Towards a configurable and non-hierarchical search space for NAS.

Neural Architecture Search (NAS) outperforms handcrafted Neural Network (NN) design. However, current NAS methods generally use hard-coded search spaces, and predefined hierarchical architectures. As a consequence, adapting them to a new problem can be cumbersome, and it is hard to know which of the NAS algorithm or the predefined hierarchical structure impacts performance the most.

From Near-Sensor to In-Sensor: A State-of-the-Art Review of Embedded AI Vision Systems.

In modern cyber-physical systems, the integration of AI into vision pipelines is now a standard practice for applications ranging from autonomous vehicles to mobile devices. Traditional AI integration often relies on cloud-based processing, which faces challenges such as data access bottlenecks, increased latency, and high power consumption. This article reviews embedded AI vision systems, examining the diverse landscape of near-sensor and in-sensor processing architectures that incorporate convolutional neural networks.

Pegylated liposome encapsulating docetaxel using microfluidic mixing technique: Process optimization and results in breast cancer models.

The development of nanoparticles could help to improve the efficacy/toxicity balance of drugs. This project aimed to develop liposomes and immunoliposomes using microfluidic mixing technology.Various formulation tests were carried out to obtain liposomes that met the established specifications.

Overcoming immuno-resistance by rescheduling anti-VEGF/cytotoxics/anti-PD-1 combination in lung cancer model.

Many tumors are refractory to immune checkpoint inhibitors, but their combination with cytotoxics is expected to improve sensitivity. Understanding how and when cytotoxics best re-stimulate tumor immunity could help overcome resistance to immune checkpoint inhibitors. studies were performed in C57BL/6 mice grafted with immune-refractory LL/2 lung cancer model.

Cytidine deaminase status as a marker of response to azacytidine treatment in MDS and AML patients.

Azacitidine (Aza) is a mainstay of treatment for patients with acute myeloid leukaemia (AML) ineligible for induction chemotherapy and other high-risk myelodysplastic syndromes (MDS). Only half of patients respond, and almost all will eventually relapse. There are no predictive markers of response to Aza.