The last decade has seen widespread adoption of Machine Learning (ML) components in software systems. This has occurred in nearly every domain, from natural language processing to computer vision. These ML components range from relatively simple neural networks to complex and resource-intensive large language models. However, despite this widespread adoption, little is known about the supply chain relationships that produce these models, which can have implications for compliance and security. In this work, we conduct an extensive analysis of 760,460 models and 175,000 datasets mined from the popular model-sharing site Hugging Face. First, we evaluate the current state of documentation in the Hugging Face supply chain, report real-world examples of shortcomings, and offer actionable suggestions for improvement. Next, we analyze the underlying structure of the extant supply chain. Finally, we explore the current licensing landscape against what was reported in prior work and discuss the unique challenges posed in this domain. Our results motivate multiple research avenues, including the need for better license management for ML models/datasets, better support for model documentation, and automated inconsistency checking and validation. We make our research infrastructure and dataset available to facilitate future research.

While guide dogs offer essential mobility assistance, their high cost, limited availability, and care requirements make them inaccessible to most blind or low vision (BLV) individuals. Recent advances in quadruped robots provide a scalable solution for mobility assistance, but many current designs fail to meet real-world needs due to a lack of understanding of handler and guide dog interactions. In this paper, we share lessons learned from developing a human-centered guide dog robot, addressing challenges such as optimal hardware design, robust navigation, and informative scene description for user adoption. By conducting semi-structured interviews and human experiments with BLV individuals, guide-dog handlers, and trainers, we identified key design principles to improve safety, trust, and usability in robotic mobility aids. Our findings lay the building blocks for future development of guide dog robots, ultimately enhancing independence and quality of life for BLV individuals.

Large Language Models (LLMs) represent a significant stride toward Artificial General Intelligence. As scaling laws underscore the potential of increasing model sizes, the academic community has intensified its investigations into LLMs with capacities exceeding 50 billion parameters. This technical report builds on our prior work with Tele-FLM (also known as FLM-2), a publicly available 52-billion-parameter model. We delve into two primary areas: we first discuss our observation of Supervised Fine-tuning (SFT) on Tele-FLM-52B, which supports the "less is more" approach for SFT data construction; second, we demonstrate our experiments and analyses on the best practices for progressively growing a model from 52 billion to 102 billion, and subsequently to 1 trillion parameters. We will open-source a 1T model checkpoint, namely Tele-FLM-1T, to advance further training and research.

Seven years ago (2016), we began integrating Robotics into our Computer Science curriculum. This paper explores the mission, initial goals and objectives, specific choices we made along the way, and why and outcomes. Of course, we were not the first to do so. Our contribution in this paper is to describe a seven-year experience in the hope that others going down this road will benefit, perhaps avoiding some missteps and dead-ends. We offer our answers to many questions that anyone undertaking bootstrapping a new robotics program may have to deal with. At the end of the paper, we discuss a set of lessons learned, including striking the right balance between depth and breadth in syllabus design and material organization, the significance of utilizing physical robots and criteria for selecting a suitable robotics platform, insights into the scope and design of a robotics lab, the necessity of standardizing hardware and software configurations, along with implementation methods, and strategies for preparing students for the steep learning curve.

The rapidly evolving fields of Machine Learning (ML) and Artificial Intelligence have witnessed the emergence of platforms like Hugging Face (HF) as central hubs for model development and sharing. This experience report synthesizes insights from two comprehensive studies conducted on HF, focusing on carbon emissions and the evolutionary and maintenance aspects of ML models. Our objective is to provide a practical guide for future researchers embarking on mining software repository studies within the HF ecosystem to enhance the quality of these studies. We delve into the intricacies of the replication package used in our studies, highlighting the pivotal tools and methodologies that facilitated our analysis. Furthermore, we propose a nuanced stratified sampling strategy tailored for the diverse HF Hub dataset, ensuring a representative and comprehensive analytical approach. The report also introduces preliminary guidelines, transitioning from repository mining to cohort studies, to establish causality in repository mining studies, particularly within the ML model of HF context. This transition is inspired by existing frameworks and is adapted to suit the unique characteristics of the HF model ecosystem. Our report serves as a guiding framework for researchers, contributing to the responsible and sustainable advancement of ML, and fostering a deeper understanding of the broader implications of ML models.

