20 results for “classification”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper establishes a large deviation principle for the generalization error of interpolating classifiers in the overparametrized regime.
Proposes an agentic large language model framework for accurate HTS code classification in maritime logistics.
This paper proposes a hybrid feature fusion and voting-based approach for automated malware detection and classification into specific malware families, achieving high performance metrics like an AUC…
This paper proposes a segment combination strategy to improve automatic multi-label classification of research methods in full-text articles.
The paper proposes a novel KAN-enhanced BiGRU architecture to improve legal document classification and summarization in a low-resource, multilingual setting using Bengali and English legal texts.
The paper proposes a zero-shot multi-label topic classification framework and finds that while knowledge graph augmentation improves performance for smaller language models, it offers diminishing retu…
The study investigates the limitations of Phonetic Foundation Models (PFMs) for Speech-to-IPA transcription using Grapheme-to-Phoneme (G2P) labels and proposes a new approach based on continuous Artic…
The paper systematically compares multimodal transformer and LLM approaches for document type classification, finding that specialized multimodal Transformers outperform LLM-based models, especially w…
This paper extends gradient boosting to functions of vector inputs using a simple algorithm with histogram-based decision trees.
The paper proposes a zero-label malware family classification framework that uses a weighted hierarchical ensemble of large language models (LLMs) to classify malware without requiring labeled trainin…
This paper investigates the effectiveness of lightweight lexical machine-learning methods for classifying disaster-related social-media posts into humanitarian information labels.
This paper characterizes proper binary classification from positive-only samples, revealing a rich landscape that differs from standard PAC learning.
Li Zhang, Yuyuan Li, XiaoHua Feng, Jiaming Zhang +2 more
This paper addresses the challenge of achieving optimal fairness and accuracy simultaneously in multi-class classification by proposing novel in-processing and post-processing algorithms that converge…
The paper proves that the majority vote of three independent consistent classifiers is an optimal learner in the realizable PAC setting.
Yuzhu Wang, Kalle Lahtinen, Patrik Lauha, Shiqi Zhang +3 more
This paper proposes an ensemble of two source separators, FTRNN and TF-Locoformer, trained with mixture invariant training (MixIT), and introduces mixture-constrained max pooling (MCM) to improve bird…
This paper presents methods for ranking and unranking permutations avoiding a pattern of length three in lexicographic or colexicographic order.
The paper proposes a robust, multi-stage pipeline combining rule-based classification and machine learning to map noisy retail product names to standardized consumption categories, finding that simple…
Adrián Cánovas-Rodriguez, Miguel A. González-Illán, Maria Fernanda García-Cruz, Pedro Nortes Tortosa +4 more
The paper proposes an attention-enhanced deep learning framework using EfficientNet and CBAM to achieve high accuracy (93.3%) in classifying peach leaf damage, demonstrating improved robustness under…
The authors introduce the Certus Caliber Classification Gunshot Dataset (C3GD) for analyzing firearm muzzle blast sounds.