Model predicts parallel search times before files are opened
A computational framework matched simulations closely in a design case, but its estimates became much less reliable in some low-capacity settings.
Scientific publication5 min read
Research field
Technology & Engineering
Artificial intelligence, computing, robotics, energy, and engineering.
913 published articles3 subjects
Latest in Technology
A new kernel method shows lower errors in multiscale PDE tests
A preprint describes a Frame Kernel Method for learning partial differential equations with multiple spatial scales. It reports the lowest error on most tested benchmark problems, while its proposed explanation for unusually fast convergence remains a conjecture.
Scientific publication4 min read
Preprint reports strong results for a multimodal UAV vision system
An arXiv preprint reports that its alignment-first model posted top or near-top scores across several UAV and remote-sensing benchmarks, while broader sensor settings remain untested.
Scientific publication3 min read
Preprint reports near-linear bounds for Khatri-Rao sketches
A theoretical analysis says Khatri-Rao sketches can reach a nearly linear dependence on subspace dimension, narrowing a gap with unstructured random sketches.
Scientific publication4 min read
Verifier-guided method posts higher scores in long AI tasks
A verifier-based method recorded sizable gains over outcome-level GRPO on ALFWorld and WebShop, while its audits showed that proof-based credit was sometimes unavailable.
Scientific publication4 min read
Preprint links softmax attention rank to interaction geometry
An arXiv preprint combines a worst-case analysis of softmax approximation rank with a limited learned-head audit, finding a sharp intrinsic geometry law but no added held-out signal from native coordinates.
Scientific publication5 min read
AI Video Model Reports Tighter Camera Control in Tests
The computer-vision model reported lower camera-motion errors than tested baselines and broadly comparable visual quality, but its rankings depend on the evaluation setup.
Scientific publication4 min read
AI Training Filter Reports Higher Math and Code Scores
An arXiv preprint reports higher math and code benchmark averages for a reward-aligned trajectory filter, with total training time close to standard on-policy distillation.
Scientific publication4 min read
AI controller keeps GSM8K accuracy near full budget with far less reasoning
A preprint presents AERA, a controller that estimates whether more reasoning may help and reports near-baseline GSM8K accuracy with sharply lower generation use.
Scientific publication5 min read
BERT leads test of sector-aware cyber threat intelligence routing
A preprint reports that BERT had the strongest overall scores for assigning cyber threat intelligence events to sectors, with a caveat about unequal sector coverage.
Scientific publication4 min read
Preprint method tracks artery motion better in 4D heart scans
CMGR outperformed three registration methods on right coronary artery motion in XCAT simulations and selected clinical pairs, while whole-volume results were less consistent.
Scientific publication5 min read
openJiuwen posts higher scores than selected systems on two coding tests
An open-source harness for long-horizon coding agents scored above selected systems on two benchmarks, but the study did not isolate the harness from model, prompt, tool and implementation differences.
Scientific publication4 min read
AI framework recovers C from binaries, but behavior still slips
A test-suite-free framework built around an AI model produced C candidates that often compiled and matched held-out input-output checks, but the benchmark also exposed false acceptances and weaker results on stripped binaries.
Scientific publication4 min read
AI training method reports gains on harder mathematics problems
A method called DA3PO was reported to outperform GRPO, DAPO and GSPO on mathematical reasoning benchmarks, though the tests covered only two Qwen3 base models and did not report uncertainty estimates.
Scientific publication4 min read
AI agents that adapt teamwork report higher reasoning scores
A preprint describes an AI system that retrieves evidence before choosing how its agents collaborate. It reports higher scores across seven reasoning benchmarks, but the evidence comes from in-silico evaluations rather than human users or real-world deployments.
Scientific publication4 min read
Analysis Says Tree Search and Monte Carlo Control Share a Core
A conceptual note argues that Monte Carlo Tree Search can be understood as every-visit Monte Carlo control when the comparison is limited to trajectory sampling and Monte Carlo action-value updating. The claim clarifies terminology and computational scope, but does not compare performance.
Scientific publication4 min read
New Preprint Simplifies Analysis of a Randomized Integration Method
A theoretical preprint offers a direct Haar-based analysis of randomized quasi-Monte Carlo integration and derives an expected squared-error bound under specified function assumptions, but reports no experiments.
Scientific publication4 min read
A model combining speech and gaze better predicts turn-taking
A secondary analysis of four-person conversations reported that combining speech intensity, gaze and perceived interpersonal closeness distinguished gaps from overlaps better than gaze alone, including in noisy conditions.
Scientific publication4 min read
Preprint: Compact latent hubs lead four recommendation tasks
HubMixer sends recommendation features through compact learned hubs before mixing them and writing them back to individual tokens. The preprint reports the best offline AUC on four objectives, fewer parameters than RankMixer and TokenMixer, and a 5.48% online conversion improvement before full deployment in the tested business.
Scientific publication4 min read
AI Control Room Test Tracks Commands, Replays and Agent Moves
A preprint reports that GOD linked browser commands to execution records, replay checks and portable packs in 15 completed run slots. The evaluation focused on command, replay and artifact checks, not human or social validity.
