Related papers: Technical report on label-informed logit redistrib…

Handling distribution shifts from training data, known as out-of-distribution (OOD) generalization, poses a significant challenge in the field of machine learning. While a pre-trained vision-language model like CLIP has demonstrated…

Continual learning for large language models is typically evaluated through accuracy retention under sequential fine-tuning. We argue that this perspective is incomplete, because uncertainty reliability can degrade earlier and more sharply…

Recent advances in vision-language foundational models, such as CLIP, have demonstrated significant strides in zero-shot classification. However, the extensive parameterization of models like CLIP necessitates a resource-intensive…

Contrastive Language-Image Pre-Training (CLIP) has enabled zero-shot classification in radiology, reducing reliance on manual annotations. However, conventional contrastive learning struggles with normal case detection due to its strict…

Medical vision-language models (VLMs) are strong zero-shot recognizers for medical imaging, but their reliability under domain shift hinges on calibrated uncertainty with guarantees. Split conformal prediction (SCP) offers finite-sample…

Vision-language models (VLMs) have demonstrated exceptional generalization capabilities for downstream tasks. Due to its efficiency, prompt learning has gradually become a more effective and efficient method for transferring VLMs to…

Large language models (LLMs) often make accurate next token predictions but their confidence in these predictions can be poorly calibrated: high-confidence predictions are frequently wrong, and low-confidence predictions may be correct.…

Recalibration of binary probabilistic classifiers to a target prior probability is an important task in areas like credit risk management. However, recalibration of a classifier learned on a training dataset to a target on a test dataset in…

Under label shift, the label distribution p(y) might change but the class-conditional distributions p(x|y) do not. There are two dominant approaches for estimating the label marginal. BBSE, a moment-matching approach based on confusion…

Safety alignment in Large Language Models (LLMs) often creates a systematic discrepancy between a model's aligned output and the underlying pre-aligned data distribution. We propose a framework in which the effect of safety alignment on…

Cache-based approaches stand out as both effective and efficient for adapting vision-language models (VLMs). Nonetheless, the existing cache model overlooks three crucial aspects. 1) Pre-trained VLMs are mainly optimized for image-text…

The ultimate performance of machine learning algorithms for classification tasks is usually measured in terms of the empirical error probability (or accuracy) based on a testing dataset. Whereas, these algorithms are optimized through the…

While significant progress has been made in specifying neural networks capable of representing uncertainty, deep networks still often suffer from overconfidence and misaligned predictive distributions. Existing approaches for measuring this…

We extend our previous work on Inductive Conformal Prediction (ICP) for multi-label text classification and present a novel approach for addressing the computational inefficiency of the Label Powerset (LP) ICP, arrising when dealing with a…

Vision-language models like CLIP show impressive ability to align images and text, but their training on short, concise captions makes them struggle with lengthy, detailed descriptions. Recent advances mitigate this challenge by leveraging…

Image recognition has recently witnessed a paradigm shift, where vision-language models are now used to perform few-shot classification based on textual prompts. Among these, the CLIP model has shown remarkable capabilities for zero-shot…

Precise action spotting has attracted considerable attention due to its promising applications. While existing methods achieve substantial performance by employing well-designed model architecture, they overlook a significant challenge: the…

Few shot learning is an important problem in machine learning as large labelled datasets take considerable time and effort to assemble. Most few-shot learning algorithms suffer from one of two limitations- they either require the design of…

Vision-language pre-training like CLIP has shown promising performance on various downstream tasks such as zero-shot image classification and image-text retrieval. Most of the existing CLIP-alike works usually adopt relatively large image…

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…