Amos Azaria

Ariel University · Department of Computer Science and Mathematics

Conversational tutoring systems (CTSs) offer learning experiences through interactions based on natural language. They are recognized for promoting cognitive engagement and improving learning outcomes, especially in reasoning tasks. Nonetheless, the cost associated with authoring CTS content is a major obstacle to widespread adoption and to researc...

Efforts are being made to improve the time effectiveness of healthcare providers. Artificial intelligence tools can help transcript and summarize physician-patient encounters and produce medical notes and medical recommendations. However, in addition to medical information, discussion between healthcare and patients includes small talk and other in...

This paper investigates the capabilities of ChatGPT as an automated assistant in diverse domains, including scientific writing, mathematics, education, programming, and healthcare. We explore the potential of ChatGPT to enhance productivity, streamline problem-solving processes, and improve writing style. Furthermore, we highlight the potential ris...

In many situations when people are assigned to coalitions the assignment must be social aware, i.e, the utility of each person depends on the friends in her coalition. Additionally, in many situations the size of each coalition should be bounded. This paper initiates the study of such coalition formation scenarios in both weighted and unweighted se...

This paper investigates the capabilities of ChatGPT as an automated assistant in diverse domains, including scientific writing, mathematics, education, programming, and healthcare. We explore the potential of ChatGPT to enhance productivity, streamline problem-solving processes, and improve writing style. Furthermore, we highlight the potential ris...

Open-world survival games pose significant challenges for AI algorithms due to their multi-tasking, deep exploration, and goal prioritization requirements. Despite reinforcement learning (RL) being popular for solving games, its high sample complexity limits its effectiveness in complex open-world games like Crafter or Minecraft. We propose a novel...

Pre-trained large language models (LLMs) capture procedural knowledge about the world. Recent work has leveraged LLM's ability to generate abstract plans to simplify challenging control tasks, either by action scoring, or action modeling (fine-tuning). However, the transformer architecture inherits several constraints that make it difficult for the...

Children with special needs may struggle to identify uncomfortable and unsafe situations. In this study, we aimed at developing an automated system that can detect such situations based on audio and text cues to encourage children’s safety and prevent situations of violence toward them. We composed a text and audio database with over 1891 sentences...

High sample complexity has long been a challenge for RL. On the other hand, humans learn to perform tasks not only from interaction or demonstrations, but also by reading unstructured text documents, e.g., instruction manuals. Instruction manuals and wiki pages are among the most abundant data that could inform agents of valuable features and polic...

Large language models have been shown useful in multiple domains including conversational agents, education , and explainable AI. ChatGPT is a large language model developed by OpenAI as a conversational agent. ChatGPT was trained on data generated by humans and by receiving human feedback. This training process results in a bias toward humans' tra...

It is difficult to overestimate the importance of detecting human deception, specifically by using speech cues. Indeed, several works attempt to detect deception from speech. Unfortunately, most works use the same people and environments in training and in testing. That is, they do not separate training samples from test samples according to the pe...

On-demand ridesharing services play a crucial part in the development of modern smart cities. Unfortunately, despite their advantages, not many people opt to use them. We believe that increasing the user satisfaction from the services will cause more people to utilize them. Sometimes, it is possible to increase user satisfaction by providing accura...

Large language models have been shown useful in multiple domains including conversational agents, education, and explainable AI. ChatGPT is a large language model developed by OpenAI as a conversational agent. Being a large language model, ChatGPT is trained on massive amounts of data. Clearly, the characteristics of the data influence ChatGPT's re...

In meta-reinforcement learning, an agent is trained in multiple different environments and attempts to learn a meta-policy that can efficiently adapt to a new environment. This paper presents RAMP, a Reinforcement learning Agent using Model Parameters that utilizes the idea that a neural network trained to predict environment dynamics encapsulates...

Autonomous agents that interact with humans are becoming more and more prominent. Currently, such agents usually take one of the following approaches for considering human behavior. Some methods assume either a fully cooperative or a zero-sum setting; these assumptions entail that the human's goals are either identical to that of the agent, or thei...

One of the ways to make reinforcement learning (RL) more efficient is by utilizing human advice. Because human advice is expensive, the central question in advice-based reinforcement learning is, how to decide in which states the agent should ask for advice. To approach this challenge, various advice strategies have been proposed. Although all of t...

The Shapley value is one of the most important normative division scheme in cooperative game theory, satisfying basic axioms. However, some allocation according to the Shapley value may seem unfair to humans. In this paper, we develop an automatic method that generates intuitive explanations for a Shapley-based payoff allocation, which utilizes the...

