Related papers: Important Molecular Descriptors Selection Using Se…

Selecting a suitable pretraining dataset is crucial for both general-domain (e.g., GPT-3) and domain-specific (e.g., Codex) language models (LMs). We formalize this problem as selecting a subset of a large raw unlabeled dataset to match a…

Foundation models and their checkpoints have significantly advanced deep learning, boosting performance across various applications. However, fine-tuned models often struggle outside their specific domains and exhibit considerable…

Language Models (LMs) pre-trained with self-supervision on large text corpora have become the default starting point for developing models for various NLP tasks. Once the pre-training corpus has been assembled, all data samples in the…

Many studies regarding the vasculature of biological tissues involve the segmentation of the blood vessels in a sample followed by the creation of a graph structure to model the vasculature. The graph is then used to extract relevant…

Estimating causal effects from observational data is challenging due to selection bias, which leads to imbalanced covariate distributions across treatment groups. Propensity score-based weighting methods are widely used to address this…

Accurate tumour segmentation is vital for various targeted diagnostic and therapeutic procedures for cancer, e.g., planning biopsies or tumour ablations. Manual delineation is extremely labour-intensive, requiring substantial expert time.…

The uncertainty estimation is critical in real-world decision making applications, especially when distributional shift between the training and test data are prevalent. Many calibration methods in the literature have been proposed to…

We consider the problem of selecting confounders for adjustment from a potentially large set of covariates, when estimating a causal effect. Recently, the high-dimensional Propensity Score (hdPS) method was developed for this task; hdPS…

The goal in network state prediction (NSP) is to classify the global state (label) associated with features embedded in a graph. This graph structure encoding feature relationships is the key distinctive aspect of NSP compared to classical…

Tabular biomedical data is often high-dimensional but with a very small number of samples. Although recent work showed that well-regularised simple neural networks could outperform more sophisticated architectures on tabular data, they are…

Large Language Model (LLM) agents can increasingly automate complex reasoning through Test-Time Scaling (TTS), iterative refinement guided by reward signals. However, many real-world tasks involve multi-stage pipeline whose final outcomes…

Stochastic control-flow models (SCFMs) are a class of generative models that involve branching on choices from discrete random variables. Amortized gradient-based learning of SCFMs is challenging as most approaches targeting discrete…

The presence of tertiary lymphoid structures (TLSs) on pancreatic pathological images is an important prognostic indicator of pancreatic tumors. Therefore, TLSs detection on pancreatic pathological images plays a crucial role in diagnosis…

Large-scale association analysis between multivariate responses and predictors is of great practical importance, as exemplified by modern business applications including social media marketing and crisis management. Despite the rapid…

In high-energy particle physics, complex Monte Carlo (MC) simulations are needed to compare theory predictions to measurable quantities. Many and large MC samples are needed to be generated to take into account all the systematics.…

Enabling efficient and accurate deep neural network (DNN) inference on microcontrollers is non-trivial due to the constrained on-chip resources. Current methodologies primarily focus on compressing larger models yet at the expense of model…

Background: CT imaging is vital for lung cancer management, offering detailed visualization for AI-based prognosis. However, supervised learning SL models require large labeled datasets, limiting their real-world application in settings…

Statistical model checking avoids the exponential growth of states associated with probabilistic model checking by estimating properties from multiple executions of a system and by giving results within confidence bounds. Rare properties…

Evaluating LLMs and text-to-image models is a computationally intensive task often overlooked. Efficient evaluation is crucial for understanding the diverse capabilities of these models and enabling comparisons across a growing number of…

Effective data selection is essential for pretraining large language models (LLMs), enhancing efficiency and improving generalization to downstream tasks. However, existing approaches often require leveraging external pretrained models,…