Yanda Meng

Integration of clinical data with scanned ECGs using deep learning methods for stroke risk prediction in Indian patients with atrial fibrillation: evidence from the KERALA-AF study #Afib @LHCHFT @LivHPartners sciencedirect.com/science/articl…

Please join us in welcoming @yanda_meng to KAUST as Assistant Professor of Bioengineering. His research advances AI for healthcare by developing adaptive, trustworthy computational systems that support biomedical discovery and clinical decision making. By combining machine learning with real clinical needs, his work contributes to BESE’s focus on research that improves human health and strengthens the region’s growing capability in medical innovation. Learn more about Prof. Meng: bese.kaust.edu.sa/news/detail/20… #Bioengineering #AIinHealthcare #MachineLearning #BiomedicalAI #MedicalImaging #KAUSTResearch

🔥Check out the hy-FSD method for better 3D visual quality! The authors have developed an image-to-3D generation pipeline to create high-quality 3D objects within one minute. 🔗link.springer.com/article/10.100… #Diffusionmodel #AI @SpringerEng

@Kylelauersen @KAUST_News @KAUST_BESE Huge Congrats Kyle!

Thrilled to announce I have been promoted to Associate Professor commencing July 1st. The SSB Lab will continue to innovate in algal biotechnology @KAUST_News @KAUST_BESE ssb.kaust.edu.sa

#ArtificialInteligence -based classification of cardiac autonomic neuropathy from retinal fundus images in patients with #diabetes: The Silesia Diabetes Heart Study @LHCHFT @LJMU_Health @LivHPartners cardiab.biomedcentral.com/articles/10.11…

📢 Fully Funded PhD Opportunity - findaphd.com/phds/project/u… A joint PhD studentship at @exetercompsci @UniExeterIDSAI with @LiverpoolCCS #PhD #MachineLearning #AF #biostatistics

I am hiring a postdoctoral fellow to work in the Harvard Ophthalmology AI Lab. The postdoctoral fellow will develop machine learning models to improve the diagnosis and prognosis of eye diseases. Please check the link below for more information. ophai.hms.harvard.edu/news/postdocto…

📢 Fully Funded PhD Opportunity - findaphd.com/phds/project/a… A joint PhD studentship at @exetercompsci @UniExeterIDSAI with @LiverpoolCCS #PhD #AI #AF #ECG #LLM

Computer Vision conference's acceptance criteria these days: #CVPR2024 #eccc2024 #AI #ComputerVision

A good opportunity to work with Zeyu and his team!

Let's not forget the positive side.

The deadline is extended to 3rd April 2024.

The Impact of Reasoning Step Length on Large Language Models paper page: huggingface.co/papers/2401.04… Chain of Thought (CoT) is significant in improving the reasoning abilities of large language models (LLMs). However, the correlation between the effectiveness of CoT and the length of reasoning steps in prompts remains largely unknown. To shed light on this, we have conducted several empirical experiments to explore the relations. Specifically, we design experiments that expand and compress the rationale reasoning steps within CoT demonstrations, while keeping all other factors constant. We have the following key findings. First, the results indicate that lengthening the reasoning steps in prompts, even without adding new information into the prompt, considerably enhances LLMs' reasoning abilities across multiple datasets. Alternatively, shortening the reasoning steps, even while preserving the key information, significantly diminishes the reasoning abilities of models. This finding highlights the importance of the number of steps in CoT prompts and provides practical guidance to make better use of LLMs' potential in complex problem-solving scenarios. Second, we also investigated the relationship between the performance of CoT and the rationales used in demonstrations. Surprisingly, the result shows that even incorrect rationales can yield favorable outcomes if they maintain the requisite length of inference. Third, we observed that the advantages of increasing reasoning steps are task-dependent: simpler tasks require fewer steps, whereas complex tasks gain significantly from longer inference sequences.

Fully funded PhD available at @LivUni @LiverpoolCCS @LivuniILCaMS. If you're interested in #digitaltwins and #insilico #clinicaltrials please get in touch to apply! Do forward on to any students who may be interested. shorturl.at/eghMQ

Scientists from @livuni & @ManMetUni have been awarded £1.4m to create an early test for Diabetic Peripheral Neuropathy (DPN), a complication caused by diabetes and which costs the NHS billions. Read more➡️news.liverpool.ac.uk/2023/06/07/1-4… @livunihls @LivuniILCaMS @livuniresthemes

Our work has been accepted by the top AI/Medical Image Analysis Journal. We propose a weakly/semi supervised method for optic disc and cup segmentation and glaucoma diagnosis with fundus images. Thanks to all the co-authors! @LivuniILCaMS @StPaulsNews

@vision_sharib @UniversityLeeds Congrats!

I am very thankful to all the colleagues and mentors at Oxford. Great learning experience and wonderful collaborators. I will be establishing my group at the @UniversityLeeds. If you are interested to collaborate/work with me, please contact me. Excited to start this journey!

Congrats!! Prof Xiaowei Huang @xiaoweih 🎉🎉

Congrats!! Prof Yalin Zheng 🎉🎉

Proud that our paper made the front cover of the @DiabetologiaJnl March issue! Images include corneal confocal microscopy #CCM images and images of the attribution-based explainability methods we used to help explain the #AI algorithm @AlamUazman @GroupENA @LivuniILCaMS