Related papers: AutoAlias: Automatic Variable-Precision Alias Anal…
Document Visual Question Answering (VQA) requires models to not only extract accurate textual answers but also precisely localize them within document images, a capability critical for interpretability in high-stakes applications. However,…
People often give instructions whose meaning is ambiguous without further context, expecting that their actions or goals will disambiguate their intentions. How can we build assistive agents that follow such instructions in a flexible,…
Symbolic execution is a classical program analysis technique used to show that programs satisfy or violate given specifications. In this work we generalize symbolic execution to support program analysis for relational specifications in the…
We introduce a new algorithm for approximation by rational functions on a real or complex set of points, implementable in 40 lines of Matlab and requiring no user input parameters. Even on a disk or interval the algorithm may outperform…
Autonomous multi-agent systems (MAS) are useful for automating complex tasks but raise trust concerns due to risks such as miscoordination or goal misalignment. Explainability is vital for users' trust calibration, but explainable MAS face…
CiaoPP is an analyzer and optimizer for logic programs, part of the Ciao Prolog system. It includes PLAI, a fixpoint algorithm for the abstract interpretation of logic programs which we adapt to use tabled constraint logic programming. In…
The overall problem addressed in this paper is the long-standing problem of program correctness, and in particular programs that describe systems of parallel executing processes. We propose a new method for proving correctness of parallel…
Annotating datasets for object detection is an expensive and time-consuming endeavor. To minimize this burden, active learning (AL) techniques are employed to select the most informative samples for annotation within a constrained…
The application of operator overloading algorithmic differentiation (AD) to computer programs in order to compute the derivative is quite common. But, the replacement of the underlying computational floating point type with the specialized…
AI-assisted programming greatly increases software development performance. We enhance this potential by integrating transparency through domain-specific modeling techniques and providing instantaneous, graphical visualizations that…
In this paper, we propose an autonomous information seeking visual question answering framework, AVIS. Our method leverages a Large Language Model (LLM) to dynamically strategize the utilization of external tools and to investigate their…
A flaw in QA evaluation is that annotations often only provide one gold answer. Thus, model predictions semantically equivalent to the answer but superficially different are considered incorrect. This work explores mining alias entities…
Software analytics has been widely used in software engineering for many tasks such as generating effort estimates for software projects. One of the "black arts" of software analytics is tuning the parameters controlling a data mining…
Machine learning (ML) is increasingly being used in critical decision-making software, but incidents have raised questions about the fairness of ML predictions. To address this issue, new tools and methods are needed to mitigate bias in…
Security practitioners face growing challenges in exploit assessment, as public vulnerability repositories are increasingly populated with inconsistent and low-quality exploit artifacts. Existing scoring systems, such as CVSS and EPSS,…
Authorship Attribution (AA) and Authorship Obfuscation (AO) are two competing tasks of increasing importance in privacy research. Modern AA leverages an author's consistent writing style to match a text to its author using an AA classifier.…
Behavioral skills or policies for autonomous agents are conventionally learned from reward functions, via reinforcement learning, or from demonstrations, via imitation learning. However, both modes of task specification have their…
Policy documents, such as legislation, regulations, and executive orders, are crucial in shaping society. However, their length and complexity make interpretation and application challenging and time-consuming. Artificial intelligence (AI),…
AI deployed in many real-world use cases should be capable of adapting to novelties encountered after deployment. Here, we consider a challenging, under-explored and realistic continual adaptation problem: a deployed AI agent is…
Parameter identification for mechanistic Ordinary Differential Equation (ODE) models underpins prediction and control in several applications, yet remains a manual and labor-intensive process: datasets are noisy and partial, models can be…