Scientific publication4 min read
Video AI Keeps Nearly All Benchmark Performance With Fewer Tokens
A new arXiv preprint reports that a coding-inspired system kept average benchmark performance close to the uncompressed setup while using 25% of the visual-token budget on Qwen3-VL-8B.
Scientific publication3 min read
Flow-matching shortcuts aid training but miss exact likelihoods
A theoretical and synthetic analysis finds that conditional flow matching can replace endpoint likelihood calculations only when specific residual errors cancel. In on-policy training, the shortcut may still improve reward even when its likelihood ratios are far from exact.
Scientific publication5 min read
Preprint Reports Fuzzers Reach More Bugs Than They Trigger
An updated Magma benchmark separates reaching a bug, satisfying its trigger condition, and detecting the resulting fault. In reported 24-hour campaigns, 77 of 127 bugs were reached and 43 were triggered, while AFL++ recorded the highest observed trigger count.
Scientific publication4 min read
AI method flags answers that may outrun their evidence
Twin Worlds compares answers before and after controlled entity substitutions, using inconsistent changes as a reason to withhold an answer.
Scientific publication4 min read
Text Models Spot Evasion Better Than They Read Vocal Confidence
Models performed strongly on written signs of evasion but struggled more with vocal unconfidence, and speaker-level calibration helped only modestly.
Scientific publication4 min read
Brain MRI Review Finds Safety Checks Rarely Test Small Lesions
A systematic review finds that most deep-learning brain MRI reconstruction studies did not compare image-fidelity scores with radiologist assessments on the same data, leaving key safety questions unanswered.
Scientific publication4 min read
Medical AI method links uncertainty to features in each prediction
A preprint introduces egRUE, a method that combines uncertainty scoring with feature-level explanations; its reported gains came from benchmark tests and a small BloodMNIST expert study.
Scientific publication5 min read
AI Models Struggle to Rebuild How Chinese Internet Words Are Made
A new benchmark finds that language models often handle the meaning of Chinese internet neologisms better than the sounds, characters and source forms used to create them.
Scientific publication5 min read
MPC method bounds disturbance reserve before full solve
A new preprint reports a method that builds lower and upper disturbance-reserve bounds, reaches exactness after finite expansions and delivers benchmark speedups over warm-started full solves.
Scientific publication4 min read
New bounds map a threshold in composite hypothesis testing
An arXiv preprint presents a unified Rényi framework for composite binary testing, combining finite-sample bounds with asymptotic results that separate two Type II error regimes.
Scientific publication4 min read
AI model scores higher at finding camouflaged copper-tube defects
CF-YOLO, a YOLOv11-based detector built to refine context and fine detail, scored higher than YOLOv11n on CTDD but delivered mixed results on external NEU-DET data.
Scientific publication4 min read
RISC-V FFT Tests Show juFFTe Gains, While Zen 5 Leads
Benchmark tests on three RVV 1.0 RISC-V CPU configurations found that juFFTe's gains varied by hardware, with a reported threefold average speedup on the SG2044 multi-core comparison, while AMD Zen 5 led across the full range.
Scientific publication4 min read
Wireless AI System Cuts Image Data by Generating Missing Tokens
The system sends a short token prefix and generates the untransmitted tail at the receiver, trading communication overhead for computation.
Scientific publication5 min read
Simple color forecast beat trained models on unseen copper
A tiny two-recording test found that a parameter-free color extrapolator beat copying the last frame and every trained comparator on held-out copper in both directions. The air-to-chamber advantage was individually separated from zero, while the chamber-to-air interval included zero.
Scientific publication5 min read
Robot Study Finds Gesture Commands Hold Up Better in Unseen Tests
An evaluation in simulation and on a physical robot found that one shared interface could support three instruction modes, with gesture-based modes often performing better when wording, surfaces or objects changed.
Scientific publication4 min read
Preprint reports higher LLM scores with NVFP4 scale refinement
H-Scale uses calibration activations to choose hardware-valid NVFP4 scales, with higher average scores reported across Qwen3 and LLaMA tests but a narrow evaluation scope.
Scientific publication4 min read
Adaptive forecast weighting leads three datasets, but not all
Gibbs-family methods led the aggregate scores in Traffic Hourly, Electricity Hourly and Solar Weekly, but classical baselines remained on top in some M4 frequency and disagreement groups.
Scientific publication4 min read
Robot video models can look right while getting the scene wrong
An arXiv preprint proposes a 3D-grounded test for robot video models. Cosmos led composite scores, but detailed checks found weaker object localization and trajectory accuracy, underscoring the gap between plausible footage and executable behavior.
Scientific publication5 min read
New analysis puts a strict prime-power limit on bent partitions
A theoretical result forces the number of cells in a bent partition to be a prime power and narrows its exponent using the dimension of the underlying finite space.
Scientific publication4 min read
Video AI Retains Near-Full Scores With Just 10% of Visual Tokens
A video AI method called Token-Budget Distillation retained strong benchmark scores after aggressive visual-token compression, although its training still depended on the uncompressed teacher model.
Scientific publication5 min read