The advancements in machine learning (ML) opened a new opportunity to bring intelligence
to the low-end Internet-of-Things (IoT) nodes, such as microcontrollers. Conventional ML …

Deep neural networks are powerful tools to detect hidden patterns in data and leverage
them to make predictions, but they are not designed to understand uncertainty and estimate …

We propose a method to infer a dense depth map from a single image, its calibration, and
the associated sparse point cloud. In order to leverage existing models (teachers) that …

Abstract Knowledge Distillation (KD) has proven effective for compressing large teacher
models into smaller student models. While it is well known that student models can achieve …

Over the past few years, machine learning models have significantly increased in size and
complexity, especially in the area of generative AI such as large language models. These …

Systematic techniques to improve quality of deep neural networks (DNNs) are critical given
the increasing demand for practical applications including safety-critical ones. The key …

When machine learning systems meet real world applications, accuracy is only one of
several requirements. In this paper, we assay a complementary perspective originating from …

In asymmetric retrieval systems, models with different capacities are deployed on platforms
with different computational and storage resources. Despite the great progress, existing …

Large Language Models (LLMs) are regularly updated to enhance performance, typically
through changes in data or architecture. Within the update process, developers often …

Our work tackles the emergent problem of reducing predictive inconsistencies arising as
negative flips: test samples that are correctly predicted by a less accurate model, but …