This record contains the manuscript “Weights Learn Experiences, Structures Crystallize Knowledge: Trace-Governed Structural Plasticity for Continual Learning — A Controlled Proof-of-Mechanism Study”. The paper investigates whether repeated explicit reasoning can alter a learner’s computation graph, not only its numeric...
Zhongren Wang· Zenodo (CERN European Organi...· 0 citations
A formal verification of the math of modern deep learning, written as a Lean 4 blueprint project and shipped as the code it proves. Mathlib's fderiv is the foundation; every layer's backward is derived as a vector-Jacobian product rather than asserted -- dense, ReLU, softmax cross-entropy, 2D convolution, max-pool, Bat...
Brett Koonce· Zenodo (CERN European Organi...· 0 citations
Machine-learning interatomic potentials of several functional forms now support large-scale atomistic simulation.Within this landscape, graph neural network (GNN) potentials such as M3GNet offer transferable message-passing models, but their application to very large systems remains limited by graph construction, messa...
The demand for intelligent operation and maintenance of urban drainage network continues to increase, and the rapid and accurate identification of blockage state has become a key issue in urban drainage security. Aiming at the limitation of insufficient description of pipe network topology association, local propagatio...
Underwater wireless sensor networks (UWSN) are characterized by dynamic network topology, limited node energy, and constrained communication capabilities, which make reliable and energy-efficient data transmission a significant challenge in time-varying underwater environments. Conventional routing approaches, usually...
Cai-Xia Cai, Chao-Yun Pu, Wen-Yang Gan et al.· Ocean Engineering· 0 citations
Mechanistic understanding and rational design of complex chemical systems depend on fast and accurate predictions of electronic structures beyond individual building blocks. However, if the system exceeds hundreds of atoms, first-principles quantum mechanical (QM) modeling becomes impractical. In this study, we develop...
Dieaa Alhmoud, Yili Shen, Cheng-Wei Ju et al.· AIP Publishing· 0 citations
DrugVision is an AI-based clinical decision support platform designed to enhance medication safety and detect adverse drug interactions. The system integrates a convolutional neural network ensemble (ResNet-50, EfficientNet-B0, MobileNetV3) for solid oral dosage form identification, transformer-augmented OCR for handwr...
Heet Ruparel, Preet Ravaria, Kishan Rathod et al.· Zenodo (CERN European Organi...· 0 citations
An evaluation protocol for multi-view molecular property prediction, and a fusion architecture measured under it. Eight MoleculeNet datasets, six scaffold splits (the DeepChem canonical split plus five seeded), paired comparisons with Holm correction, an across-dataset test and an equivalence test, split-conformal unce...
Aarya Sharma· Zenodo (CERN European Organi...· 0 citations
This record contains the datasets, trained graph neural network models, and source code supporting the manuscript “Enhancing protein binding site residue prediction with graph neural networks: impacts of cutoff distance and feature selection.”
Serena H. Chen· Zenodo (CERN European Organi...· 0 citations
VR-based AO+MI paradigm is found to enhance sensorimotor connectivity and promote large-scale network integration, indicating more coordinated neural dynamics during MI tasks, and a hierarchical graph learning framework tailored for VR-based MI decoding is proposed.
Kai-Yue Du, Wen-Wen Chang, Wei-Xuan Kong et al.· Journal of Neural Engineerin...· 0 citations
Assistant Professor Pat Pataranutaporn describes a new interface that lets everyday users glimpse inside an AI's neural network before their chatbot ever says a word.
Microsoft Research Blog· microsoft.comJul 13, 2026
Cryptographic code supports vital protections in modern computing systems. Learn how a new method helps verify code as developers write it while preserving speed and adaptability as it gets implemented and evolves. The post Verifying Rust cryptography in SymCrypt, from standards to code appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduJul 6, 2026
PhD student Rachel Sava, winner of the Envisioning the Future of Computing Prize, explores transformative improvements and dystopian risks of neural technology.
