Related papers: LADDER: Language-Driven Slice Discovery and Error …
Self-supervised representation learning methods often fail to learn subtle or complex features, which can be dominated by simpler patterns which are much easier to learn. This limitation is particularly problematic in applications to…
Clustering short text is a difficult problem, due to the low word co-occurrence between short text documents. This work shows that large language models (LLMs) can overcome the limitations of traditional clustering approaches by generating…
Identification of disease subtypes and corresponding biomarkers can substantially improve clinical diagnosis and treatment selection. Discovering these subtypes in noisy, high dimensional biomedical data is often impossible for humans and…
New Large Language Models (LLMs) become available every few weeks, and modern application developers confronted with the unenviable task of having to decide if they should switch to a new model. While human evaluation remains the gold…
Computer vision datasets frequently contain spurious correlations between task-relevant labels and (easy to learn) latent task-irrelevant attributes (e.g. context). Models trained on such datasets learn "shortcuts" and underperform on…
Clustering and outlier detection are two important tasks in data mining. Outliers frequently interfere with clustering algorithms to determine the similarity between objects, resulting in unreliable clustering results. Currently, only a few…
Although prior work on bias mitigation has focused on promoting social equality and demographic parity, less attention has been given to aligning LLM's outputs to desired distributions. For example, we might want to align a model with…
Intelligent fault diagnosis has made extraordinary advancements currently. Nonetheless, few works tackle class-incremental learning for fault diagnosis under limited fault data, i.e., imbalanced and long-tailed fault diagnosis, which brings…
A challenge in advancing Visual-Language Models (VLMs) is determining whether their failures on abstract reasoning tasks, such as Bongard problems, stem from flawed perception or faulty top-down reasoning. To disentangle these factors, we…
Continual learning with vision-language models like CLIP offers a pathway toward scalable machine learning systems by leveraging its transferable representations. Existing CLIP-based methods adapt the pre-trained image encoder by adding…
CLIP has shown impressive results in aligning images and texts at scale. However, its ability to capture detailed visual features remains limited because CLIP matches images and texts at a global level. To address this issue, we propose…
In this paper we explore different regression models based on Clusterwise Linear Regression (CLR). CLR aims to find the partition of the data into $k$ clusters, such that linear regressions fitted to each of the clusters minimize overall…
Out-of-distribution (OOD) detection aims to discern outliers from the intended data distribution, which is crucial to maintaining high reliability and a good user experience. Most recent studies in OOD detection utilize the information from…
Diversity is essential for language-model applications ranging from creative generation to scientific discovery, yet modern LLMs often collapse into a narrow subset of plausible outputs. While prior work has developed benchmarks for…
Recent advancements in Artificial Intelligence, particularly in Large Language Models (LLMs), have transformed natural language processing by improving generative capabilities. However, detecting biases embedded within these models remains…
Low-latency instance segmentation of LiDAR point clouds is crucial in real-world applications because it serves as an initial and frequently-used building block in a robot's perception pipeline, where every task adds further delay.…
Data slice finding is an emerging technique for validating machine learning (ML) models by identifying and analyzing subgroups in a dataset that exhibit poor performance, often characterized by distinct feature sets or descriptive metadata.…
Recent advances in foundation models present new opportunities for interpretable visual recognition -- one can first query Large Language Models (LLMs) to obtain a set of attributes that describe each class, then apply vision-language…
Generative data augmentation with latent diffusion models is a promising strategy for addressing class imbalance in medical imaging, yet current approaches focus on perceptual fidelity and domain-specific autoencoder fine-tuning while…
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,…