Related papers: Foundation Priors
Human emotion synthesis is a crucial aspect of affective computing. It involves using computational methods to mimic and convey human emotions through various modalities, with the goal of enabling more natural and effective human-computer…
Confirmation bias is a cognitive bias that adversely affects management decisions, and mathematical modelling is an aid to its detailed understanding. Bias in opinion update about the value of a parameter is modelled here assuming that…
Synthetic control is a causal inference tool used to estimate the treatment effects of an intervention by creating synthetic counterfactual data. This approach combines measurements from other similar observations (i.e., donor pool ) to…
Multimodal foundation models offer promising advancements for enhancing driving perception systems, but their high computational and financial costs pose challenges. We develop a method that leverages foundation models to refine predictions…
In science, we are interested not only in forecasting but also in understanding how predictions are made, specifically what the interpretable underlying model looks like. Data-driven machine learning technology can significantly streamline…
This article was motivated by the discovery of a potential new foundation for mainstream mathematics. The goals are to clarify the relationships between primitives, foundations, and deductive practice; to understand how to determine what…
We introduce Prior-Fitted Functional Flows, a generative foundation model for pharmacokinetics that enables zero-shot population synthesis and individual forecasting without manual parameter tuning. We learn functional vector fields,…
We put forth a critical theoretical framework for analyzing generative models both descriptively and normatively. Our thesis is that generative models automate the production not only of intellectual labor or intelligence, but of a broader…
Many data-driven decision problems are formulated using a nominal distribution estimated from historical data, while performance is ultimately determined by a deployment distribution that may be shifted, context-dependent, partially…
In order to improve forecasts, a decisionmaker often combines probabilities given by various sources, such as human experts and machine learning classifiers. When few training data are available, aggregation can be improved by incorporating…
Synthetic data generators, when trained using privacy-preserving techniques like differential privacy, promise to produce synthetic data with formal privacy guarantees, facilitating the sharing of sensitive data. However, it is crucial to…
Large language models sometimes produce structured, first-person descriptions that explicitly reference awareness or subjective experience. To better understand this behavior, we investigate one theoretically motivated condition under which…
Foundation models trained on web-scale data have revolutionized robotics, but their application to low-level control remains largely limited to behavioral cloning. Drawing inspiration from the success of the reinforcement learning stage in…
We propose a novel approach to perform approximate Bayesian inference in complex models such as Bayesian neural networks. The approach is more scalable to large data than Markov Chain Monte Carlo, it embraces more expressive models than…
The specification of prior distributions is fundamental in Bayesian inference, yet it remains a significant bottleneck. The prior elicitation process is often a manual, subjective, and unscalable task. We propose a novel framework which…
Real-world data often exhibits bias, imbalance, and privacy risks. Synthetic datasets have emerged to address these issues. This paradigm relies on generative AI models to generate unbiased, privacy-preserving data while maintaining…
Progress in generative modelling, especially generative adversarial networks, have made it possible to efficiently synthesize and alter media at scale. Malicious individuals now rely on these machine-generated media, or deepfakes, to…
Foundation models are large-scale machine learning models that are pre-trained on massive amounts of data and can be adapted for various downstream tasks. They have been extensively applied to tasks in Natural Language Processing and…
People naturally bring their prior beliefs to bear on how they interpret the new information, yet few formal models exist for accounting for the influence of users' prior beliefs in interactions with data presentations like visualizations.…
Using instruments comprising ordered responses to items are ubiquitous for studying many constructs of interest. However, using such an item response format may lead to items with response categories infrequently endorsed or unendorsed…