Related papers: Scrambler: Mixed Boolean Arithmetic Obfuscation To…

In the present work we have selected a collection of statistical and mathematical tools useful for the exploration of multivariate data and we present them in a form that is meant to be particularly accessible to a classically trained…

Lexical ambiguities naturally arise in languages. We present Lamb, a lexical analyzer that produces a lexical analysis graph describing all the possible sequences of tokens that can be found within the input string. Parsers can process such…

Machine-learning methods are gradually being adopted in a wide variety of social, economic, and scientific contexts, yet they are notorious for struggling with exact mathematics. A typical example is computer algebra, which includes tasks…

Android applications are usually obfuscated before release, making it difficult to analyze them for malware presence or intellectual property violations. Obfuscators might hide the true intent of code by renaming variables and/or modifying…

We present DiffExplainer, a novel framework that, leveraging language-vision models, enables multimodal global explainability. DiffExplainer employs diffusion models conditioned on optimized text prompts, synthesizing images that maximize…

As more decisions in our daily life become automated, the need to have machine learning algorithms that make fair decisions increases. In fair representation learning we are tasked with finding a suitable representation of the data in which…

Large language models have recently pushed open domain question answering (ODQA) to new frontiers. However, prevailing retriever-reader pipelines often depend on multiple rounds of prompt level instructions, leading to high computational…

Regular expressions are widely used in software. Various regular expression engines support different combinations of extensions to classical regular constructs such as Kleene star, concatenation, nondeterministic choice (union in terms of…

Labeling a large number of electronic health records is expensive and time consuming, and having a labeling assistant tool can significantly reduce medical experts' workload. Nevertheless, to gain the experts' trust, the tool must be able…

Graph clustering, aiming to partition nodes of a graph into various groups via an unsupervised approach, is an attractive topic in recent years. To improve the representative ability, several graph auto-encoder (GAE) models, which are based…

Query expansion is a method for alleviating the vocabulary mismatch problem present in information retrieval tasks. Previous works have shown that terms selected for query expansion by traditional methods such as pseudo-relevance feedback…

Library learning compresses a given corpus of programs by extracting common structure from the corpus into reusable library functions. Prior work on library learning suffers from two limitations that prevent it from scaling to larger, more…

Representing graphs as sets of node embeddings in certain curved Riemannian manifolds has recently gained momentum in machine learning due to their desirable geometric inductive biases, e.g., hierarchical structures benefit from hyperbolic…

Graph transformation approaches have been successfully used to analyse and design chemical and biological systems. Here we build on top of a DPO framework, in which molecules are modelled as typed attributed graphs and chemical reactions…

Bayesian graphical models are a useful tool for understanding dependence relationships among many variables, particularly in situations with external prior information. In high-dimensional settings, the space of possible graphs becomes…

Interpretability is a crucial aspect of machine learning models that enables humans to understand and trust the decision-making process of these models. In many real-world applications, the interpretability of models is essential for legal,…

Gamma uncertainty sets have been introduced for adjusting the degree of conservatism of robust counterparts of (discrete) linear programs. The contribution of this paper is a generalization of this approach to (mixed integer) nonlinear…

Adapting small instruction-tuned models to specialized domains often relies on supervised fine-tuning (SFT) on curated instruction-response examples, which is expensive to collect at scale. Synthetic training examples generated by a teacher…

In reinforcement learning, the graph Laplacian has proved to be a valuable tool in the task-agnostic setting, with applications ranging from skill discovery to reward shaping. Recently, learning the Laplacian representation has been framed…

At the boundary between the known and the unknown, an agent inevitably confronts the dilemma of whether to explore or to exploit. Epistemic uncertainty reflects such boundaries, representing systematic uncertainty due to limited knowledge.…