We analyze the assignment of passengers in a shared ride, which considers the social relationship among the passengers. Namely, there is a fixed number of passengers in each vehicle, and the goal is to recommend an assignment of the passengers such that the number of friendship relations is maximized. We show that the problem is computationally har...

This paper presents ACCWSI (Attentive Context Clustering WSI), a method for Word Sense Induction, suitable for languages with limited resources. Pretrained on a small corpus and given an ambiguous word (a query word) and a set of excerpts that contain it, ACCWSI uses an attention mechanism for generating context-aware embeddings, distinguishing bet...

Goldbach conjecture is one of the most famous open mathematical problems. He asserts that: Every even number greater than two is the sum of two prime numbers. The Goldbach function receives an even number and returns the number of different ways to write it as an unordered sum of two prime numbers. We developed a simple multilayer perceptron that a...

In the context of reinforcement learning we introduce the concept of criticality of a state, which indicates the extent to which the choice of action in that particular state influences the expected return. That is, a state in which the choice of action is more likely to influence the final outcome is considered as more critical than a state in whi...

When AI agents don't align their actions with human values they may cause serious harm. One way to solve the value alignment problem is by including a human operator who monitors all of the agent's actions. Despite the fact, that this solution guarantees maximal safety, it is very inefficient, since it requires the human operator to dedicate all of...

When a student is asked to perform a given task, her subjective estimate of the difficulty of that task has a strong influence on her performance. There exists a rich literature on the impact of perceived task difficulty on performance and motivation. Yet, there is another topic that is closely related to the subject of the influence of perceived t...

This paper addresses the issue of autonomous competitive yet safe driving in the context of the Indy Autonomous Challenge (IAC) simulation race. The IAC is the first multi-vehicle autonomous head-to-head competition, reaching speeds of 300 km/h along an oval track modeled after the Indianapolis Motor Speedway (IMS). We present a racing controller t...

In recent years, conversational agents (CAs) have become ubiquitous and are a presence in our daily routines. It seems that the technology has finally ripened to advance the use of CAs in various domains, including commercial, healthcare, educational, political, industrial, and personal domains. In this study, the main areas in which CAs are succes...

Smart home assistants, which enable users to control home appliances and can be used for holding entertaining conversations, have become an inseparable part of many people's homes. Recently, there have been many attempts to allow end-users to teach a home assistant new commands, responses, and rules, which can then be shared with a larger community...

This paper addresses the problem of automated advice provision in settings that involve repeated interactions between people and computer agents. This problem arises in many real world applications such as route selection systems and office assistants. To succeed in such settings agents must reason about how their actions in the present influence p...

This paper addresses the problem of automated advice provision in settings that involve repeated interactions between people and computer agents. This problem arises in many real world applications such as route selection systems and office assistants. To succeed in such settings agents must reason about how their actions in the present influence p...

The traveling salesman game (TSG) consists of dividing the cost of a round trip among several customers. One of the most significant solution concepts in cooperative game theory is the Shapley value, which provides a fair division of the costs for a variety of games including the TSG, based on the marginal costs attributed with each customer. In th...

We present the single track road problem. In this problem two agents face each-other at opposite positions of a road that can only have one agent pass at a time. We focus on the scenario in which one agent is human, while the other is an autonomous agent. We run experiments with human subjects in a simple grid domain, which simulates the single tra...

This paper describes Ariel Team's autonomous racing controller for the Indy Autonomous Challenge (IAC) simulation race \cite{INDY}. IAC is the first multi-vehicle autonomous head-to-head competition, reaching speeds of 300 km/h along an oval track, modeled after the Indianapolis Motor Speedway (IMS). Our racing controller attempts to maximize progr...

This work presents a concept of intelligent vision-less micro-drones, which are motivated by flying animals such as insects, birds, and bats. The presented micro-drone (named BAT: Blind Autonomous Tiny-drone) can perform bio-inspired complex tasks without the use of cameras. The BAT uses LIDARs and self-emitted optical-flow in order to perform obst...

Transportation services play a crucial part in the development of modern smart cities. In particular, on-demand ridesharing services, which group together passengers with similar itineraries, are already operating in several metropolitan areas. These services can be of significant social and environmental benefit, by reducing travel costs, road con...

In the context of reinforcement learning we introduce the concept of criticality of a state, which indicates the extent to which the choice of action in that particular state influences the expected return. That is, a state in which the choice of action is more likely to influence the final outcome is considered as more critical than a state in whi...

