- Robusto-1 Dataset: Comparing Humans and VLMs on Real Out-Of-Distribution Autonomous Driving VQA from Peru
- Late Breaking Results: Customized Diffusion Model Empowered by Heterogeneous Graph Network for Effective Floorplanning
- V3LMA: Visual 3D-Enhanced Language Model for Autonomous Driving
- Fairness-Aware Boosting Model for Imbalanced 3D Point Cloud Segmentation in Autonomous Driving
- NVR: Vector Runahead on NPUs for Sparse Memory Access
- Attention-Guided Hierarchical Defense for Multimodal Attacks in Vision-Language Models
- Perturbed State Space Feature Encoders for Optical Flow with Event Cameras
- Harmonic Suppression of Grid-Forming Inverters Based on QPMR Controller
- RUPlace: Optimizing Routability via Unified Placement and Routing Formulation
- Jump-Aware: Player Position Rectification and Identification in Dynamic Sports Using Jump Event Spotting
- NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
- Word2Vec-Based Facial Serum Recommender System
- ADVISOR: Approximate Computing-frienDly High-LeVel Synthesis DesIgn Space ExplORer
- NTIRE 2025 Challenge on Image Super-Resolution ( $\times 4$ ): Methods and Results
- Identifying System-on-Chip Security Assets with Structure-Based Analysis
- BirdMoE: Reducing Communication Costs for Mixture-of-Experts Training Using Load-Aware Bi-random Quantization
- Few-shot Learning on AMS Circuits and Its Application to Parasitic Capacitance Prediction
- Disentangling Visual Transformers: Patch-Level Interpretability for Image Classification
- Enhancing Multi-Modal Zero-Calibration RSVP-based Target Detection with Cross-Subject Mixing and Cross-Modal Alignment
- Convolutional Neural Network -Based Indonesian Sign Language (BISINDO) Recognition for Enhanced Communication
- EVA: An Efficient and Versatile Generative Engine for Targeted Discovery of Novel Analog Circuits
- Logic Optimization Meets SAT: A Novel Framework for Circuit-SAT Solving
- Deep Learning based Ensemble Model for Intrusion Detection in IoT Network
- Research on the Control Strategy of a Three-Level Back-To-Back Converter with a Vienna Rectifier as the Front-End Stage
- DWFDA-CD:A Diffusion Model-based Wavelet Frequency Domain Attention Network for Remote Sensing Change Detection
- Comparing Predictive Capabilities of Machine Learning Models in Weather Forecasting
- Probabilistic Perspective-n-Lines for Indoor Camera Pose Estimation
- NTIRE 2025 Challenge on HR Depth From Images of Specular and Transparent Surfaces
- Harnessing Artificial Intelligence to Tackle Market Uncertainty in Marketing, Managerial Decision-Making, and Engineering Systems
- Contention-Aware Forecasting of Energy Efficiency through Sequence-Based Models in Modern Heterogeneous Processors
- NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
- Towards Smarter Clinical Predictions: Foundation Models for Integrating Multi-Source Domain Knowledge in EHRs
- Training Neural Networks on RAW and HDR Images for Restoration Tasks
- Assessing the InfoBMKG Disaster Mitigation Application in Indonesia: An Integrated CatBoost and SHAP-Based Sentiment Analysis Approach
- Segmentation of Hepatic Steatosis in a Histopathological Image Using U-Net-based Architecture
- Espresso: Exploiting the Sparsity Property in Event Sensors with Spatiotemporal Ordering
- Automatic Explicit Content Detection in Anime: Comparison of DETR and YOLO
- Can Vision-Language Models Understand and Interpret Dynamic Gestures from Pedestrians? Pilot Datasets and Exploration Towards Instructive Nonverbal Commands for Cooperative Autonomous Vehicles
- NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results
- FedEDA: Federated Learning Framework for Privacy-Preserving Machine Learning in EDA
- MILLION: MasterIng Long-Context LLM Inference Via Outlier-Immunized KV Product QuaNtization
- Enabling On-Tiny-Device Model Personalization via Gradient Condensing and Alternant Partial Update
- Robust AD: A Real World Benchmark Dataset for Robustness in Industrial Anomaly Detection
- PICK: An SRAM-based Processing-in-Memory Accelerator for K-Nearest-Neighbor Search in Point Clouds
- Datasets for Valence and Arousal Inference: A Survey
- Fast Sphericity and Roundness Approximation in 2D and 3D Using Local Thickness
- AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements
- Enhanced Feature Fused Vision Transformer Framework for Multiclass Brain Tumor Classification Using MRI Images
