Category
2,370 papers
🌟 Summary v8.4.172 makes oriented-box cropping work as expected and improves reliability across model training, export, dataset handling, and deployment. 📊 Key Changes Rotation-aligned OBB crops: save_crop=True and ObjectCropper now save crops upright and aligned to each oriented bounding box. Areas extending beyond...
Graphs represent pairwise relations through vertices and edges, whereas hypergraphs capture multi-way interactions by allowing each hyperedge to connect an arbitrary number of vertices. Superhypergraphs extend this representation through an iterated powerset construction, enabling nested, multi-level relations in which...
The Tier-0 Condition-Monitoring Gate: An Out-of-Sample Test of a Frozen Single-Token Encoder in Industrial Predictive Maintenance Randolph James Ferlic, M.D. and Kimberly Kate Ferlic — Fieldstone Analytics, LLC, Austin, TX, USA Preprint · Zenodo DOI: 10.5281/zenodo.23127675 · CC-BY 4.0 · Community: spiral-domain-encode...
The Tier-0 Condition-Monitoring Gate: An Out-of-Sample Test of a Frozen Single-Token Encoder in Industrial Predictive Maintenance Randolph James Ferlic, M.D. and Kimberly Kate Ferlic — Fieldstone Analytics, LLC, Austin, TX, USA Preprint · Zenodo DOI: 10.5281/zenodo.23127675 · CC-BY 4.0 · Community: spiral-domain-encode...
Reach audiences
Advertise in front of researchers, engineers, and readers.
# Phantom Vision Lab — a computational instrument for perturbing an image-analysis pipeline and measuring how its output changes **A deterministic structured-light stimulus generator paired with a fixed classical computer-vision pipeline, used to measure how much the pipeline's own output moves when 11 computational pa...
This paper presents a comparative analysis of MobileNetV2 and EfficientNetB0 for face and fingerprint recognition in amachine learning-enhanced access control system. The study was developed within an edge computing security frameworkwhere biometric verification was integrated with contextual risk analysis and Chinese...
AbstractDeep neural networks deployed in edge-computing perception layers are the backbone of modernautonomous driving systems. While the state-of-the-art YOLOv12 architecture family deliversunprecedented real-time object detection performance, its vulnerability to sophisticated adversarialmanipulation remains a critic...
From Covering-Edge Descent Complexes to Functorial Presheaves and Coherence Defects (PO-001) Subtitle: Strict Functorial Completion, Coboundary-Curvature Duality, and the Finite Obstruction Boundary Abstract Covering-edge descent data on a finite poset assigns restriction maps only to adjacent comparable elements. A st...
Supplementary code and materials for 'SurfaceRecipe: Information-Efficient Mesh Surface Representation for Lightweight 3-D Shape Classification' (submitted to Computers and Graphics). SurfaceRecipe is a lightweight, mesh-informed 3-D shape classifier organised around a continuous geometric evidence signal. It builds fi...
We construct a sequential measurement protocol on the n=8 Fibonacci-anyon fusion space of dimension D = F₇ = 13 whose CHSH-form expectation value attains |S| = 3.406, above the value 2√2≈ 2.828 that bounds CHSH correlations under the standard setting-locality precondition, which this construction does not satisfy. The...
Bug-fix release associated with the revision of "Computing Left Eigenvalues of Quaternion Matrices". uses scale-aware relative residual acceptance fixes zero-eigenvalue/nullspace edge cases fixes the multiplication side in the polishing Jacobian improves diagonal-shortcut, trial-budget, and backtracking safety adds res...
pysurfacefun 2.0.0 rebuilds the solver core. Code written for 1.0.1 should run without changes: the 1.0.1 test suite passes on 2.0.0 unmodified. What's new Quadrilateral and triangular patches now share one HPS fast direct solver, and its merges follow a nested dissection of the patch graph. On the Rhino cow mesh (339...
By rethinking how large cloud computing systems operate, Associate Professor Christina Delimitrou seeks to make data centers more energy efficient.
An ongoing survey tracks the latest AI accelerator systems to keep hardware relevant for Lincoln Laboratory staff and sponsors.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Associate Professor Cathy Wu uses reinforcement learning to help map out improvements to transportation and other multifaceted systems.
Announcing Gemini 4 Argon, our frontier model for real-world coding, enterprise knowledge work and cyber defense, rolling out soon.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
