arXiv:2507.22095v4 Announce Type: replace Abstract: We consider fully connected and feedforward deep neural networks with dependent and possibly heavy-tailed weights, as introduced in Lee et al. 2023, to address limitations of the standard Gaussian prior. It has been proved in Lee et al. 2023 that, as the number of nodes in the hidden layers grows large, according to a sequential and ordered limit, the law of the output converges weakly to a Gaussian mixture. Among our results, we […]

Ver mais

Data-independent acquisition mass spectrometry (DIA-MS) has established itself as a cornerstone of proteomic profiling and large-scale systems biology, offering unparalleled depth and reproducibility. Current DIA analysis frameworks, however, require semi-supervised training within each run for peptide-spectrum match (PSM) re-scoring. This approach is prone to overfitting and lacks generalizability across diverse species and experimental conditions. Here, we present DIA-CLIP, a pre-trained model shifting the DIA analysis paradigm from semi-supervised training to universal cross-modal representation learning. By integrating dual-encoder contrastive […]

Ver mais

arXiv:2603.01971v1 Announce Type: new Abstract: Modern machine learning models can be accurate on average yet still make mistakes that dominate deployment cost. We introduce Locus, a distribution-free wrapper that produces a per-input loss-scale reliability score for a fixed prediction function. Rather than quantifying uncertainty about the label, Locus models the realized loss of the prediction function using any engine that outputs a predictive distribution for the loss given an input. A simple split-calibration step turns this function into […]

Ver mais

arXiv:2602.00979v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable potential for automatic short answer grading (ASAG), significantly boosting student assessment efficiency and scalability in educational scenarios. However, their vulnerability to adversarial manipulation raises critical concerns about automatic grading fairness and reliability. In this paper, we introduce GradingAttack, a fine-grained adversarial attack framework that systematically evaluates the vulnerability of LLM based ASAG models. Specifically, we align general-purpose attack methods with the specific objectives of ASAG by […]

Ver mais

AI in medtech effectively helps with medical diagnosis and treatment plan development, drug discovery, and gene modification. 86% of healthcare providers and life science companies were harnessing the power of artificial intelligence in their work already 5 years ago. Medtech conferences with a focus on AI have become essential platforms for collaboration, knowledge exchange, and the unveiling of developments. In this article, we will share 8 events not to miss if you work in the medtech or AI […]

Ver mais

Semantic communication promises task-aligned transmission but must reconcile semantic fidelity with stringent latency guarantees in immersive and safety-critical services. This paper introduces a time-constrained human-in-the-loop reinforcement learning (TC-HITL-RL) framework that embeds human feedback, semantic utility, and latency control within a semantic-aware Open radio access network (RAN) architecture. We formulate semantic adaptation driven by human feedback as a constrained Markov decision process (CMDP) whose state captures semantic quality, human preferences, queue slack, and channel dynamics, and solve it via […]

Ver mais

arXiv:2601.21170v2 Announce Type: replace-cross Abstract: Emergent phenomena — onset of epileptic seizures, sudden customer churn, or pandemic outbreaks — often arise from hidden causal interactions in complex systems. We propose a machine learning method for their early detection that addresses a core challenge: unveiling and harnessing a system’s latent causal structure despite the data-generating process being unknown and partially observed. The method learns an optimal feature representation from a one-parameter family of estimators — powers of the empirical […]

Ver mais

Checking if a model is valid is pretty an automatic behavior at this point. Whenever a request expects a model, we need to make sure that the validation is good, and we use ModelState.IsValid for that. But that becomes boring, most of the time (if not always) we redirect to the same page, another page or return a bad request in case of an API.

Ver mais

arXiv:2601.22231v1 Announce Type: new Abstract: This paper revisits the role of positional embeddings (PEs) within vision transformers (ViTs) from a geometric perspective. We show that PEs are not mere token indices but effectively function as geometric priors that shape the spatial structure of the representation. We introduce token-level diagnostics that measure how multi-view geometric consistency in ViT representation depends on consitent PEs. Through extensive experiments on 14 foundation ViT models, we reveal how PEs influence multi-view geometry and […]

Ver mais