In the realm of interactive machine-learning systems, the provision of explanations serves as a vital aid in the processes of debugging and enhancing prediction models. However, the extent to which various global model-centric and data-centric explanations can effectively assist domain experts in detecting and resolving potential data-related issues for the purpose of model improvement has remained largely unexplored. In this technical report, we summarise the key findings of our two user studies. Our research involved a comprehensive examination of the impact of global explanations rooted in both data-centric and model-centric perspectives within systems designed to support healthcare experts in optimising machine learning models through both automated and manual data configurations. To empirically investigate these dynamics, we conducted two user studies, comprising quantitative analysis involving a sample size of 70 healthcare experts and qualitative assessments involving 30 healthcare experts. These studies were aimed at illuminating the influence of different explanation types on three key dimensions: trust, understandability, and model improvement. Results show that global model-centric explanations alone are insufficient for effectively guiding users during the intricate process of data configuration. In contrast, data-centric explanations exhibited their potential by enhancing the understanding of system changes that occur post-configuration. However, a combination of both showed the highest level of efficacy for fostering trust, improving understandability, and facilitating model enhancement among healthcare experts. We also present essential implications for developing interactive machine-learning systems driven by explanations. These insights can guide the creation of more effective systems that empower domain experts to harness the full potential of machine learning

We address, through the automated reasoning tools in GeoGebra Discovery, a problem from a regional phase of the Austrian Mathematics Olympiad 2023. Trying to solve this problem gives rise to four different kind of feedback: the almost instantaneous, automated solution of the proposed problem; the measure of its complexity, according to some recent proposals; the automated discovery of a generalization of the given assertion, showing that the same statement is true over more general polygons than those mentioned in the problem; and the difficulties associated to the analysis of the surprising and involved high number of degenerate cases that appear when using the LocusEquation command in this problem. In our communication we will describe and reflect on these diverse issues, enhancing its exemplar role for showing some of the advantages, problems, and current fields of development of GeoGebra Discovery.

Data integration is considered a classic research field and a pressing need within the information science community. Ontologies play a critical role in such a process by providing well-consolidated support to link and semantically integrate datasets via interoperability. This paper approaches data integration from an application perspective, looking at techniques based on ontology matching. An ontology-based process may only be considered adequate by assuming manual matching of different sources of information. However, since the approach becomes unrealistic once the system scales up, automation of the matching process becomes a compelling need. Therefore, we have conducted experiments on actual data with the support of existing tools for automatic ontology matching from the scientific community. Even considering a relatively simple case study (i.e., the spatio-temporal alignment of global indicators), outcomes clearly show significant uncertainty resulting from errors and inaccuracies along the automated matching process. More concretely, this paper aims to test on real-world data a bottom-up knowledge-building approach, discuss the lessons learned from the experimental results of the case study, and draw conclusions about uncertainty and uncertainty management in an automated ontology matching process. While the most common evaluation metrics clearly demonstrate the unreliability of fully automated matching solutions, properly designed semi-supervised approaches seem to be mature for a more generalized application.

On-device machine learning (ML) promises to improve the privacy, responsiveness, and proliferation of new, intelligent user experiences by moving ML computation onto everyday personal devices. However, today's large ML models must be drastically compressed to run efficiently on-device, a hurtle that requires deep, yet currently niche expertise. To engage the broader human-centered ML community in on-device ML experiences, we present the results from an interview study with 30 experts at Apple that specialize in producing efficient models. We compile tacit knowledge that experts have developed through practical experience with model compression across different hardware platforms. Our findings offer pragmatic considerations missing from prior work, covering the design process, trade-offs, and technical strategies that go into creating efficient models. Finally, we distill design recommendations for tooling to help ease the difficulty of this work and bring on-device ML into to more widespread practice.

Social distance, or perception of the other, is recognized as a dynamic dimension of an interaction, but yet to be widely explored or understood. Through CORAE, a novel web-based open-source tool for COntinuous Retrospective Affect Evaluation, we collected retrospective ratings of interpersonal perceptions between 12 participant dyads. In this work, we explore how different aspects of these interactions reflect on the ratings collected, through a discourse analysis of individual and social behavior of the interactants. We found that different events observed in the ratings can be mapped to complex interaction phenomena, shedding light on relevant interaction features that may play a role in interpersonal understanding and grounding. This paves the way for better, more seamless human-robot interactions, where affect is interpreted as highly dynamic and contingent on interaction history.