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
Subject
Computing & Robotics
Algorithms, software, networks, cybersecurity, automation, and robotics.
292 published articles7 specialties
Latest in Computing
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
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
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
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
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
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
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
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
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
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
Preprint tests a robot trained to find contact before moving objects
An arXiv preprint tests a multi-critic training method for robots that push and transport objects and open a dishwasher through contact. It reports 94.1% simulation success and 69.0% success in 58 trials on four unseen objects, while the dishwasher test is qualitative.
Scientific publication4 min read
AI Engineering Agents Rechecked More Often With Explicit Guidance
Across 120 slots per condition, first post-edit re-verification appeared in 78.3% of cadence-guided slots and 26.7% of cadence-omitted slots. The same descriptive comparison showed fewer cadence violations and more bounded final successes with the guidance.
Scientific publication4 min read
Less Robot Sharing Linked to More Human Openness
In a randomized experiment, people working with a non-human-shaped robot disclosed more when its small talk contained fewer personal details, while teamwork and coordination ratings were also higher.
Scientific publication4 min read
AI-guided FPGA task mapping reports speed gains in two workloads
An arXiv preprint reports an LLM-assisted workflow for assigning application tasks to a processor or FPGA, with reported speedups up to 92.53 times and repeated partition choices in the tested configurations.
Scientific publication4 min read
Robot system clears every test bin, but grasp success varies
A four-level robotic bin-picking system cleared all 30 experimental bins, while the study found that bin clearance and individual grasp success told different stories.
Scientific publication4 min read
URIUM Course Uses a Small Language to Teach Compiler Design
A preprint presents URIUM as an open, adaptable compiler-design course built around a small language, a staged compiler and several assembly backends.
Scientific publication3 min read
Preprint finds exact shortest code embeddings over finite rings
A preprint by Junmin An and Jon-Lark Kim gives exact formulas for the shortest self-orthogonal and LCD embeddings of linear codes over the ring Fq + uFq.
Scientific publication5 min read
LLM-guided drone searches showed paths up to 52% shorter
A simulated comparison found higher success and shorter routes for an LLM-guided UAV than for a conventional lawn-mower scan, but the evaluation did not test unknown environments.
Scientific publication4 min read
Robot Planner Rejected One in Four Candidates in Tests
A preprint describes MaCoPlanner, a system that turns equipment manuals into structured knowledge, checks robot plans before action, and rejects unresolved candidates. It reported higher success on the hardest benchmark tasks than the listed baselines, but the physical evaluation was small and limited to a no-load simulator.
Scientific publication5 min read
Algorithms offer new guarantees for multi-tier network design
A theoretical preprint proposes algorithms for flexible graph connectivity across several nested tiers. Its main randomized method succeeds with probability at least one third for a fixed number of tiers, while a related multi-graph problem receives a factor-two approximation.
Scientific publication4 min read
Blockchain query system shrinks proof data, but scans still ran faster
A prototype for verifiable blockchain time-series queries sharply reduced the data and client work needed for some checks, but scan-based methods were faster in wall-clock tests and approximate proof savings varied by stream.
Scientific publication4 min read
Layered AI defenses stop tested jailbreaks but reject benign prompts
A preprint study found that failures across LLM defenses were positively correlated, challenging the idea that stacking independent safeguards automatically multiplies protection.
Scientific publication4 min read
False Channel Reports Could Disrupt 6G NOMA Decisions
The preprint maps how false channel-state information could alter power allocation, user ranking, decoding, fairness and secrecy in power-domain NOMA. It offers a qualitative threat taxonomy and impact analysis, but reports no empirical sample or dataset and does not quantify the resulting harm.
Scientific publication4 min read
GaussDB Posts Strong 30TB Score, But Results Are Unaudited
A 30 TB GaussDB TPC-H test reported a composite score 40% above Hologres, alongside smaller tests of execution, networking, Bloom filters and memory use. The paper is an unaudited arXiv preprint.
Scientific publication4 min read
Cybersecurity AI Leads Benchmark With 58.1% CyberGym Score
The CyberFactory framework links data construction, trajectory synthesis and model training, and OpenAegis recorded the highest reported CyberGym score among the compared models.
Scientific publication4 min read
Climate model footprints change sharply with what is counted
A case study of a 5 km Destination Earth simulation compares operational, active-only and life-cycle accounting, showing how each boundary changes the reported energy and carbon totals.
Scientific publication4 min read
Robot Tests Report Higher Success With Visual Tracks
A robotics preprint reports higher task success for a visual-track system in simulation and physical manipulation, along with better future-video prediction scores.
Scientific publication4 min read
Robot sensor network turns readings into machine-readable data
A model-based system for wireless sensor networks produced semantically enriched measurements, while most micro-ontology generation took place within 500 microseconds. Compression depended on the serialization format, and the reported engineering results came from an illustrative robot-based setup.
2020 46th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), Portoroz, Slovenia, 2020, pp. 561-5684 min read
Product-form centers and linear codes match the optimal covering rate
A theoretical analysis finds that generalized covering codes with product-form centers reach the ordinary sphere-covering rate, while linear codes over prime-power alphabets reach the same asymptotic benchmark.
Scientific publication4 min read
Battery-free sensor system reaches every first rendezvous in tests
In simulations and controlled hardware experiments, MagPie completed all reported first rendezvous, while variable energy and imposed clock-loss stress reduced delivery in modeled networks.
Scientific publication5 min read
TailorCoPilot Linked to Higher Novice Success in Pattern Tests
A 20-person comparison reported higher task-success odds, shorter completion times, lower perceived workload and stronger expert ratings with TailorCoPilot than with skill-appropriate baseline tools.
Scientific publication4 min read
Physical AI benchmarks often rank models in similar ways
A preprint audit of 12 physical-AI benchmarks found positive relationships across every pair, with especially strong agreement for two pairs of tests. The analysis covered 51 models and suggests that benchmark averages can repeat the same strengths, while a compact suite may preserve useful model separation.
Scientific publication5 min read
Robot tests suggest a vegetation stiffness profile stays stable across heights
A two-specimen laboratory study found that a distributed measure of vegetation stiffness stayed stable across robot push heights, while a lumped stiffness varied.
Scientific publication5 min read
New corpus tracks 470,795 software specification files
A preprint describes SpecMine, a public GitHub corpus of software specification artifacts that combines broad and Kiro censuses with commit histories, pull requests and typed links to code.
Scientific publication4 min read
AI method shrinks the evidence trail for checking LLM answers
A preprint reports that BLIP can reduce the material used to check an LLM answer to around 9.8% of the full text while retaining an accuracy score of 1 in its evaluation.
Scientific publication3 min read
Preprint claims a tighter deterministic approximation for matrix permanents
The arXiv work claims a deterministic polynomial-time certificate for every nonnegative rational square matrix, with an exponential approximation base below the canonical Bethe guarantee.
Scientific publication5 min read
Robot AI Speeds Action Decoding in Simulated and Physical Tests
FlashVLA, a streaming method for vision-language-action policies, cut reported inference time while maintaining or improving task success across selected simulated benchmarks and three physical-arm tests.
Scientific publication5 min read