Transportation services play a crucial part in the development of modern smart cities. In particular, on-demand ridesharing services, which group together passengers with similar itineraries, are already operating in several metropolitan areas. These services can be of significant social and environmental benefit, by reducing travel costs, road con...

An increasingly important process of the internet age and the massive data era is file compression. One popular compression scheme, Lempel–Ziv–Welch (LZW), maintains a dictionary of previously seen strings. The dictionary is updated throughout the parsing process by adding new encountered substrings. Klein, Opalinsky and Shapira (2019) recently stu...

In order for conversational AI systems to hold more natural and broad-ranging conversations, they will require much more commonsense, including the ability to identify unstated presumptions of their conversational partners. For example, in the command "If it snows at night then wake me up early because I don't want to be late for work" the speaker...

Intelligent agents that can interact with users using natural language are becoming increasingly common. Sometimes an intelligent agent may not correctly understand a user command or may not perform it properly. In such cases, the user might try a second time by giving the agent another, slightly different command. Giving an agent the ability to de...

Autonomous navigation has recently gained great interest in the field of reinforcement learning. However, little attention was given to the time-optimal velocity control problem, i.e. controlling a vehicle such that it travels at the maximal speed without becoming dynamically unstable (roll-over or sliding). Time optimal velocity control can be sol...

One aspect of human commonsense reasoning is the ability to make presumptions about daily experiences, activities and social interactions with others. We propose a new commonsense reasoning benchmark where the task is to uncover commonsense presumptions implied by imprecisely stated natural language commands in the form of if-then-because statement...

Ridesharing can significantly reduce individual passenger transport and thus greenhouse gas emissions generated by traffic. Although ridesharing offers great potential, it is not yet popular enough to be seen as an important contribution to solving the aforementioned problems. Our hypothesis suggests that we need to make the assignment mechanism of...

Transportation services play a crucial part in the development of modern smart cities. In particular, on-demand ridesharing services, which group together passengers with similar itineraries, are already operating in several metropolitan areas. These services can be of significant social and environmental benefit, by reducing travel costs, road con...

Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known. It is even more important when the AI system makes decisions in multi-agent environments where the human does not know the systems' goals since they may depend on other agents' preferences. In such situations, explanations sh...

Purose We investigated the value of reactive stroma as a redictor for trastuzumab resistance in atients with early HER2-ositive breast cancer receiving adjuvant theray. Exerimental Design The athological reactive stroma and the mRNA gene signatures that reflect reactive stroma in 209 HER2-ositive breast cancer samles from the FinHer adjuvant trial...

We investigated the value of reactive stroma as a predictor for trastuzumab resistance in patients with early HER2‐positive breast cancer receiving adjuvant therapy. The pathological reactive stroma and the mRNA gene signatures that reflect reactive stroma in 209 HER2‐positive breast cancer samples from the FinHer adjuvant trial were evaluated. Lev...

Teaching via natural language is an intuitive way for end users to add functionality to a virtual assistant, enabling them to personalize their assistant with new commands without requiring the intervention of the system developer, who cannot possibly anticipate all of an end user’s needs. In this paper we introduce our Learning by Instruction Agen...

We describe the task of sentence expansion and enhancement, in which a sentence provided by a human is expanded in some creative way. The expansion should be understandable, believably grammatical, and optimally meaning-preserving. Sentence expansion and enhancement may serve as an authoring tool, or integrate in dynamic media, conversational agent...

Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known. It is even more important when the AI system makes decisions in multi-agent environments where the human does not know the systems' goals since they may depend on other agents' preferences. In such situations, explanations sh...

In this paper, we introduce a learning model able to conceals personal information (e.g. gender, age, ethnicity, etc.) from an image, while maintaining any additional information present in the image (e.g. smile, hair-style, brightness). Our trained model is not provided the information that it is concealing, and does not try learning it either. Na...

Natural language interfaces have become a common part of modern digital life. Chatbots utilize text-based conversations to communicate with users; personal assistants on smartphones such as Google Assistant take direct speech commands from their users; and speech-controlled devices such as Amazon Echo use voice as their only input mode. In this pap...

Natural language interfaces have become a common part of modern digital life. Chatbots utilizetext-based conversations to communicate with users; personal assistants on smartphones such asGoogle Assistant take direct speech commands from their users; and speech-controlled devices suchas Amazon Echo use voice as their only input mode. In this paper,...

Ride-sharing services are gaining popularity and are crucial for a sustainable environment. A special case in which such services are most applicable, is the last mile variant. In this variant it is assumed that all the passengers are positioned at the same origin location (e.g. an airport), and each have a different destination. One of the major i...

