Related papers: Conversational Code Generation: a Case Study of De…
Existing dialog datasets contain a sequence of utterances and responses without any explicit background knowledge associated with them. This has resulted in the development of models which treat conversation as a sequence-to-sequence…
Simulation environments are good for learning different driving tasks like lane changing, parking or handling intersections etc. in an abstract manner. However, these simulation environments often restrict themselves to operate under…
We demonstrate that large language models are able to simulate Task Oriented Dialogues in novel domains, provided only with an API implementation and a list of goals. We show these simulations can formulate online, automatic metrics that…
End-to-end neural approaches are becoming increasingly common in conversational scenarios due to their promising performances when provided with sufficient amount of data. In this paper, we present a novel methodology to address the…
Generating realistic and controllable traffic scenes from natural language can greatly enhance the development and evaluation of autonomous driving systems. However, this task poses unique challenges: (1) grounding free-form text into…
The development of artificial agents able to learn through dialog without domain restrictions has the potential to allow machines to learn how to perform tasks in a similar manner to humans and change how we relate to them. However,…
We present a novel method for testing the safety of self-driving vehicles in simulation. We propose an alternative to sensor simulation, as sensor simulation is expensive and has large domain gaps. Instead, we directly simulate the outputs…
Evaluating the decision-making system is indispensable in developing autonomous vehicles, while realistic and challenging safety-critical test scenarios play a crucial role. Obtaining these scenarios is non-trivial, thanks to the…
The generation of realistic and diverse traffic scenarios in simulation is essential for developing and evaluating autonomous driving systems. However, most simulation frameworks rely on rule-based or simplified models for scene generation,…
This paper addresses user-specific dialogs. In contrast to previous research on personalized dialogue focused on achieving virtual user dialogue as defined by persona descriptions, user-specific dialogue aims to reproduce real-user dialogue…
Testing autonomous vehicles (AVs) requires complex oracles to determine if the AVs behavior conforms with specifications and humans' expectations. Available open source oracles are tightly embedded in the AV simulation software and are…
Autonomous systems in remote locations have a high degree of autonomy and there is a need to explain what they are doing and why in order to increase transparency and maintain trust. Here, we describe a natural language chat interface that…
Building a dialogue system that can communicate naturally with humans is a challenging yet interesting problem of agent-based computing. The rapid growth in this area is usually hindered by the long-standing problem of data scarcity as…
The manual modeling of complex systems is a daunting task; and although a plethora of methods exist that mitigate this issue, the problem remains very difficult. Recent advances in generative AI have allowed the creation of general-purpose…
The recent paradigm shift toward large reasoning models (LRMs) as autonomous agents has intensified the demand for sophisticated, multi-turn tool-use capabilities. Yet, existing datasets and data-generation approaches are limited by static,…
The predominant approach to open-domain dialog generation relies on end-to-end training of neural models on chat datasets. However, this approach provides little insight as to what these models learn (or do not learn) about engaging in…
We propose a new probabilistic programming language for the design and analysis of cyber-physical systems, especially those based on machine learning. Specifically, we consider the problems of training a system to be robust to rare events,…
End-to-end generation-based approaches have been investigated and applied in task-oriented dialogue systems. However, in industrial scenarios, existing methods face the bottlenecks of controllability (e.g., domain-inconsistent responses,…
Recent advancements in conversational systems have significantly enhanced human-machine interactions across various domains. However, training these systems is challenging due to the scarcity of specialized dialogue data. Traditionally,…
Realistic trajectory generation with natural language control is pivotal for advancing autonomous vehicle technology. However, previous methods focus on individual traffic participant trajectory generation, thus failing to account for the…