927 papers
This paper proposes a knowledge graph-guided framework that leverages prior knowledge about anomalies and their relationships to construct text prompts, enabling foundation models and diffusion techniques to generate realistic anomalous images for various product classes.
This paper introduces Scholar-ML-1000, a publicly released dataset of 996 top-cited machine learning researchers collected in June 2026, which reveals that major tech companies like Google and DeepMind now host more leading ML scholars than top universities combined, while highlighting the field's significant global diversity and interdisciplinary reach.
PRISM-VFL is a differentially private vertical federated learning framework that integrates LSTM encoders with a Multi-gate Mixture-of-Experts module to enable concurrent training of heterogeneous clinical prediction tasks, demonstrating that while in-hospital mortality prediction remains clinically viable under moderate privacy constraints, other tasks like decompensation and phenotyping face significant utility challenges despite effectively suppressing label inference attacks.
This paper introduces the Scholar-India-ML bibliometric dataset to analyze the citation patterns and research trajectories of 478 top-cited Indian machine learning scholars, revealing that the Indian Institute of Science and the Indian Statistical Institute outperform the IITs in citation impact while industry labs are emerging as significant contributors to the nation's AI ecosystem.
This paper proposes an adaptive Wireless Sensor Network-based IoT node deployment and data transmission model that integrates the HEED clustering protocol with IEEE 802.11x standards and deep learning analytics to optimize energy efficiency, extend network lifetime, and enhance Quality of Service in large-scale IoT applications.
This study evaluates the reliability and validity of multimodal LLMs for urban design assessment in Seoul, finding that while they perform well on visually explicit features, their inability to fully replicate human ratings for contextual or proportional variables limits their suitability to element-specific rather than universal applications.
This paper proposes a machine learning paradigm that bypasses traditional image reconstruction to directly detect entities of interest, such as diseases, from minimal measurements, thereby significantly reducing acquisition costs and time while maintaining diagnostic accuracy.
This paper proposes a hybrid task allocation framework for heterogeneous multi-robot systems that combines a Large Language Model for generating high-quality initial solutions based on natural language with a memory-guided Speed-Up Slow-Down local search algorithm, achieving a 17.07% reduction in mission makespan compared to traditional methods while maintaining scalability.
This paper introduces the Virtual Speech Therapist (VST), an AI-driven, clinician-in-the-loop platform that integrates deep learning-based stuttering classification with multi-agent large language model reasoning to generate, critique, and refine personalized, evidence-based therapy plans for expert review and implementation.
This paper introduces the "Dice Roll Method," a statistically principled protocol that replaces flawed parametric assumptions with a negative-binomial GLMM framework and simulation-based power analysis to establish standardized iteration counts and reliability thresholds for measuring stochastic bias in large language model outputs.