Related papers: ALEA IACTA EST: A Declarative Domain-Specific Lang…
Many existing systems track aliasing and uniqueness, each with their own trade-off between expressiveness and developer effort. We propose Latte, a new approach that aims to minimize both the amount of annotations and the complexity of…
A preliminary test of the software package RA is presented. The main focus of this test is to assess RA`s reasoning capabilities that are based on the formal system PECR. Particular attention is given to the finite computational resources…
In testing stateful abstractions, it is often necessary to record interactions, such as method invocations, and express assertions over these interactions. Following the Test Spy design pattern, we can reify such interactions…
Most numerical solvers used to determine free variables of dynamical systems rely on first-order derivatives of the state of the system w.r.t. the free variables. The number of the free variables can be fairly large. One of the approaches…
Recent advances in large language models have enabled natural language to serve as a flexible interface for controlling complex systems, but often at the cost of large-scale multimodal training or weakened domain-specific inductive biases.…
Sample average approximation (SAA), a popular method for tractably solving stochastic optimization problems, enjoys strong asymptotic performance guarantees in settings with independent training samples. However, these guarantees are not…
Active learning (AL) aims to optimize model training and reduce annotation costs by selecting the most informative samples for labeling. Typically, AL methods rely on the empirical distribution of labeled data to define the decision…
The massive successes of large language models (LLMs) encourage the emerging exploration of LLM-augmented Autonomous Agents (LAAs). An LAA is able to generate actions with its core LLM and interact with environments, which facilitates the…
This paper describes MAIA, a Multimodal Automated Interpretability Agent. MAIA is a system that uses neural models to automate neural model understanding tasks like feature interpretation and failure mode discovery. It equips a pre-trained…
Machine learning provides algorithms that can learn from data and make inferences or predictions on data. Stochastic acceptors or probabilistic automata are stochastic automata without output that can model components in machine learning…
Recursive calls over recursive data are useful for generating probability distributions, and probabilistic programming allows computations over these distributions to be expressed in a modular and intuitive way. Exact inference is also…
Software engineering requires rigorous testing to guarantee the product's quality. Semantic testing of functional correctness is challenged by nondeterminism in behavior, which makes testers difficult to write and reason about. This thesis…
In this paper, we propose SEA, a novel approach for active robot exploration through semantic map prediction and a reinforcement learning-based hierarchical exploration policy. Unlike existing learning-based methods that rely on one-step…
An algorithm specification in natural language or pseudocode is expected to be clear and explicit enough to enable mechanical execution. In this position paper we contribute an initial characterization of the knowledge that an executing…
Active learning (AL) is a promising ML paradigm that has the potential to parse through large unlabeled data and help reduce annotation cost in domains where labeling data can be prohibitive. Recently proposed neural network based AL…
PROMELA (Process Meta Language) is a high-level specification language designed for modeling interactions in distributed systems. PROMELA is used as the input language for the model checker SPIN (Simple Promela INterpreter). The main…
In this demo, we present AERA Chat, an automated and explainable educational assessment system designed for interactive and visual evaluations of student responses. This system leverages large language models (LLMs) to generate automated…
When collaborating with an AI system, we need to assess when to trust its recommendations. If we mistakenly trust it in regions where it is likely to err, catastrophic failures may occur, hence the need for Bayesian approaches for…
Programming a parallel computing system that consists of several thousands or even up to a million message passing processing units may ask for a language that supports waiting for and sending messages over hardware channels. As programs…
We introduce Meta Agents Research Environments (ARE), a research platform for scalable creation of environments, integration of synthetic or real applications, and execution of agentic orchestrations. ARE provides simple abstractions to…