Preprint: GLAD leads most measures in two industrial benchmarks
The multi-view system restricts cross-view information and is reported as best on nine of 10 Real-IAD measures and all 10 MANTA-Tiny measures.
Search
2,451 results
1001–1020
Preprint tests a pay-for-filtering plan against BGP hijacks
Simulations found broad monitor visibility and concentrated rewards, while leaving the bounty needed for participation and the market equilibrium unresolved.
AI models reveal a shifting geometric signal for grammar
Preprint analysis finds that closed-class word neighborhoods expand and contract earlier than open-class neighborhoods across transformer layers.
Learned controller tracks soft-robot paths in a lab test
Preprint: A data-driven controller followed prescribed and user-guided paths, maintained clearance from a dynamic obstacle and tested local stability on one three-bellows actuator.
A Turbulence Model Tests a New Route to Anomalous Scaling
Preprint: A nonlinear stochastic cascade calculation derives a weak-noise correction to scaling exponents and finds numerical support for the theory.
A geometry iteration is stable near a three-circle target
Preprint: The analysis finds local convergence for a Malfatti configuration, but leaves global behavior unresolved.
Preprint: AI Flags 14,426 Likely Young Stars in APOGEE Data
The model recovered most labeled cool stars, but its performance fell sharply for hotter stars, and the training labels were not definitive ground truth.
Spatial model maps patterns in brain tissue and African vegetation data
A preprint reports a spatial factor method designed to scale with the number of locations, tested on brain tissue and African vegetation data.
New Protocol Links Communication to Differences Between Strings
Preprint: A theorem describes a randomized protocol that uses O(k log^3 n) bits and O(n) time under stated assumptions.
Coding agents moved fast, but the software needed more guardrails
Preprint: A 20-week software project used coding agents at high speed while building a much larger layer of models, checks and controls.
Preprint finds alternating regret rates for experts and online convex problems
The proof-based analysis finds a horizon-independent logarithmic expert rate and matching dimension-horizon bounds for online convex optimization.
AI model groups speech by meaning, emotion and background noise
Preprint: AudioLens-R1 scored higher than competing audio systems, but the evaluation used synthesized speech and controlled paralinguistic features.
No-Code AI Tool Shows Higher Crack Recall in Tungsten Test
This preprint reports that YOLOEZ combines labeling, training and inference in a code-free interface, but a small benchmark found a tradeoff between catching cracks and avoiding incorrect detections.
AI tutor handled correctness better than completeness in Java CS1 pilot
This preprint reports a pilot with eight Java students in which an LLM grader tracked correctness better than explanation completeness, while learning evidence remained preliminary.
Learning method separates interaction and environmental forces
Preprint: In synthetic collective-dynamics tests, the method recovered interaction laws, improved environmental-force estimates, and selected among candidate models.
Proof finds nonnegative partial-wave coefficients through 26 dimensions
A preprint reports an exact analysis of the bosonic Veneziano amplitude, finding nonnegative coefficients for every mass level and allowed spin in dimensions above 3 and up to 26.
Vector search study finds average scores can hide weak queries
Preprint: A benchmark across four workloads found that query-aware tuning raised the share of searches meeting recall targets and often improved speed.
Language model identifies PDE terms more accurately from summaries
Preprint: In a 44-sample simulation benchmark, a frozen QwQ-32B model recorded higher PDE-term recovery scores from compact physical measurements than from raw field slices.
Hubble Scan Tests Find Tens-of-Parts-Per-Million Precision
Preprint: STIS spatial scanning showed strong broad-band stability, but red spectral bins and a puzzling wavelength trend need further testing.
BanglaMamba Uses Less GPU Memory but Trails BanglaBERT
Preprint compares three Bangla fake-news models and finds a trade-off between classification scores, speed and memory use.