- PF3Det: A Prompted Foundation Feature Assisted Visual Lidar 3D Detector
- Intelligent Symptom-to-Medicine Mapping using MAGRU-IDMO: An Attention-GRU Framework with Bio-Inspired Optimization
- Multi-Entity Video Transformers for Fine-Grained Video Representation Learning
- SDISC: A Spike-Driven Human-Machine Interface with In-Situ Computing for Real-Time Low-Power Interaction
- A Mixed-Signal Photonic SRAM-based High-Speed Energy-Efficient Photonic Tensor Core with Novel Electro-Optic ADC
- Joint Design of Transmit Waveform and Mismatch Filter for MIMO Radar Under ISRJ Scenario
- Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic Programming
- Disturbance Observe Based Model Predictive Frequency Controller for Virtual Power Plant
- Systematic Design of a Compact Lumped-Element Outphasing Class-E Power Amplifier for HF Band
- Interactive Multimodal Framework with Temporal Modeling for Emotion Recognition
- MiniWear: Minimizing Flash Wear via Hybrid Persistent Cache for Extended EF-SMR Lifetime
- Sensitivity of Pareto Optimality in Multicriteria Optimal Control with Respect to the Reduction of the Terminal Time
- SoccerNet-v3D: Leveraging Sports Broadcast Replays for 3D Scene Understanding
- BPUFuzzer: Effective Fuzz Testing for Branching Transient Execution Vulnerabilities of RISC-V CPU
- A Lightweight Privacy-Preserving Scheme for Verifiable Multi-Dimensional Data Aggregation in Vehicular Crowdsensing Networks
- LFTransMamba: A Hybrid Mamba-Transformer Model for Light Field Image Super-Resolution
- What is the Added Value of UDA in the VFM Era?
- SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding
- Optimizing Recovery Logic in Speculative High-Level Synthesis
- AI-Driven Air Quality Index Forecasting: Advancing Cyber-Resilience in Environmental Monitoring and Public Health
- Late Breaking Results: Novel Design of MTJ-Based Unified LIF Spiking Neuron and PUF
- Adaptive Control of Two-Mass System with Nonlinear Stiffness and Backlash
- Understanding and Mitigating Toxicity in Image-Text Pretraining Datasets: A Case Study on LLaVA
- Rel-SA: Alzheimer's Disease Detection Using Relevance-augmented Self Attention by Inducing Domain Priors in Vision Transformers
- Retinex-Guided Histogram Transformer for Mask-Free Shadow Removal
- Flatness Analysis of a Micro Tandem Helicopter
- ParGNN: A Scalable Graph Neural Network Training Framework on multi-GPUs
- The Tenth NTIRE 2025 Image Denoising Challenge Report
- Instance Feature Caching for Cross-Domain Few-Shot Object Detection
- Partial Least Square Segmentation Modeling Using PATHMOX on Tuberculosis Patient Data
- Fine-Grained Few-Shot Classification with Part Matching
- Predictive Analysis of Electrical Load Forecasting and Classification of Feeder Efficiency with Random Forest Algorithm
- Deep learning-based data centre energy efficiency analysis and optimisation research
- DELTA: Dense Depth from Events and LiDAR Using Transformer's Attention
- ScoreCAM++: Gated Score-Weighted Visual Explanations for CNNs
- iTaskSense: Task-Oriented Object Detection in Resource-Constrained Environments
- Design of Interior Permanent Magnet Synchronous Motor Complex Vector Current Regulator
- Automated Liver Lesion Segmentation with Deep Learning Model
- Late Breaking Results: Scalable GPU-Friendly Parallelization for Sweep-Based Maze Routing
- Sales Forecasting for SMEs in Digital Ecosystems: A Comparative Evaluation of ARIMA and Random Forest Models
- ChatLS: Multimodal Retrieval-Augmented Generation and Chain-of-Thought for Logic Synthesis Script Customization
- Construction of DAG Models for Autonomous Systems
- Multi-Aspect Sentiment Analysis on KAI Access App Reviews (Google Play Store) Using CNN-LSTM Method
- Late Breaking Results: Encoder-Decoder Generative Diffusion Transformer Towards Push-Button Analog IC Sizing
- Power prediction of mine wind power supply system based on TCN-Transformer
- Dual-Path Enhancements in Event-Based Eye Tracking: Augmented Robustness and Adaptive Temporal Modeling
- Comix – A Deep Learning Approach to Automated Educational Comic Creation
- Distillation-Supervised Convolutional Low-Rank Adaptation for Efficient Image Super-Resolution
- U-Shape Mamba: State Space Model for Faster Diffusion
- Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Models
- DistilBERT and LDA for Understanding Consumer Attitudes Toward Sustainable Products in E-Business
- SSpMV: A Sparsity-aware SpMV Framework Empowered by Multimodal Machine Learning