Related papers: Masked Measurement Prediction: Learning to Jointly…

Generalized Entity Matching (GEM), which aims at judging whether two records represented in different formats refer to the same real-world entity, is an essential task in data management. The prompt tuning paradigm for pre-trained language…

Hidden Markov Models (HMMs) are foundational tools for modeling sequential data with latent Markovian structure, yet fitting them to real-world data remains computationally challenging. In this work, we show that pre-trained large language…

Integrating segmentation into Multimodal Large Language Models (MLLMs) presents a core trilemma: simultaneously preserving dialogue ability, achieving high segmentation performance, and ensuring fast inference. Prevailing paradigms are…

Probability theory has become the predominant framework for quantifying uncertainty across scientific and engineering disciplines, with a particular focus on measurement and control systems. However, the widespread reliance on simple…

Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their…

Multimodal Large Language Models advance multimodal representation learning by acquiring transferable semantic embeddings, thereby substantially enhancing performance across a range of vision-language tasks, including cross-modal retrieval,…

We introduce Masked Trajectory Models (MTM) as a generic abstraction for sequential decision making. MTM takes a trajectory, such as a state-action sequence, and aims to reconstruct the trajectory conditioned on random subsets of the same…

Despite significant progress in robotic systems for operation within human-centric environments, existing models still heavily rely on explicit human commands to identify and manipulate specific objects. This limits their effectiveness in…

Medical image-language pre-training aims to align medical images with clinically relevant text to improve model performance on various downstream tasks. However, existing models often struggle with the variability and ambiguity inherent in…

An earlier introduced characterization of nonuniform learnability that allows the sample size to depend on the hypothesis to which the learner is compared has been redefined using the measure theoretic approach. Where nonuniform…

In recent years, there has been remarkable progress in leveraging Language Models (LMs), encompassing Pre-trained Language Models (PLMs) and Large-scale Language Models (LLMs), within the domain of mathematics. This paper conducts a…

A common practice in metric learning is to train and test an embedding model for each dataset. This dataset-specific approach fails to simulate real-world scenarios that involve multiple heterogeneous distributions of data. In this regard,…

Masked Image Modeling (MIM) has emerged as a promising method for deriving visual representations from unlabeled image data by predicting missing pixels from masked portions of images. It excels in region-aware learning and provides strong…

The increasing use of text as data in social science research necessitates the development of valid, consistent, reproducible, and efficient methods for generating text-based concept measures. This paper presents a novel method that…

Large language models (LLMs) process and predict sequences containing text to answer questions, and address tasks including document summarization, providing recommendations, writing software and solving quantitative problems. We provide a…

Statistical evaluation aims to estimate the generalization performance of a model using held-out i.i.d.\ test data sampled from the ground-truth distribution. In supervised learning settings such as classification, performance metrics such…

Prompting is now a dominant method for evaluating the linguistic knowledge of large language models (LLMs). While other methods directly read out models' probability distributions over strings, prompting requires models to access this…

Compared to the prosperity of pre-training models in natural image understanding, the research on large-scale pre-training models for facial knowledge learning is still limited. Current approaches mainly rely on manually assembled and…

Predicting molecular properties is a critical component of drug discovery. Recent advances in deep learning, particularly Graph Neural Networks (GNNs), have enabled end-to-end learning from molecular structures, reducing reliance on manual…

Multi-year-to-decadal climate prediction is a key tool in understanding the range of potential regional and global climate futures. Here, we present a framework that combines machine learning and analog forecasting for predictions on these…