Category
232 papers
This article introduces KirchhoffNet, a novel class of neural network models inspired by the principles of analog electronic circuitry, specifically Kirchhoff’s laws. KirchhoffNet operates as an analog circuit, where the network input is represented by initial node voltages, and the output corresponds to the node voltages at a specific time. The dynamics of the node voltages are governed by learnable parameters on the edges, and the evolution of these voltages follows a system of ordinary differential equations (ODEs). Despite the absence of traditional neural network components such as convolutional layers, KirchhoffNet achieves outstanding performance across a wide range of machine-learning tasks. We further demonstrate that KirchhoffNet is capable of computing diffusion models, making it a promising candidate for accelerating modern generative AI applications. Most notably, KirchhoffNet can be implemented as a high-speed & low-power analog integrated circuit, which introduces a compelling advantage: irrespective of the number of parameters in the network, its on-chip forward calculation can always be completed within a short time. This property makes KirchhoffNet a highly attractive and scalable paradigm for implementing large-scale neural networks, opening new avenues in the realm of analog neural networks for artificial intelligence (AI).
The Interactions website (interactions.acm.org) hosts a stable of bloggers who share insights and observations on HCI, often challenging current practices. Each issue we'll publish selected posts from some of the leading and emerging voices in the field.
Generative AI is again changing public understanding of what kind of tool a computer can be, much as personal computing, the internet, smartphones and web search did before it. Policy makers have accordingly recognised a need for “AI literacy,” yet definitions of that literacy are frequently shaped by businesses whose motivation is to cultivate a new generation of customers. This paper argues for alternative foundations. It proposes that information theory and Bayesian statistics deserve greater emphasis in the curriculum than they currently receive, that the everyday experience of end-user programming is a more honest starting point than the rhetoric of conversational “agents,” and that the proper aim of AI education is to form critical technical practitioners rather than compliant consumers
Reach audiences
Advertise in front of researchers, engineers, and readers.
DevJourney is presented, a Generative AI-powered educational game that supports experiential and adaptive learning and highlights the potential of AI-enhanced game-based learning to strengthen software engineering education and better prepare students for industry practice.
A theory-oriented framework that integrates KDD, knowledge-creation theory, human-AI collaboration, responsible generative AI, and epistemological reflection into a single-layered ecology is proposed.
This review traces the development of the field from classical machine learning and deep learning to generative models, transfer learning, transformers, and emerging foundation models, and introduces major nanophotonic platforms.
A narrative review of the available evidence presents a narrative review of the available evidence on the effect of LLMs on diagnostic reasoning, the optimal design of clinician-LLM interaction, the appropriate timing of consultation during the clinical encounter, the safest models of clinical-AI integration, and the main risks associated with their use.
The proposed GenAI Responsible Adoption Framework for Vietnamese Higher Education (GRAV-HE) comprises four interdependent dimensions: ethical policy and AI disclosure, data governance and secure infrastructure, pedagogical transformation, and comprehensive AI literacy.
This work introduces MotionPhys, a lightweight and interpretable framework that treats sparse motion trajectories as physical evidence rather than relying on appearance artifacts or generator-specific traces and reveals subtle motion inconsistencies that are difficult to capture with conventional visual cues and transforms them into a compact representation for efficient detection.
ClinX is introduced, an end-to-end multimodal PHI sanitization framework for medical image-text data, and results show that OCR-only masking is not sufficient as a standalone solution, and restoration-based sanitization better preserves clinically relevant visual context while sharply reducing recoverable PHI.
Based on the results of all evaluations performed, it has been found that AI-based adaptive learning systems provide greater motivation, more successfully comprehend course content, and a higher level of academic performance compared to the use of traditional mobile learning apps.
Earth AI
Piloting the world's first double-blind AI evaluations
The “CrysVCD” tool developed at MIT could cut the huge amounts of time and money spent on screening out chemically unstable designs.
Generative AI
Google DeepMind partners with game studios to prototype breakthrough AI gameplay.