Natural language interfaces have become a common part of modern digital life. Chatbots utilize text-based conversations to communicate with users; personal assistants on smartphones such as Google Assistant take direct speech commands from their users; and speech-controlled devices such as Amazon Echo use voice as their only input mode. In this pap...

Question Answering (QA), as a research field, has primarily focused on either knowledge bases (KBs) or free text as a source of knowledge. These two sources have historically shaped the kinds of questions that are asked over these sources, and the methods developed to answer them. In this work, we look towards a practical use-case of QA over user-i...

In the imminent future, people are likely to engage with smart devices by instructing them in natural language. A fundamental question to ask is how might intelligent agents interpret such instructions and learn new tasks. In this article we present the first speech-based virtual assistant that can be taught new commands by speech. A user study on...

An overall goal of our work is to use machine-learning based solutions to assist children with communication difficulties in their communication task. In this paper, we concentrate on the problem of recognizing insulting sentences the child says, or insulting sentences that are told to him. An automated agent that is able to recognize such sentenc...

While autonomous navigation has recently gained great interest in the field of reinforcement learning, only a few works in this field have focused on the time optimal velocity control problem, i.e. controlling a vehicle such that it travels at the maximal stable speed. Achieving maximal stable speed is important in many situations, such as emergenc...

Reinforcement learning methods carry a well known bias-variance trade-off in n-step algorithms for optimal control. Unfortunately, this has rarely been addressed in current research. This trade-off principle holds independent of the choice of the algorithm, such as n-step SARSA, n-step Expected SARSA or n-step Tree backup. A small n results in a la...

This chapter introduces an end user development (EUD) approach for handling common types of failures encountered by goal-oriented conversational agents. We start with identifying three common sources of failures in human-agent conversations: unknown concepts, out-of-domain tasks and wrong fulfillment means or level of generalization in task executi...

Transportation services play a crucial part in the development of modern smart cities. In particular, on-demand ridesharing services, which group together passengers with similar itineraries, are already operating in several metropolitan areas. These services can be of significant social and environmental benefit, by reducing travel costs, road con...

Chatbots have been a core measure of AI since Turing has presented his test for intelligence, and are also widely used for entertainment purposes. In this paper we present a platform that enables users to collaboratively teach a chatbot responses, using natural language. We present a method of collectively detecting malicious users and using the co...

Goldbach conjecture is one of the most famous open mathematical problems. It states that every even number, bigger than two, can be presented as a sum of 2 prime numbers. % In this work we present a deep learning based model that predicts the number of Goldbach partitions for a given even number. Surprisingly, our model outperforms all state-of-the...

Intelligent conversational assistants, such as Apple's Siri, Microsoft's Cortana, and Amazon's Echo, have quickly become a part of our digital life. However, these assistants have major limitations, which prevents users from conversing with them as they would with human dialog partners. This limits our ability to observe how users really want to in...

Intelligent conversational assistants, such as Apple's Siri, Microsoft's Cortana, and Amazon's Echo, have quickly become a part of our digital life. However, these assistants have major limitations, which prevents users from conversing with them as they would with human dialog partners. This limits our ability to observe how users really want to in...

In this work, we focus on semantic parsing of natural language conversations. Most existing methods for semantic parsing are based on understanding the semantics of a single sentence at a time. However, understanding conversations also requires an understanding of conversational context and discourse structure across sentences. We formulate semanti...

In this position paper, we first summarize our work on designing the conversational interface for SUGILITE – a multimodal programming by demonstration system that enables a virtual agent to learn how to handle out-of-domain commands and perform the tasks using available third-party mobile apps in task-oriented dialogs from the user's demonstrations...

In this position paper, we first summarize our work on designing the conversational interface for SUGILITE – a multimodal programming by demonstration system that enables a virtual agent to learn how to handle out-of-domain commands and perform the tasks using available third-party mobile apps in task-oriented dialogs from the user's demonstrations...

SUGILITE is a new programming-by-demonstration (PBD) system that enables users to create automation on smartphones. SUGILITE uses Android's accessibility API to support automating arbitrary tasks in any Android app (or even across multiple apps). When the user gives verbal commands that SUGILITE does not know how to execute, the user can demonstrat...

Recommender Systems have become increasingly important and are applied in an increasing number of domains. While common collaborative methods measure similarity between different users, common content based methods measure similarity between different content. We propose a privacy aware recommender system that exploits relations present between ent...