AI Core
935 items
Survey maps high-level synthesis for approximate computing around error estimation, approximation techniques, and design space exploration, and flags research gaps
Addressing the lack of a systematic survey and in-depth analysis of the latest methodologies in high-level synthesis for approximate computing (AHLS), this survey summarizes recent technologies in the field with particular focus on error estimation, approximation techniques, and design space exploration (DSE), and analyzes current research gaps, aiming to give researchers, engineers, and scholars a theoretical and practical framework for AHLS.
FedTrust-GNN reaches 94.2% accuracy at 10,000-100,000 participants and cuts label-flipping attack success from 34% to 6.1%
The work proposes FedTrust-GNN, a decentralized user-modeling framework that combines differentially private federated learning with secure multi-party computation, a permissioned blockchain using PBFT consensus, and a heterogeneous graph attention network (HGAT) that infers dynamic trust scores, with trust-weighted robust aggregation (TWRA, combining norm clipping and coordinate-wise median aggregation) providing Byzantine fault tolerance; on Federated EMNIST, Stack Overflow, and synthetic datasets with 10,000-100,000 participants it reports 94.2% accuracy (within 1.3% of centralized models), a reduction of label-flipping attack success from 34% to 6.1% (an 82% reduction), a 41% improvement in convergence stability, and blockchain performance of 1,200 TPS with 2.3-second finality.
DCONVNET splits 2D direction-of-arrival estimation into two 1D problems and estimates azimuth and elevation via the alternating direction method of multipliers
The work presents a fast two-dimensional direction-of-arrival (DOA) estimation approach for low-elevation targets of very-high-frequency array radar: it uses the azimuth and pitch angle uncoupling properties of a uniform planar array to turn the 2D angle estimation problem into two 1D DOA estimation problems, retrieves target information in the azimuth and elevation dimensions with digital beamforming, and then estimates azimuth and pitch angles using the alternating direction method of multipliers, thereby reducing complexity and eliminating the need for eigenvalue decomposition during operation.
1,003 people with depression rated psychotherapy with different levels of AI involvement: they preferred human therapists, willing to pay 31.6% less for assistive or collaborative AI and 57.2% less for fully autonomous AI
The study had 1,003 participants with depression read vignettes describing psychotherapy options with different levels of AI involvement (a human therapist without AI, assistive AI, collaborative AI, and fully autonomous AI) and rate them; participants consistently evaluated human therapists more favorably, reporting greater likelihood of seeking treatment, less hesitancy, and greater treatment acceptability, and compared with a human therapist they were willing to pay 31.6% less for therapists using assistive or collaborative AI and 57.
SCITFS folds adaptive redundancy penalization and bootstrap stability regularization into one objective, lifting SVM accuracy by 3.7% and Random Forest by 4.2% on eight benchmarks while cutting 92.3% of features.
The work proposes Stability-Constrained Information-Theoretic Feature Selection (SCITFS), which integrates conditional entropy, normalized mutual information maximization, and a stability term penalizing feature-ranking variance across bootstrap samples into a single formally defined objective, implemented via a greedy forward-selection strategy with proven monotonicity guarantees at O(B n^2 m d^4 + k n^2); across eight benchmark datasets and five classifiers (SVM, Random Forest, k-NN, XGBoost, Logistic Regression), SCITFS outperforms Information Gain, Mutual Information, mRMR, ReliefF, Fisher Score, and JMI, achieving a 3.7% average accuracy improvement on SVM and 4.2% on Random Forest with 92.3% feature reduction while maintaining performance; Friedman test (χ² = 127.4, p < 0.
Evo 2 shows in-context learning on five binary classification tasks with F1 up to 0.902 on short sequences, but collapses at kilobase scale and the 7B model beats the 40B
This study maps the in-context learning operating regime of Evo 2, a nucleotide-level foundation genomic language model, across five binary classification tasks spanning biological and artificial sequences, finding robust performance on shorter natural sequences (F1=0.902 for miRNA, 0.785 for Toxins), degradation with sequence length and collapse at kilobase scale, no benefit from model scaling (the 7B model systematically outperforms the 40B variant), poor prediction of accuracy by perplexity, and mechanistic interpretability via logit-lens and Jacobian Scope suggesting a prediction-generalisation trade-off and that models might track prompt structure rather than signal-carrying content.
Ridezy derives driver credibility in real time from edge AI and IoT sensors and anchors hashes and reputation updates on Polygon, outperforming rating-based, AI-only, and blockchain-only baselines in behavioural fidelity and trust guarantees
The paper presents Ridezy, a decentralized trust architecture that uses edge Artificial Intelligence and Internet of Things (AIIoT) to continuously monitor behavioural indicators such as lane discipline, speed compliance, braking behaviour, and traffic sign adherence, processes behavioural summaries off-chain while anchoring only cryptographic hashes, credibility updates, and payment records on Polygon smart contracts, and compares it against three representative trust models—a traditional rating-based system, an AI-only architecture, and a blockchain-only architecture—across behavioural detection performance, end-to-end latency, cost efficiency, throughput, reputation stability, tamper resistance, and component-wise ablation studies, with results showing higher behavioural fidelity and st
Gated-attention multiple instance learning triages multi-center cervical cytology slides without per-cell labels, reaching 90.96% accuracy with MobileNetV2 and 80.43% balanced accuracy out-of-distribution with Xception
The work presents a weakly-supervised, detection-free multiple instance learning framework that uses dual-branch gated attention pooling to make slide-level predictions on whole-slide cervical cytology images, treating each slide as a bag of local instance patches so that single-cell bounding boxes or pixel-level annotations are not required; evaluated on internal multi-center cohorts (SIPaKMeD, Herlev, and CRIC) and on the unannotated, out-of-distribution Mendeley LBC validation cohort processed via an unsupervised marker-controlled watershed pipeline, it reports that the lightweight MobileNetV2 backbone optimizes in-distribution multi-center accuracy (90.96% accuracy, 0.9800 ROC-AUC) while the higher-capacity Xception provides better out-of-distribution robustness under domain shift (80.
Fuzzy-rank feature selection plus H2O AutoML ensembles reach up to 95.1% accuracy and 98.1% AUC on two public cervical cancer datasets
The work introduces an interpretable Fuzzy Rank-H2O AutoML framework in which a Fuzzy Rank Feature Selection (FRFS) algorithm picks predictors by combining statistical significance, information gain, clinical importance, and uncertainty, H2O AutoML then automatically builds ensemble models, and SHAP and LIME supply global and patient-level explanations; evaluated on two public cervical cancer datasets with stratified five-fold cross-validation where SMOTE is applied only to training folds to avoid information leakage, it reports a highest accuracy of 95.1% and AUC of 98.1%, outperforming traditional machine learning models and the baseline H2O AutoML framework.
Page 14 · showing 10