Knowledge editing is a technique for efficiently and accurately updating the knowledge of large language models (LLMs) to alleviate obsolescence and correct errors. However, most existing methods overfit to specific models, causing edited knowledge to be discarded during each LLM update and requiring frequent re-editing, which is particularly burdensome in today's rapidly evolving open-source community. To address this issue, we propose the problem of cross-model knowledge editing and introduce MindBridge, a scalable solution inspired by the low coupling between modality processing and LLMs in multi-modal models. MindBridge introduces the novel concept of memory modality, which encodes edited knowledge as an independent modality. It first performs LLM-agnostic pre-training of the memory modality and then integrates it with various LLMs. Extensive experiments on multiple LLMs and popular knowledge editing datasets demonstrate that MindBridge achieves superior performance even in editing tens of thousands of knowledge entries and can flexibly adapt to different LLMs. Our code is available at https://github.com/CrashBugger/MindBridge.

Brain decoding, a pivotal field in neuroscience, aims to reconstruct stimuli from acquired brain signals, primarily utilizing functional magnetic resonance imaging (fMRI). Currently, brain decoding is confined to a per-subject-per-model paradigm, limiting its applicability to the same individual for whom the decoding model is trained. This constraint stems from three key challenges: 1) the inherent variability in input dimensions across subjects due to differences in brain size; 2) the unique intrinsic neural patterns, influencing how different individuals perceive and process sensory information; 3) limited data availability for new subjects in real-world scenarios hampers the performance of decoding models. In this paper, we present a novel approach, MindBridge, that achieves cross-subject brain decoding by employing only one model. Our proposed framework establishes a generic paradigm capable of addressing these challenges by introducing biological-inspired aggregation function and novel cyclic fMRI reconstruction mechanism for subject-invariant representation learning. Notably, by cycle reconstruction of fMRI, MindBridge can enable novel fMRI synthesis, which also can serve as pseudo data augmentation. Within the framework, we also devise a novel reset-tuning method for adapting a pretrained model to a new subject. Experimental results demonstrate MindBridge's ability to reconstruct images for multiple subjects, which is competitive with dedicated subject-specific models. Furthermore, with limited data for a new subject, we achieve a high level of decoding accuracy, surpassing that of subject-specific models. This advancement in cross-subject brain decoding suggests promising directions for wider applications in neuroscience and indicates potential for more efficient utilization of limited fMRI data in real-world scenarios. Project page: https://littlepure2333.github.io/MindBridge

MindBridge surfaces unintentional error and fraud across your financial data in a way that auditors, finance professionals, and accountants can easily find and understand.

Ottawa-based MindBridge Analytics announced, on Wednesday, a partnership with the Bank of Canada that will see the FinTech and AI startup participate in a proof-of-concept project to track payment transactions. "Working alongside a leading central bank accelerates MindBridge's capabilities in delivering impactful solutions." Through the partnership, Bank of Canada will utilize MindBridge's AI platform, which analyzes large datasets to detect deviating patterns of activity and errors. The financial institution is hoping to develop an AI solution that can spot abnormalities in payment transactions. A core function of the Bank of Canada is to provide funds-management services to the Government of Canada, as well as other customers.

Becky Shields, partner at top 20 firm Moore Kingston Smith, is passionate about the potential of technology in the accounting profession. In her 13 years at the firm, she has focused on IT, and now chairs an IT committee at the ICAEW as well as playing a key role in Engine B, the consortium run by ex-KPMG luminary Shamus Rae. It looks at how the digital revolution impacts on professional services. For three years, Moore Kingston Smith has used the AI MindBridge software for its audits. Here, in this two-part interview, she shares her thoughts on how the technology has improved the offering Moore Kingston Smith can give its clients, the future of audit, and how close we are to real time advisory.

This Privacy Policy describes how we collect, store, use and distribute information about visitors and users of our Website and the App and personal information contained in User Content (collectively the "Services"). Terms used in this Privacy Policy have the same meaning as given to them in our Terms of Use. This policy only applies to information that is provided to us by visitors of our Website or users of our Services about themselves. We act as the controller of that information. To the extent that our Services are used to process any Personal Information (as defined below) we act as a data processor, and the terms of our Data Processing Addendum applies in respect of our processing that personal information on behalf of the data controller.

The word "chaos" comes up often in an interview with Solon Angel, founder and chief strategy officer of Mindbridge Analytics Inc. He grew up in the Caribbean and France, where he dealt with discrimination, family instability and violence. Today the Ottawa-based entrepreneur says he's "comfortable" with the other kind of chaos, that which comes naturally in a tech startup. After the 2008 global financial crisis, Mr. Angel aimed to come up with something that might keep it from happening again. In 2015, he launched Mindbridge with the goal of transforming the financial auditing business with machine learning, or artificial intelligence.

I was talking to a banking compliance executive recently about how banks are looking to use artificial intelligence to spot clues to crimes being committed by customers or employees. This executive was clearly not buying into the hype. "We've thought about that, but we don't plan to use it at this time," she said. "There's too much risk of innocent people getting caught up in a dragnet." An AI engine could find a pattern of transactions or behavior among law-abiding customers that mimics money laundering or some other crime.