Related papers: Lensing Machines: Representing Perspective in Late…

Cognitive neuroscience is enjoying rapid increase in extensive public brain-imaging datasets. It opens the door to large-scale statistical models. Finding a unified perspective for all available data calls for scalable and automated…

Visual scenes are extremely rich in diversity, not only because there are infinite combinations of objects and background, but also because the observations of the same scene may vary greatly with the change of viewpoints. When observing a…

Generating detailed descriptions from multiple cameras and viewpoints is challenging due to the complex and inconsistent nature of visual data. In this paper, we introduce PerspectiveNet, a lightweight yet efficient model for generating…

The commonly used latent space embedding techniques, such as Principal Component Analysis, Factor Analysis, and manifold learning techniques, are typically used for learning effective representations of homogeneous data. However, they do…

Large language models (LLMs) are capable of producing high quality information at unprecedented rates. As these models continue to entrench themselves in society, the content they produce will become increasingly pervasive in databases that…

We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partially observed setting in which each view constitutes a…

Sequential modelling of high-dimensional data is an important problem that appears in many domains including model-based reinforcement learning and dynamics identification for control. Latent variable models applied to sequential data…

Multimodal learning has been lacking principled ways of combining information from different modalities and learning a low-dimensional manifold of meaningful representations. We study multimodal learning and sensor fusion from a latent…

The open-source model ecosystem now contains hundreds of thousands of pretrained models, yet picking the best model for a new dataset is increasingly infeasible: new models and unbenchmarked datasets emerge continuously, leaving…

Dashboard cameras capture a tremendous amount of driving scene video each day. These videos are purposefully coupled with vehicle sensing data, such as from the speedometer and inertial sensors, providing an additional sensing modality for…

Image classification models tend to make decisions based on peripheral attributes of data items that have strong correlation with a target variable (i.e., dataset bias). These biased models suffer from the poor generalization capability…

This thesis presents new methods for unsupervised learning of distributed representations of words and entities from text and knowledge bases. The first algorithm presented in the thesis is a multi-view algorithm for learning…

We propose an approach to self-supervised representation learning based on maximizing mutual information between features extracted from multiple views of a shared context. For example, one could produce multiple views of a local…

To explore underlying complementary information from multiple views, in this paper, we propose a novel Latent Multi-view Semi-Supervised Classification (LMSSC) method. Unlike most existing multi-view semi-supervised classification methods…

For a long time, machine learning (ML) has been seen as the abstract problem of learning relationships from data independent of the surrounding settings. This has recently been challenged, and methods have been proposed to include external…

In this paper, we propose Multi-View Dreaming, a novel reinforcement learning agent for integrated recognition and control from multi-view observations by extending Dreaming. Most current reinforcement learning method assumes a single-view…

Recently, multi-view representation learning has become a rapidly growing direction in machine learning and data mining areas. This paper introduces two categories for multi-view representation learning: multi-view representation alignment…

Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision. A good general representation can be fine-tuned for new target tasks using…

Large Language Models (LLMs) have demonstrated impressive performance across various tasks, with different models excelling in distinct domains and specific abilities. Effectively combining the predictions of multiple LLMs is crucial for…

Advances in dataset analysis techniques have enabled more sophisticated approaches to analyzing and characterizing training data instances, often categorizing data based on attributes such as ``difficulty''. In this work, we introduce…