Related papers: Towards Verifiable Transformers: Solver-Checkable …

The efficiency of modern optimization methods, coupled with increasing computational resources, has led to the possibility of real-time optimization algorithms acting in safety critical roles. There is a considerable body of mathematical…

The companion paper introduced a four-level verification lattice on agent-skill manifests (unverified, declared, tested, formal) and left the top level aspirational. This paper closes that gap. We give a precise semantics for skill…

Single-cell foundation models (scFMs) have demonstrated state-of-the-art performance on various tasks, such as cell-type annotation and perturbation response prediction, by learning gene regulatory networks from large-scale transcriptome…

The fields of explainable AI and mechanistic interpretability aim to uncover the internal structure of neural networks, with circuit discovery as a central tool for understanding model computations. Existing approaches, however, rely on…

In the field of robotics, researchers face a critical challenge in ensuring reliable and efficient task planning. Verifying high-level task plans before execution significantly reduces errors and enhance the overall performance of these…

While transformer-based models have achieved state-of-the-art results in a variety of classification and generation tasks, their black-box nature makes them challenging for interpretability. In this work, we present a novel visual…

Transformer language models are neural networks used for a wide variety of tasks concerning natural language, including some that also require logical reasoning. However, a transformer model may easily learn spurious patterns in the data,…

We present a new approach to automated reasoning about higher-order programs by endowing symbolic execution with a notion of higher-order, symbolic values. Our approach is sound and relatively complete with respect to a first-order solver…

Transformers are being used extensively across several sequence modeling tasks. Significant research effort has been devoted to experimentally probe the inner workings of Transformers. However, our conceptual and theoretical understanding…

Verification of modern microprocessors is a complex task that requires a substantial allocation of resources. Despite significant progress in formal verification, the goal of complete verification of an industrial design has not been…

Semantic communications utilize the transceiver computing resources to alleviate scarce transmission resources, such as bandwidth and energy. Although the conventional deep learning (DL) based designs may achieve certain transmission…

Recently, Transformer-based architectures have been explored for speaker embedding extraction. Although the Transformer employs the self-attention mechanism to efficiently model the global interaction between token embeddings, it is…

Prior studies investigating the internal workings of LLMs have uncovered sparse subnetworks, often referred to as circuits, that are responsible for performing specific tasks. Additionally, it has been shown that model performance…

In previous work, we proposed a method for leveraging efficient classical simulation algorithms to aid in the analysis of large-scale fault tolerant circuits implemented on hypothetical quantum information processors. Here, we extend those…

Logs of real-life processes often feature uncertainty pertaining the recorded timestamps, data values, and/or events. We consider the problem of checking conformance of uncertain logs against data-aware reference processes. Specifically, we…

Software contracts allow programmers to state rich program properties using the full expressive power of an object language. However, since they are enforced at runtime, monitoring contracts imposes significant overhead and delays error…

The increasing use of deep neural networks for safety-critical applications, such as autonomous driving and flight control, raises concerns about their safety and reliability. Formal verification can address these concerns by guaranteeing…

Quantum computations are expressed in general as quantum circuits, which are specified by ordered lists of quantum gates. The resulting specifications are used during the optimisation and execution of the expressed computations. However,…

Interrupts have been widely used in safety-critical computer systems to handle outside stimuli and interact with the hardware, but reasoning about interrupt-driven software remains a difficult task. Although a number of static verification…

In the field of source code processing, the transformer-based representation models have shown great powerfulness and have achieved state-of-the-art (SOTA) performance in many tasks. Although the transformer models process the sequential…