
CheXTemporal: A Dataset for Temporally-Grounded Reasoning in Chest Radiography
Eva Prakash, Yunhe Gao, Chong Wang +10
Chest radiograph interpretation requires temporal reasoning over prior and current studies, yet most vision-language models are trained on static image-report pairs and lack explic…
CheXmix: Unified Generative Pretraining for Vision Language Models in Medical Imaging
Ashwin Kumar, Robbie Holland, Corey Barrett +8
Recent medical multimodal foundation models are built as multimodal LLMs (MLLMs) by connecting a CLIP-pretrained vision encoder to an LLM using LLaVA-style finetuning. This two-sta…
A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation
Yabin Zhang, Chong Wang, Yunhe Gao +19
Chest X-rays (CXRs) are among the most frequently performed imaging examinations worldwide, yet rising imaging volumes increase radiologist workload and the risk of diagnostic erro…
Activation Matters: Test-time Activated Negative Labels for OOD Detection with Vision-Language Models
Yabin Zhang, Maya Varma, Yunhe Gao +4
Out-of-distribution (OOD) detection aims to identify samples that deviate from in-distribution (ID). One popular pipeline addresses this by introducing negative labels distant from…
Learning Generalizable 3D Medical Image Representations from Mask-Guided Self-Supervision
Yunhe Gao, Yabin Zhang, Chong Wang +5
Foundation models have transformed vision and language by learning general-purpose representations from large-scale unlabeled data, yet 3D medical imaging lacks analogous approache…
A data- and compute-efficient chest X-ray foundation model beyond aggressive scaling
Chong Wang, Yabin Zhang, Yunhe Gao +9
Foundation models for medical imaging are typically pretrained on increasingly large datasets, following a "scale-at-all-costs" paradigm. However, this strategy faces two critical…
Unpaired Image-to-Image Translation via a Self-Supervised Semantic Bridge
Jiaming Liu, Felix Petersen, Yunhe Gao +6
Adversarial diffusion and diffusion-inversion methods have advanced unpaired image-to-image translation, but each faces key limitations. Adversarial approaches require target-domai…
LUCID-SAE: Learning Unified Vision-Language Sparse Codes for Interpretable Concept Discovery
Difei Gu, Yunhe Gao, Gerasimos Chatzoudis +6
Sparse autoencoders (SAEs) offer a natural path toward comparable explanations across different representation spaces. However, current SAEs are trained per modality, producing dic…