Related papers: Data Feedback Loops: Model-driven Amplification of…

The real-time segmentation of drivable areas plays a vital role in accomplishing autonomous perception in cars. Recently there have been some rapid strides in the development of image segmentation models using deep learning. However, most…

Recent language models achieve impressive results in tasks involving complex multistep reasoning, but scaling these capabilities further traditionally requires expensive collection of more annotated data. In this work, we explore the…

World models aim to improve robotic decision making by predicting the consequences of actions. However, in practice, their predictions often become unreliable once the robot encounters states outside the training distribution, limiting…

Extensive numerical evidence shows that the assimilation of observations has a stabilizing effect on unstable dynamics, in numerical weather prediction and elsewhere. In this paper, we apply mathematically rigorous methods to showing why…

While biological vision systems rely heavily on feedback connections to iteratively refine perception, most artificial neural networks remain purely feedforward, processing input in a single static pass. In this work, we propose a…

Polarization issue is generally subject to ideological polarization and affective polarization. In particular, affective polarization usually accelerates the polarization process and transform social interactions into a zero-sum game. Yet,…

Data attribution methods trace model behavior back to its training dataset, offering an effective approach to better understand ''black-box'' neural networks. While prior research has established quantifiable links between model output and…

Automatic unreliable news detection is a research problem with great potential impact. Recently, several papers have shown promising results on large-scale news datasets with models that only use the article itself without resorting to any…

We tackle the problem of providing closed-loop stability guarantees with a scalable data-driven design. We combine virtual reference feedback tuning with dissipativity constraints on the controller for closed-loop stability. The constraints…

Understanding how sustainable behaviors spread within heterogeneous societies requires the integration of behavioral data, social influence mechanisms, and structured approaches to control. In this paper, we propose a data-driven…

The flow of information reaching us via the online media platforms is optimized not by the information content or relevance but by popularity and proximity to the target. This is typically performed in order to maximise platform usage. As a…

Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained…

Because imitation learning relies on human demonstrations in hard-to-simulate settings, the inclusion of force control in this method has resulted in a shortage of training data, even with a simple change in speed. Although the field of…

Large language models often achieve strong benchmark gains without corresponding improvements in broader capability. We hypothesize that this discrepancy arises from differences in training regimes induced by data distribution. To…

Data-Augmentation (DA) is known to improve performance across tasks and datasets. We propose a method to theoretically analyze the effect of DA and study questions such as: how many augmented samples are needed to correctly estimate the…

Many recent advances in natural language generation have been fueled by training large language models on internet-scale data. However, this paradigm can lead to models that generate toxic, inaccurate, and unhelpful content, and automatic…

Data corruption, including missing and noisy data, poses significant challenges in real-world machine learning. This study investigates the effects of data corruption on model performance and explores strategies to mitigate these effects…

Deep generative models have made tremendous progress in modeling complex data, often exhibiting generation quality that surpasses a typical human's ability to discern the authenticity of samples. Undeniably, a key driver of this success is…

Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful estimates of their predictive {\em uncertainty}. Quantifying…

Deep learning approaches are increasingly used to tackle forecasting tasks involving datasets with multiple univariate time series. A key factor in the successful application of these methods is a large enough training sample size, which is…