📅 2026-04-16
5 items
🕐 Updated 2026-04-16 07:51
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, a...
keyword
多模态
🕐 Updated 2026-04-16 07:50
[ ACL 2026 ORAL ] MedFocusLeak is a transferable black-box multimodal adversarial attack that injects imperceptible pert...
keyword
多模态
🕐 Updated 2026-04-16 07:28
Reproduce and evaluate the OpenVLA vision-language-action model on LIBERO tasks with full setup, deployment, and perform...
keyword
多模态
🕐 Updated 2026-04-16 07:27
Provide model engineering skills for training, tuning, and modifying large language and vision models using PyTorch, Hug...
keyword
多模态
🕐 Updated 2026-04-16 06:40
🩺 Analyze skin lesions with an AI system that combines OpenCV, Vision Language Models, and literature retrieval for p...
keyword
多模态