Related papers: Leveraging Foundation Models for Calibration-Free …
Electroencephalography (EEG) foundation models hold significant promise for universal Brain-Computer Interfaces (BCIs). However, existing approaches often rely on end-to-end fine-tuning and exhibit limited efficacy under frozen-probing…
Vision-language models (VLM) have demonstrated impressive performance in image recognition by leveraging self-supervised training on large datasets. Their performance can be further improved by adapting to the test sample using test-time…
One approach, for understanding human brain functioning, is to analyze the changes in the brain while performing cognitive tasks. Towards this, Functional Magnetic Resonance (fMR) images of subjects performing well-defined tasks are widely…
We study statistical calibration, i.e., adjusting features of a computational model that are not observable or controllable in its associated physical system. We focus on functional calibration, which arises in many manufacturing processes…
In likelihood-free settings where likelihood evaluations are intractable, approximate Bayesian computation (ABC) addresses the formidable inference task to discover plausible parameters of simulation programs that explain the observations.…
Large language models (LLMs) are increasingly deployed in decision-making tasks, where not only accuracy but also reliable confidence estimates are essential. Well-calibrated confidence enables downstream systems to decide when to trust a…
We propose a probabilistic framework for performing simultaneous estimation of source structure and fringe-fitting parameters in Very Long Baseline Interferometry (VLBI) observations. As a first step, we demonstrate this technique through…
Foundation models are deep neural networks (such as GPT-5, Gemini~3, and Opus~4) trained on large datasets that can perform diverse downstream tasks -- text and code generation, question answering, summarization, image classification, and…
Brain-computer interfaces (BCIs) and their associated technologies have the potential to shape future forms of communication, control, and security. Specifically, the steady-state visual evoked potential (SSVEP) based BCIs have the…
Visual-inertial systems have been widely studied and applied in the last two decades (from the early 2000s to the present), mainly due to their low cost and power consumption, small footprint, and high availability. Such a trend…
Confidence calibration of classification models is a technique to estimate the true posterior probability of the predicted class, which is critical for ensuring reliable decision-making in practical applications. Existing confidence…
To quantify how well theoretical predictions of structural ensembles agree with experimental measurements, we depend on the accuracy of forward models. These models are computational frameworks that generate observable quantities from…
There is substantial interest in developing artificial intelligence systems to support radiologists across tasks ranging from segmentation to report generation. Existing computed tomography (CT) foundation models have largely focused on…
To enhance Large Language Models' (LLMs) reliability, calibration is essential -- the model's assessed confidence scores should align with the actual likelihood of its responses being correct. However, current confidence elicitation methods…
Brain-computer interface (BCI) based on steady-state visual evoked potentials (SSVEP) is a popular paradigm for its simplicity and high information transfer rate (ITR). Accurate and fast SSVEP decoding is crucial for reliable BCI…
Recent advancements in artificial intelligence (AI), particularly foundation models (FMs), have revolutionized medical image analysis, demonstrating strong zero- and few-shot performance across diverse medical imaging tasks, from…
Trustworthy deployment of deep learning medical imaging models into real-world clinical practice requires that they be calibrated. However, models that are well calibrated overall can still be poorly calibrated for a sub-population,…
The prevalence of online learning poses a vital challenge in real-time monitoring of students' concentration. Traditional methods such as questionnaire assessments require manual intervention, and webcam-based monitoring fails to provide…
Functional connectivity (FC) derived from resting-state fMRI plays a critical role in personalized predictions such as age and cognitive performance. However, applying foundation models(FM) to fMRI data remains challenging due to its high…
Research on Brain-Computer Interface (BCI) began in the 1970s and has increased in volume and diversified significantly since then. Today BCI is widely used for applications like assistive devices for physically challenged users, mental…