Page 30 - Paper Library - AiPaper

Early diagnosis model of mycosis fungoides and five inflammatory skin diseases based on multi-modal data-based convolutional neural network

Multi-Modal Data Convolutional Neural NetworkEarly Diagnosis of Mycosis FungoidesFive Inflammatory Skin DiseasesSkin Disease Diagnosis Model

The study introduces an innovative early diagnostic model for mycosis fungoides and five inflammatory skin diseases using a convolutional neural network that integrates multimodal data, aiming to enhance diagnostic precision and improve patient outcomes.

A Grover-Based Quantum Algorithm for Solving Perfect Mazes via Fitness-Guided Search

Published:7/29/2025

Quantum Path Planning AlgorithmGrover's AlgorithmAdaptive Search StrategyPerfect Maze SolvingQuantum Computing Pathfinding

This paper presents a Groverbased quantum algorithm for solving perfect mazes, encoding candidate paths in superposition and using a reversible fitness operator for proximity evaluation. The method shows efficient scalability and lays the foundation for quantumhybrid pathfindin

InfiniteWorld: A Unified Scalable Simulation Framework for General Visual-Language Robot Interaction

Published:12/8/2024

Vision-Language Robot InteractionUnified Scalable Simulation FrameworkRobot Interaction Learning Benchmarks3D Asset Construction MethodsEnvironmental Understanding and Task Planning

This paper presents InfiniteWorld, a unified and scalable simulator based on Nvidia Isaac Sim, aimed at enhancing research efficiency in embodied AI. It integrates 3D asset generation, automated annotation, and unified processing methods, establishing four new benchmarks to asses

LoRA: Low-Rank Adaptation of Large Language Models

Published:6/18/2021

Low-Rank Adaptation for Large Language ModelsTransformer architectureLarge Language Model Fine-TuningParameter Efficiency OptimizationRoBERTa and Its Derivatives

LoRA introduces a lowrank adaptation method for finetuning large language models, significantly reducing trainable parameters by injecting rank decomposition matrices while freezing the model weights. It achieves comparable or better performance on RoBERTa, DeBERTa, GPT2, and

One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Models

Published:11/14/2025

Diffusion Model Super-ResolutionLightweight Latent Upscaler AdapterSwin-Style BackboneHigh-Fidelity Image SynthesisLatent Space Image Generation

The paper introduces a lightweight Latent Upscaler Adapter (LUA) that performs superresolution directly on latent codes in diffusion models, reducing image generation time by nearly threefold while maintaining comparable perceptual quality, facilitating highfidelity synthesis w

NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration

Published:10/12/2023

Goal-Driven Navigation and ExplorationDiffusion Policy ModelsLarge-Scale Transformer PolicyRobotic NavigationTask-Agnostic Exploration

The paper introduces NoMaD, a unified diffusion policy for robots that simultaneously handles taskoriented navigation and taskagnostic exploration. Utilizing a largescale Transformer and a diffusion model decoder, it flexibly manages goal conditioning and improves performance

Characteristics Matching Based Hash Codes Generation for Efficient Fine-grained Image Retrieval

Published:6/16/2024

Fine-Grained Image RetrievalHash Code Generation MethodFeature Learning and EfficiencyCross-Layer Semantic Information TransferMulti-Region Feature Embedding

This paper proposes a characteristics matching based hash code generation method for finegrained image retrieval, addressing inherent contradictions in hashing model design. By integrating crosslayer semantic transfer and multiregion feature embedding, it effectively captures

PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System

Published:10/13/2025

Humanoid Robot Scene Interaction SystemAdversarial Motion Prior Policy LearningReal-World Deployment SystemCoarse-to-Fine Object Localization ModuleMulti-Task Robot Interaction Validation

The paper presents PhysHSI, a humanoidscene interaction system that enables robots to perform diverse tasks in realworld environments. It combines adversarial motion priorbased policy learning and a coarsetofine object localization module, achieving natural behaviors and rob

RankMixer: Scaling Up Ranking Models in Industrial Recommenders

Published:11/8/2025

Scaling Up Industrial Recommendation ModelsHardware-Aware Recommendation Model DesignEfficient Feature Interaction in Transformer ArchitectureSparse Mixture of Experts MechanismDynamic Routing Strategy

RankMixer is introduced to enhance the efficiency and scalability of ranking models in industrial recommenders. Utilizing a hardwareaware design, it replaces selfattention with multihead token mixing, achieving improved model performance with one billion parameters and a Spars

FogBus: A Blockchain-based Lightweight Framework for Edge and Fog Computing

Published:4/13/2019

Integration of Edge and Fog ComputingBlockchain Applications in IoTMulti-Application Execution Resource ManagementSecurity for IoT DevicesCross-Platform Interface Design

FogBus is a blockchainbased lightweight framework for integrating edge, fog, and cloud computing, supporting latencysensitive IoT applications. It offers platformindependent interfaces, assists in multiapplication execution, and secures data through authentication and encrypt

