arXiv AI By Rishabh Jha, Amrita Singh, Prashanna Chudal

CADRE: Stable, Parameter Efficient Adaptation of Medical Vision Language Models with Bounded Forgetting and Prior Drift

Read the original on arXiv AI →

arXiv:2606. 23487v2 Announce Type: replace Abstract: Medical vision-language models (VLMs) such as BiomedCLIP generalize broadly, but adapting them to a clinical service is as much a safety problem as an accuracy one.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computer Vision
5d ago

What Do Medical Vision-Language Models Learn in Radiology? Transfer, Alignment, and Source-Proxy Leakage Under Distribution Shift

The paper investigates how medical vision‑language models (VLMs) behave when faced with distribution shifts such as changes in acquisition domain, supervision, or evaluation protocol. Using datasets like NIH ChestXray14, CheXpert, PadChest, and OpenI, the authors isolate cross‑dataset visual transfer, evaluate multimodal alignment, and quantify source‑proxy leakage in frozen embeddings. They find that self‑supervised visual initialization improves transfer, adversarial adaptation is only marginally helpful, and that multimodal retrieval performance drops under external stress tests while source‑proxy information remains recoverable, highlighting hidden failure modes in medical VLMs.

By Ayoub Louaye Bouaziz, Lokmane Chebouba, Yassine Himeur
arXiv AI
Aug 11

LoRSA: Toward Generalizable Parameter-Efficient Fine-Tuning for Biomedical Downstream Tasks

arXiv:2608. 07749v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning enables the adaptation of vision foundation models to biomedical tasks under limited computational resources, but a single low-rank update can constrain all task-specific changes to one narrow parameter subspace.

By Saed Moradi, Benyamin Ghojogh, M. Hadi Sepanj, Yimin Yang, Ashirbani Saha
arXiv AI
Jul 15

Continual Learning with Elastic Regularization and Synthetic Replay for Federated MLLM Fine-Tuning

arXiv:2607. 12112v1 Announce Type: cross Abstract: Federated fine-tuning of Multimodal Large Language Models (MLLMs) across distributed networks enables privacy-sensitive adaptation to evolving data streams, yet a fundamental obstacle prevents robust deployment in dynamic environments: catastrophic forgetting, wherein sequential task updates erase previously acquired knowledge across visual, linguistic, and cross-modal representations.

By Jing Liu, Chenxuanyin Zou, Jiayang Ren, Gaoyun Fang, Chengfang Li, Yan Wang, Zhenchao Ma, Bo Hu