7179 papers
This paper proposes a joint optimization framework for sensing, communication, and exploration speed in lifelong SLAM systems to minimize energy consumption, validated through simulations and experiments involving LiDAR-equipped robots transmitting data to a deep learning-based cloud reconstruction center.
This paper introduces HarmonicEval, a reference-free, multi-criteria evaluation metric for vision-language models that aggregates criterion-wise scores to better align with human judgments across diverse multi-modal tasks, supported by the newly constructed MMHE benchmark containing 18,000 expert human evaluations.
This paper proposes a method that leverages pretrained vision-language models to learn compact, abstract symbolic world models from limited visual demonstrations, enabling zero-shot generalization and long-horizon planning for complex robotic tasks across novel objects, environments, and goals.
This paper proposes efficient data reduction strategies for semi-supervised adversarial training that utilize latent clustering techniques to select or generate critical boundary-adjacent samples, significantly reducing data requirements and computational costs while maintaining state-of-the-art robustness.
This paper proposes a pivot-based single-model ensemble framework that generates diverse translation candidates through pivot languages and aggregates the best ones to improve translation quality for low-resource language pairs while avoiding the high computational costs of traditional multi-model ensembles.
This paper introduces GRADIEND, a novel encoder-decoder method that utilizes model gradients to identify and rewrite specific neural network weights, effectively debiasing AI systems regarding gender, race, and religion while preserving their other capabilities.
This paper proposes a novel local search algorithm with a balanced optimization objective and provable linear convergence to efficiently identify polarized communities in signed networks, effectively addressing size imbalance and scaling to large datasets while outperforming state-of-the-art methods.
This paper demonstrates that integrating Low-Rank Adaptation (LoRA) into Federated Learning for Large Language Models significantly reduces unintended memorization of sensitive training data across diverse model sizes and domains, while maintaining performance and offering compatibility with other privacy-preserving techniques.
Prompt-SID is a self-supervised single-image denoising framework that leverages a latent diffusion-based structural representation generator and a scale replay training mechanism to preserve detailed structural information without relying on expensive paired datasets.
This paper proposes a discrete mathematical framework using coarse-grained partitions and categorical unification to quantify information loss in explainable AI, demonstrating that zero loss is an exceptional case and providing a method to optimize the trade-off between interpretability and informational fidelity.
This paper introduces Texts as Time Series (TaTS), a novel framework that leverages the periodic alignment between paired texts and time series data to enhance multimodal forecasting and imputation performance in existing numerical-only models without requiring architectural changes.
The paper proposes LaVCa, a novel data-driven approach that leverages large language models to generate natural-language captions for images, thereby providing more accurate and detailed interpretations of human visual cortex voxel selectivity and revealing fine-grained functional differentiation within the visual cortex compared to existing deep neural network-based methods.
This paper proposes a Clustering-On-Difficulty (COD) framework that groups tasks by their difficulty scaling features to predict downstream LLM performance with high accuracy (1.55% error), effectively addressing challenges like emergent capabilities and inconsistent scaling patterns.
This study proposes a high-accuracy glioma subclass classification framework that fuses 2D and 3D UNET-segmented multimodal MRI images using weighted averaging and classifies them via a pre-trained ResNet50 model, achieving a 99.25% accuracy rate.
This paper proposes a deep learning-based approach utilizing UNET, Inception, and ResNet architectures to achieve automatic 2D and 3D glioma segmentation on BraTS datasets, demonstrating that a ResNet model effectively balances computational efficiency and spatial accuracy to significantly improve diagnosis with high accuracy and Dice scores.
This paper proposes Leave-One-Out PPO (LOOP), a novel reinforcement learning method that combines variance reduction techniques from REINFORCE with the robustness of PPO to achieve a superior balance between sample efficiency and performance in fine-tuning text-to-image diffusion models.
This paper proposes a novel dual-thread framework that enables concurrent planning and acting with interruptible execution for LLM-based multi-agent systems, overcoming the limitations of serialized paradigms to enhance real-time responsiveness and adaptability in dynamic environments like Minecraft.
This paper introduces GlucoLens, an explainable machine learning system that integrates wearable sensor data, diet, and activity logs to accurately predict postprandial hyperglycemia and recommend personalized behavioral interventions for managing blood glucose levels.
This paper proposes a novel transformer-based geometric deep learning model that tokenizes tetrahedral meshes with anatomical landmarks to accurately classify Alzheimer's disease and predict brain amyloid positivity in medium-risk individuals, offering a robust alternative to costly and invasive PET scans.
This study of 36 Kazakhstani scholars using the CGScholar platform reveals that while familiarity with AI tools correlates with openness to feedback, participants still highly value peer input for methodological guidance, suggesting that integrating AI with traditional peer feedback effectively enhances academic research writing skills.