Physics-Informed Neural Operator for Learning Partial Differential Equations

Published:11/6/2021

Physics-Informed Neural OperatorsLearning Partial Differential EquationsSolution OperatorsOptimization ChallengesReduced Data Requirements

This paper introduces a PhysicsInformed Neural Operator (PINO) that learns solution operators for parametric PDE families by integrating training data with physics constraints, effectively addressing optimization challenges and reducing data needs, outperforming previous ML meth

OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting

Published:1/23/2025

LLM QuantizationOrthogonal and Scaling TransformationsQuantization Space Utilization RateKL-Top Loss FunctionPost-Training Quantization

The OSTQuant method optimizes large language model quantization using orthogonal and scaling transformations, addressing uneven and heavytailed data distributions. Introducing Quantization Space Utilization Rate (QSUR) effectively assesses quantizability, while the KLTop loss f

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

Published:9/12/2025

Vision-Language-Action ModelReinforcement Learning for Math ReasoningRL Training for Large Language ModelsMulti-Environment RenderingEfficient Reinforcement Learning Framework

SimpleVLARL is introduced to enhance the training of VisionLanguageAction models using reinforcement learning, addressing data scarcity and generalization issues. Results show stateoftheart performance on OpenVLAOFT, reducing reliance on labeled data.

WoW: Towards a World omniscient World model Through Embodied Interaction

Published:9/27/2025

Physical Intuition and Robot InteractionCausal Reasoning Benchmark WoWBenchLarge-Scale World Model TrainingVision-Language Model GuidanceRobot Motion Planning and Execution

The WoW model enhances understanding of physics through embodied interaction, trained on two million robot trajectories. It emphasizes the importance of physical intuition and employs the SOPHIA framework to ensure output's physical realism via visionlanguage model optimization.

Unleashing the Full Potential of Product Quantization for Large-Scale Image Retrieval

Published:11/2/2023

Deep Hashing Framework Based on Product QuantizationLarge-Scale Image RetrievalApproximate Nearest Neighbor SearchImageNet100 DatasetImageNet1K Dataset

This paper introduces a product quantizationbased deep hashing framework that addresses computational costs and accuracy issues in largescale datasets, efficiently learning classlevel codes through a differentiable PQ branch, demonstrating superior retrieval performance across

Lack of TYK2 signaling enhances host resistance to Candida albicans skin infection

Published:12/3/2024

TYK2 Signaling and Fungal InfectionsCandida albicans Skin InfectionNeutrophil Antifungal CapacityTranscriptomic Analysis and Immune ResponseRole of Interferon-gamma in Fungal Dissemination

This study reveals that the absence of TYK2 signaling enhances resistance to Candida albicans skin infections by limiting fungal spread and accelerating wound healing, while also affecting neutrophil antifungal capacity through regulation of interferoninducible genes.

Soil samples from sporotrichosis transmission belt area: Searching for fungal species and their antagonistic activity against Sporothrix brasiliensis

Published:12/1/2022

Soil Samples from Sporotrichosis Transmission BeltInteraction between Purpureocillium lilacinum and Sporothrix braStudy of Fungal Antagonistic ActivityIsolation and Identification of Sporothrix spp.Soil Fungi in Rio de Janeiro, Brazil

This study collected soil samples from sporotrichosis transmission areas in Rio de Janeiro and identified saprophytic fungi, notably Purpureocillium lilacinum, which inhibited the growth of Sporothrix brasiliensis, suggesting potential avenues for developing antifungal agents.

DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control

Published:10/8/2024

Diffusion-based Autoregressive Motion GenerationText-Driven Human Motion GenerationReal-Time Motion ControlSpatially-Constrained Motion GenerationReinforcement Learning Motion Decision Making

DartControl (DART) is a diffusionbased autoregressive motion model enabling realtime textdriven motion control. It overcomes limitations of existing methods by generating complex, longduration movements that effectively integrate motion history and text inputs.

Medical image recognition and segmentation of pathological slices of gastric cancer based on Deeplab v3 + neural network

Published:5/29/2021

Gastric Cancer Pathological Slice Segmentation based on DeeplabGastric Cancer Image RecognitionMulti-Scale Input Neural NetworkMedical Image AnalysisPathological Slice Images

This study presents an automatic segmentation model for gastric cancer slices using a Deeplab v3 network. Tested on 1240 images, it outperforms existing models in key metrics while reducing parameter scale, showing strong clinical applicability.

Use of artificial intelligence and deep learning in fetal ultrasound imaging

Published:11/27/2022

Deep Learning Applications in Fetal Ultrasound ImagingAI Techniques in Medical ImagingUltrasound Imaging Diagnostic Support ToolsFetal Biometry and Anatomy RecognitionIntegration of Deep Learning and Ultrasound Imaging

This review explores deep learning's application in fetal ultrasound imaging, highlighting its potential to enhance diagnostic accuracy affected by operator experience, while covering areas like fetal anatomy identification and biometry measurement.

581 - 600 / 972

Papers