Related papers: Compiling High-Level Neural Network Specifications…

Effective employment of deep neural networks (DNNs) in mobile devices and embedded systems is hampered by requirements for memory and computational power. This paper presents a non-uniform quantization approach which allows for dynamic…

Static verification is a powerful method for enhancing software quality, but it demands significant human labor and resources. This is particularly true of static verifiers that reason about heap manipulating programs using an ownership…

Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains. In response to their fast adoption in…

Engagement recognition in video datasets, unlike traditional image classification tasks, is particularly challenged by subjective labels and noise limiting model performance. To overcome the challenges of subjective and noisy engagement…

This paper is a brief introduction to our recently initiated project named VERIFAI: Traceability and verification of natural language requirements. The project addresses the challenges in the traceability and verification of formal…

This work is concerned with the generation of formal specifications from code, using Large Language Models (LLMs) in combination with symbolic methods. Concretely, in our study, the programming language is C, the specification language is…

Rule-based systems remain central in safety-critical domains but often struggle with scalability, brittleness, and goal misspecification. These limitations can lead to reward hacking and failures in formal verification, as AI systems tend…

Much algorithmic research in NLP aims to efficiently manipulate rich formal structures. An algorithm designer typically seeks to provide guarantees about their proposed algorithm -- for example, that its running time or space complexity is…

Verification of machine learning models used in Natural Language Processing (NLP) is known to be a hard problem. In particular, many known neural network verification methods that work for computer vision and other numeric datasets do not…

Formal verification of neural networks is critical for their safe adoption in real-world applications. However, designing a precise and scalable verifier which can handle different activation functions, realistic network architectures and…

A rigorous formalization of desired system requirements is indispensable when performing any verification task. This often limits the application of verification techniques, as writing formal specifications is an error-prone and…

Achieving robust networks is a challenging problem due to its NP-hard nature and complex solution space. Current methods, from handcrafted feature extraction to deep learning, have made progress but remain rigid, requiring manual design and…

Machine learning systems regularly deal with structured data in real-world applications. Unfortunately, such data has been difficult to faithfully represent in a way that most machine learning techniques would expect, i.e. as a real-valued…

In search settings, calibrating the scores during the ranking process to quantities such as click-through rates or relevance levels enhances a system's usefulness and trustworthiness for downstream users. While previous research has…

Enabling robotic assistants to navigate complex environments and locate objects described in free-form language is a critical capability for real-world deployment. While foundation models, particularly Vision-Language Models (VLMs), offer…

Neural network verifiers aim to provide formal guarantees on model behavior, but existing verification benchmarks are fundamentally limited by their lack of ground-truth labels. As a result, verifier evaluation relies on indirect…

Binarized neural networks (BNNs) are feedforward neural networks with binary weights and activation functions. In the context of using a BNN for classification, the verification problem seeks to determine whether a small perturbation of a…

Formal verification of variant requirements has gained much interest in the software product line (SPL) community. Feature diagrams are widely used to model product line variants. However, there is a lack of precisely defined formal…

Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a family of open VLMs designed to jointly optimize efficiency…

Shapley additive explanations (SHAP) are widely recognised as computationally intractable for neural networks, since they induce an exponential search space over the input features. In this work, we take a first step towards scaling exact…