相关论文: SafePILCO: a software tool for safe and data-effic…

This paper proposes a Safe Online Control-Informed Learning framework for safety-critical autonomous systems. The framework unifies optimal control, parameter estimation, and safety constraints into an online learning process. It employs an…

In this paper, we present a new fault injection tool (ProFIPy) for Python software. The tool is designed to be programmable, in order to enable users to specify their software fault model, using a domain-specific language (DSL) for fault…

This paper presents a general framework and methods for complete programming and checking of distributed algorithms at a high-level, as in pseudocode languages, but precisely specified and directly executable, as in formal specification…

Factor Engine is a high-performance, open-source Python library designed for the systematic computation and analysis of financial factors. Built around a modular and extensible API that leverages Python decorators, Factor Engine enables…

One problem with researching cognitive modeling and reinforcement learning (RL) is that researchers spend too much time on setting up an appropriate computational framework for their experiments. Many open source implementations of current…

We present a reinforcement learning toolkit for experiments with guiding automated theorem proving in the connection calculus. The core of the toolkit is a compact and easy to extend Prolog-based automated theorem prover called plCoP. plCoP…

Pattern matching is a powerful tool for symbolic computations. Applications include term rewriting systems, as well as the manipulation of symbolic expressions, abstract syntax trees, and XML and JSON data. It also allows for an intuitive…

Safe policy improvement (SPI) offers theoretical control over policy updates, yet existing guarantees largely concern offline, tabular reinforcement learning (RL). We study SPI in general online settings, when combined with world model and…

In Semi-Supervised Semi-Private (SP) learning, the learner has access to both public unlabelled and private labelled data. We propose a computationally efficient algorithm that, under mild assumptions on the data, provably achieves…

This paper introduces a new Python package specifically designed to address calibration of probabilistic classifiers under dataset shift. The method is demonstrated in binary and multi-class settings and its effectiveness is measured…

In this paper, we present a new semantics to check file safety of multithreaded programs. A file-safe program is one that reaches a final configuration under the proposed semantics. We extend the While language with file operations and…

Safety is one of the biggest concerns to applying reinforcement learning (RL) to the physical world. In its core part, it is challenging to ensure RL agents persistently satisfy a hard state constraint without white-box or black-box…

The legality of training language models (LMs) on copyrighted or otherwise restricted data is under intense debate. However, as we show, model performance significantly degrades if trained only on low-risk text (e.g., out-of-copyright books…

Recent advances in large language models (LLMs) have popularized test-time scaling, where models generate additional reasoning tokens before producing final answers. These approaches have demonstrated significant performance improvements on…

Safety-critical task planning in robotic systems remains challenging: classical planners suffer from poor scalability, Reinforcement Learning (RL)-based methods generalize poorly, and base Large Language Models (LLMs) cannot guarantee…

The democratization of Data Mining has been widely successful thanks in part to powerful and easy-to-use Machine Learning libraries. These libraries have been particularly tailored to tackle Supervised Learning. However, strong supervision…

Even though several publicly accessible pharmacovigilance databases are available, extracting data from them is a technically challenging process. Existing tools typically focus on a single database. We present SurVigilance, an open-source…

In security-critical software applications, confidential information must be prevented from leaking to unauthorized sinks. Static analysis techniques are widespread to enforce a secure information flow by checking a program after…

Safety is a crucial property of every robotic platform: any control policy should always comply with actuator limits and avoid collisions with the environment and humans. In reinforcement learning, safety is even more fundamental for…

Ensuring safe and appropriate responses from vision-language models (VLMs) remains a critical challenge, particularly in high-risk or ambiguous scenarios. We introduce SafeCoT, a lightweight, interpretable framework that leverages…