Category
5,133 papers
A mathematical theory of superposition in neural networks using tools from frame theory and compressed sensing and a novel characterization of the distribution of signs in the Gram matrix is developed.
It is revealed that the presence of undercoordinated metal atoms close to the semiconductor-oxide interface significantly affects the magnitude of the electronic current and its propagation through MoS2.
Concept-Targeted Attribution (CTA) provides a framework for moving from behavioral probe accuracy to mechanistic explanations of probe performance, enabling more detailed audits of internal concept representations, including safety-critical ones.
This paper examines the closed form of the Wasserstein distance in one dimension via node feature probability distributions, and shows how the transport plans of the Wasserstein and Gromov-Wasserstein distances visualize how mass is shifted to transform one network into another.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces a signed multilayer community detection framework that incorporates both correlated and anti-correlated brain activity to identify subject-specific community structures across tasks and sessions and offers a promising foundation for precision neuroimaging and personalized neuroscience applications.
This work reformulates the output projection followed by top-k token selection as a maximum inner product search over token embeddings and replaces the dense vocabulary projection with an HNSW-based vector index, suggesting approximate retrieval is a practical alternative to dense output projections in latency-sensitive small-batch decoding.
We propose QGPINNs, a physics-informed neural network framework developed in PyTorch for the numerical solution of nonlocal differential equations on quantum graphs. The framework is designed as a general computational implementation in which the solution on each edge of the graph is approximated by a neural network, while a unified graph-based loss function enforces the governing equations together with initial, boundary, and vertex transmission conditions. In particular, the formulation incorporates standard continuity and Kirchhoff-Neumann vertex conditions and Dirichlet boundary conditions into the learning process to couple the local edge-wise neural approximations into a global solution on the graph. The framework is developed for two representative classes of nonlinear models: multi-order fractional elliptic problems and time-fractional evolution equations on quantum graphs. To improve accuracy and training stability, QGPINNs integrates several graph-adapted learning strategies, including soft and hard constraint enforcement, dynamic loss balancing, Fourier feature embeddings, and a learnable singularity-capturing feature for weakly singular solutions arising in the considered problems. The framework also extends naturally to inverse problems, including the identification of the orders of fractional operators and physical parameters from noisy observational data. We validate the accuracy, computational efficiency, and physical consistency of the proposed framework through numerical experiments on benchmark graph structures and real-world networks, including the IEEE 14-bus system and an open-channel agricultural drainage network.
The newly introduced RBAs were among the strongest performing, and by robustly retaining both main effects and 2-way epistatic interactions, these algorithms preserve predictive signals for downstream modeling.
This work proposes Decoder-Aware Representation Tuning via Surgery (DARTS), which employs a novel entropy-weighted L1 loss to upweight correction at high-entropy positions where errors most affect generation quality, and a per-position additive bias that captures position-dependent error without overparameterization.
This work presents Replicant, a deep reinforcement learning framework that learns the realistic task of evasion under a strict label-only black-box threat model and demonstrates that learning the task of evasion not only results in stronger attack performance but provides a better signal for hardening malware detectors.
This work proposes a curvature-conditioned multiscale momentum method with sphere constraints, which significantly accelerates Muon across diverse architectures (dense, MoE) and model sizes (0.12B--2.3B parameters).
Euclidean Fourier neural operators (EFNOs) are proposed as a domain-independent alternative to FNOs and can learn operators that act consistently across periodic domains of varying shape and size by parameterizing the spectral kernel as a continuous function of the physical wavevector.
Education Innovation
Machine Intelligence
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
General Science
GPT-Lab
· gpt-lab.eu
Sep 3, 2026
Adaptive AI agents can help make BIM data more machine-readable by navigating IFC models, interpreting inconsistent information, and mapping it to defined standards. In this blog, Alok Rawat shares findings from a real-world pilot in construction workflows. The post Adaptive AI Agents in Construction Workflows appeared first on GPT-Lab.
Climate & Sustainability
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
