Nous utilisons des témoins pour analyser le trafic et l’utilisation de notre site web, afin de personnaliser votre expérience. Vous pouvez désactiver ces technologies à tout moment, mais cela peut restreindre certaines fonctionnalités du site. Consultez notre Politique de protection de la vie privée pour en savoir plus.
Paramètre des cookies
Vous pouvez activer et désactiver les types de cookies que vous souhaitez accepter. Cependant certains choix que vous ferez pourraient affecter les services proposés sur nos sites (ex : suggestions, annonces personnalisées, etc.).
Cookies essentiels
Ces cookies sont nécessaires au fonctionnement du site et ne peuvent être désactivés. (Toujours actif)
Cookies analyse
Acceptez-vous l'utilisation de cookies pour mesurer l'audience de nos sites ?
Multimedia Player
Acceptez-vous l'utilisation de cookies pour afficher et vous permettre de regarder les contenus vidéo hébergés par nos partenaires (YouTube, etc.) ?
Publications
Alcohol related hepatitis in intensive care units: clinical and biological spectrum and mortality risk factors: a multicenter retrospective study
Background Alcohol related hepatitis is responsible for high morbidity and mortality, but little is known about the management of patients w… (voir plus)ith hepatitis specifically in intensive care units (ICU). Methods Retrospective study including patients with alcohol related hepatitis hospitalized in 9 French ICUs (2006–2017). Alcohol related hepatitis was defined histologically or by an association of clinical and biological criteria according to current guidelines. Results 187 patients (median age: 53 [43–60]; male: 69%) were included. A liver biopsy was performed in 51% of cases. Patients were admitted for impaired consciousness (71%), sepsis (64%), shock (44%), respiratory failure (37%). At admission, median SOFA and MELD scores were 10 [7–13] and 31 [26–40] respectively. 63% of patients received invasive mechanical ventilation, 62% vasopressors, and 36% renal replacement therapy. 66% of patients received corticosteroids, and liver transplantation was performed in 16 patients (8.5%). ICU and in-hospital mortality were 37% and 53% respectively. By multivariate analysis, ICU mortality was associated with SOFA score (without total bilirubin) (SHR 1.08 [1.02–1.14] per one-point increase), arterial lactate (SHR 1.08 [1.03–1.13] per 1 mmol/L) and MELD score (SHR 1.09 [1.04–1.14] per 1 point), while employment was associated with increased survival (HR 0.49 [0.28–0.86]). After propensity score weighting, the use of corticosteroids did not affect ICU mortality in the overall population but had a beneficial effect in the subgroup of patients with histological proof. Patient prognosis was also better in responders assessed by Lille score at day 7 (OR 6.67 [2.44–20.15], p 0.001). Conclusion Alcohol related hepatitis is a severe condition leading to high mortality in ICU patients. Severity of organ failure
AI progress is creating a growing range of risks and opportunities, but it is often unclear how they should be navigated. In many cases, the… (voir plus) barriers and uncertainties faced are at least partly technical. Technical AI governance, referring to technical analysis and tools for supporting the effective governance of AI, seeks to address such challenges. It can help to (a) identify areas where intervention is needed, (b) identify and assess the efficacy of potential governance actions, and (c) enhance governance options by designing mechanisms for enforcement, incentivization, or compliance. In this paper, we explain what technical AI governance is, why it is important, and present a taxonomy and incomplete catalog of its open problems. This paper is intended as a resource for technical researchers or research funders looking to contribute to AI governance.
Generating novel active molecules for a given protein is an extremely challenging task for generative models that requires an understanding … (voir plus)of the complex physical interactions between the molecule and its environment. In this paper, we present a novel generative model, BindGPT which uses a conceptually simple but powerful approach to create 3D molecules within the protein's binding site. Our model produces molecular graphs and conformations jointly, eliminating the need for an extra graph reconstruction step. We pretrain BindGPT on a large-scale dataset and fine-tune it with reinforcement learning using scores from external simulation software. We demonstrate how a single pretrained language model can serve at the same time as a 3D molecular generative model, conformer generator conditioned on the molecular graph, and a pocket-conditioned 3D molecule generator. Notably, the model does not make any representational equivariance assumptions about the domain of generation. We show how such simple conceptual approach combined with pretraining and scaling can perform on par or better than the current best specialized diffusion models, language models, and graph neural networks while being two orders of magnitude cheaper to sample.
2025-04-11
Proceedings of the AAAI Conference on Artificial Intelligence (publié)
Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference. When… (voir plus) faced with challenging shifts, most methods collapse and perform worse than the original pretrained model. In this paper, we find that not all layers are equally receptive to the adaptation, and the layers with the most misaligned gradients often cause performance degradation. To address this, we propose GALA, a novel layer selection criterion to identify the most beneficial updates to perform during test time adaptation. This criterion can also filter out unreliable samples with noisy gradients. Its simplicity allows seamless integration with existing TTA loss functions, thereby preventing degradation and focusing adaptation on the most trainable layers. This approach also helps to regularize adaptation to preserve the pretrained features, which are crucial for handling unseen domains. Through extensive experiments, we demonstrate that the proposed layer selection framework improves the performance of existing TTA approaches across multiple datasets, domain shifts, model architectures, and TTA losses.
2025-04-11
Proceedings of the AAAI Conference on Artificial Intelligence (publié)
