Related papers: CIRCUITSYNTH: Leveraging Large Language Models for…

Reversible logic circuits have been historically motivated by theoretical research in low-power electronics as well as practical improvement of bit-manipulation transforms in cryptography and computer graphics. Recently, reversible circuits…

Large language model (LLM) self-correction -- the ability to detect and fix errors in generated outputs -- remains largely ad hoc, relying on generic prompts such as "please reconsider your answer" without systematic error analysis or…

The scarcity of domain-specific dialogue datasets limits the development of dialogue systems across applications. Existing research is constrained by general or niche datasets that lack sufficient scale for training dialogue systems. To…

Large language model (LLM)-based agents are increasingly used to solve complex tasks involving tool use, such as web browsing, code execution, and data analysis. However, current evaluation benchmarks do not adequately assess their ability…

Automated unit test generation is critical for software quality but traditional structure-driven methods often lack the semantic understanding required to produce realistic inputs and oracles. Large language models (LLMs) address this…

Reversible or information-lossless circuits have applications in digital signal processing, communication, computer graphics and cryptography. They are also a fundamental requirement in the emerging field of quantum computation. We…

This paper presents an algorithmic framework for control synthesis of continuous dynamical systems subject to signal temporal logic (STL) specifications. We propose a novel algorithm to obtain a time-partitioned finite automaton from an STL…

Automatic synthesis from temporal logic specifications is an attractive alternative to manual system design, due to its ability to generate correct-by-construction implementations from high-level specifications. Due to the high complexity…

Pretraining robust vision or multimodal foundation models (e.g., CLIP) relies on large-scale datasets that may be noisy, potentially misaligned, and have long-tail distributions. Previous works have shown promising results in augmenting…

Implementing Boolean functions with circuits consisting of logic gates is fundamental in digital computer design. However, the implemented circuit must be exactly equivalent, which hinders generative neural approaches on this task due to…

This paper presents an automatic layout generation framework in advanced CMOS technologies. The framework extends the template-and-grid-based layout generation methodology with the following additional techniques applied to produce optimal…

Time series forecasting is a fundamental tool with wide ranging applications, yet recent debates question whether complex nonlinear architectures truly outperform simple linear models. Prior claims of dominance of the linear model often…

Dynamic quantum circuits incorporate mid-circuit measurements and feed-forward operations originally intended to realize Quantum Error Correction. This paradigm has recently been utilized to prepare certain states and long-range entangling…

Synthesizing a reactive system from specifications given in linear temporal logic (LTL) is a classical problem, finding its applications in safety-critical systems design. These systems are typically represented using either Mealy machines…

Smart contracts are small but highly error-prone programs that implement agreements between multiple parties. We present a reactive synthesis approach for the automatic construction of smart contract state machines. Towards this end, we…

In recent years, with the rapid advancements in large language models (LLMs), achieving excellent empathetic response capabilities has become a crucial prerequisite. Consequently, managing and understanding empathetic datasets have gained…

This paper is concerned with the synthesis of RC electrical circuits from physics-based supercapacitor models describing conservation and diffusion relationships. The proposed synthesis procedure uses model discretisation, linearisation,…

Analogies help learners understand unfamiliar concepts by relating them to known concepts. Despite recent advances, large language models (LLMs) continue to struggle to generate analogies of comparable quality to those produced by humans.…

Given a quantum algorithm, it is highly nontrivial to devise an efficient sequence of physical gates implementing the algorithm on real hardware and incorporating topological quantum error correction. In this paper, we present a first step…

Current scientific research witnesses various attempts at applying Large Language Models for scenario generation but is inclined only to comprehensive or dangerous scenarios. In this paper, we seek to build a three-stage framework that not…