Related papers: EMME: a formal tool for ECMAScript Memory Model Ev…
Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks, showing amazing emergent abilities in recent studies, such as writing poems based on an image. However, it is difficult for these case studies to…
An ideal embodied agent should possess lifelong learning capabilities to handle long-horizon and complex tasks, enabling continuous operation in general environments. This not only requires the agent to accurately accomplish given tasks but…
Processing large numbers of key/value lookups is an integral part of modern server databases and other "Big Data" applications. Prior work has shown that hash table based key/value lookups can benefit significantly from using a dedicated…
Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agents, as it enables them to store, update, and retrieve information over time. This ability…
Static performance estimation is essential during compile-time analysis, yet traditional runtime-based methods are costly and platform-dependent. We investigate mems, the number of memory accesses, as a static and architecture-independent…
In recent years, a number of lightweight programs have been deployed in critical domains, such as in smart contracts based on blockchain technology. Therefore, the security and reliability of such programs should be guaranteed by the most…
The goal of this paper is to help mainstream programmers routinely use formal verification on their smart contracts by 1) proposing a new YAML-format for writing general-purpose formal specifications, 2) demonstrating how a formal…
Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual…
Empirical research on code review processes is increasingly central to understanding software quality and collaboration. However, collecting and analyzing review data remains a time-consuming and technically intensive task. Most researchers…
Large Language Models (LLMs) falter in multi-step interactions -- often hallucinating, repeating actions, or misinterpreting user corrections -- due to reliance on linear, unstructured context. This fragility stems from the lack of…
The JavaScript programming language, which began as a simple scripting language for the Web, has become ubiquitous, spanning desktop, mobile, and server applications. This increase in usage has made JavaScript an attractive target for…
Machine learning models deployed on edge devices have enabled numerous exciting new applications, such as humanoid robots, AR glasses, and autonomous vehicles. However, the computing resources available on these edge devices are not…
Many applications require that we learn the parameters of a model from data. EM is a method used to learn the parameters of probabilistic models for which the data for some of the variables in the models is either missing or hidden. There…
While current large language models (LLMs) perform well on many knowledge-related tasks, they are limited by relying on their parameters as an implicit storage mechanism. As a result, they struggle with memorizing rare events and with…
JavaScript's widespread adoption has made it an attractive target for malicious attackers who employ sophisticated obfuscation techniques to conceal harmful code. Current deobfuscation tools suffer from critical limitations that severely…
While using formal methods offers advantages over unit testing, their steep learning curve can be daunting to developers and can be a major impediment to widespread adoption. To support integration into an industrial software engineering…
As Large Language Models (LLMs) evolve from static dialogue interfaces to autonomous general agents, effective memory is paramount to ensuring long-term consistency. However, existing benchmarks primarily focus on casual conversation or…
The EM algorithm is a method for finding the maximum likelihood estimate of a model in the presence of missing data. Unfortunately, EM does not produce a parameter covariance matrix for standard errors. Supplemented EM (SEM; Meng & Rubin,…
Informal mathematics has been central to modern large language model (LLM) reasoning, offering flexibility and enabling efficient construction of arguments. However, purely informal reasoning is prone to logical gaps and subtle errors that…
The HSA Foundation has produced the HSA Platform System Architecture Specification that goes a long way towards addressing the need for a clear and consistent method for specifying weakly consistent memory. HSA is specified in a natural…