{"total":162,"rows":[{"id":"2409.12259","title":"WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild","created":"2024-09-18","cited_by_count":124,"area":null},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"id":"2406.08552","title":"DiTFastAttn: Attention Compression for Diffusion Transformer Models","created":"2024-06-12","cited_by_count":115,"area":"diffusion"},{"id":"2404.10518","title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","created":"2024-04-16","cited_by_count":99,"area":null},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96,"area":null},{"id":"2412.13303","title":"FastVLM: Efficient Vision Encoding for Vision Language Models","created":"2024-12-17","cited_by_count":77,"area":"mllm"},{"id":"2311.15599","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","created":"2023-11-27","cited_by_count":64,"area":null},{"id":"2401.16456","title":"SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design","created":"2024-01-29","cited_by_count":56,"area":null},{"id":"2407.09646","title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","created":"2024-07-12","cited_by_count":45,"area":"ssm"},{"id":"2403.19888","title":"MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection","created":"2024-03-29","cited_by_count":40,"area":"ssm"},{"id":"2601.22153","title":"DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation","created":"2026-01-29","cited_by_count":34,"area":"vla"},{"id":"2403.01813","title":"A Simple Baseline for Efficient Hand Mesh Reconstruction","created":"2024-03-04","cited_by_count":27,"area":null},{"id":"2310.04621","title":"Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences","created":"2023-10-06","cited_by_count":21,"area":null},{"id":"2405.06849","title":"GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs","created":"2024-05-10","cited_by_count":21,"area":null},{"id":"2508.20691","title":"MobileCLIP2: Improving Multi-Modal Reinforced Training","created":"2025-08-28","cited_by_count":21,"area":"distill"},{"id":"2405.01992","title":"SFFNet: A Wavelet-Based Spatial and Frequency Domain Fusion Network for Remote Sensing Segmentation","created":"2024-05-03","cited_by_count":17,"area":null},{"id":"2411.15241","title":"EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality","created":"2024-11-22","cited_by_count":17,"area":"ssm"},{"id":"2512.01540","title":"FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention","created":"2025-12-01","cited_by_count":17,"area":null},{"id":"2411.15941","title":"MobileMamba: Lightweight Multi-Receptive Visual Mamba Network","created":"2024-11-24","cited_by_count":16,"area":"ssm"},{"id":"2311.18237","title":"Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models","created":"2023-11-30","cited_by_count":15,"area":null},{"id":"2411.17473","title":"TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba","created":"2024-11-26","cited_by_count":15,"area":"ssm"},{"id":"2503.23135","title":"LSNet: See Large, Focus Small","created":"2025-03-29","cited_by_count":15,"area":null},{"id":"2403.12686","title":"WaterVG: Waterway Visual Grounding based on Text-Guided Vision and mmWave Radar","created":"2024-03-19","cited_by_count":13,"area":null},{"id":"2411.05712","title":"Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream","created":"2024-11-08","cited_by_count":13,"area":null},{"id":"2409.17978","title":"HydraViT: Stacking Heads for a Scalable ViT","created":"2024-09-26","cited_by_count":11,"area":null},{"id":"2308.09372","title":"Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformers","created":"2023-08-18","cited_by_count":9,"area":null},{"id":"2310.10563","title":"RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2311.03747","title":"SBCFormer: Lightweight Network Capable of Full-size ImageNet Classification at 1 FPS on Single Board Computers","created":"2023-11-07","cited_by_count":9,"area":null},{"id":"2406.05850","title":"Scaling Graph Convolutions for Mobile Vision","created":"2024-06-09","cited_by_count":9,"area":null},{"id":"2412.01537","title":"HandOS: 3D Hand Reconstruction in One Stage","created":"2024-12-02","cited_by_count":9,"area":null},{"id":"2501.15369","title":"iFormer: Integrating ConvNet and Transformer for Mobile Application","created":"2025-01-26","cited_by_count":9,"area":null},{"id":"2503.10687","title":"Context-guided Responsible Data Augmentation with Diffusion Models","created":"2025-03-12","cited_by_count":9,"area":"diffusion"},{"id":"2604.05546","title":"Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects","created":"2026-04-07","cited_by_count":9,"area":"lr"},{"id":"2409.18569","title":"Cross-video Identity Correlating for Person Re-identification Pre-training","created":"2024-09-27","cited_by_count":8,"area":null},{"id":"2410.08049","title":"Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2502.05800","title":"MicroViT: A Vision Transformer with Low Complexity Self Attention for Edge Device","created":"2025-02-09","cited_by_count":8,"area":null},{"id":"2305.13705","title":"DiffHand: End-to-End Hand Mesh Reconstruction via Diffusion Models","created":"2023-05-23","cited_by_count":7,"area":"diffusion"},{"id":"2405.08911","title":"CLIP with Quality Captions: A Strong Pretraining for Vision Tasks","created":"2024-05-14","cited_by_count":7,"area":null},{"id":"2407.06723","title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions","created":"2024-07-09","cited_by_count":7,"area":null},{"id":"2510.00379","title":"Composer: A Search Framework for Hybrid Neural Architecture Design","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2404.03085","title":"Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference","created":"2024-04-03","cited_by_count":6,"area":null},{"id":"2404.05196","title":"HSViT: Horizontally Scalable Vision Transformer","created":"2024-04-08","cited_by_count":6,"area":null},{"id":"2409.03460","title":"LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2501.10640","title":"ClusterViG: Efficient Globally Aware Vision GNNs via Image Partitioning","created":"2025-01-18","cited_by_count":6,"area":null},{"id":"2504.19077","title":"Learning to Drive from a World Model","created":"2025-04-27","cited_by_count":6,"area":"wm"},{"id":"2310.16210","title":"Semantic Segmentation in Satellite Hyperspectral Imagery by Deep Learning","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2407.08965","title":"Lite-SAM Is Actually What You Need for Segment Everything","created":"2024-07-12","cited_by_count":5,"area":null},{"id":"2407.11306","title":"PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformer","created":"2024-07-16","cited_by_count":5,"area":null},{"id":"2410.05500","title":"Residual Kolmogorov-Arnold Network for Enhanced Deep Learning","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2411.16170","title":"CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction","created":"2024-11-25","cited_by_count":5,"area":null},{"id":"2412.13393","title":"MaskHand: Generative Masked Modeling for Robust Hand Mesh Reconstruction in the Wild","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2505.21847","title":"RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2509.01786","title":"EgoTouch: On-Body Touch Input Using AR/VR Headset Cameras","created":"2025-09-01","cited_by_count":5,"area":null},{"id":"2605.08195","title":"ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device","created":"2026-05-05","cited_by_count":5,"area":null},{"id":"2312.08851","title":"Achelous++: Power-Oriented Water-Surface Panoptic Perception Framework on Edge Devices based on Vision-Radar Fusion and Pruning of Heterogeneous Modalities","created":"2023-12-14","cited_by_count":4,"area":null},{"id":"2401.12736","title":"$ShiftwiseConv:$ Small Convolutional Kernel with Large Kernel Effect","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2403.19882","title":"Enhancing Efficiency in Vision Transformer Networks: Design Techniques and Insights","created":"2024-03-28","cited_by_count":4,"area":null},{"id":"2404.12210","title":"An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training","created":"2024-04-18","cited_by_count":4,"area":null},{"id":"2406.08816","title":"ToSA: Token Selective Attention for Efficient Vision Transformers","created":"2024-06-13","cited_by_count":4,"area":null},{"id":"2406.16004","title":"RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization","created":"2024-06-23","cited_by_count":4,"area":null},{"id":"2407.11224","title":"Distributed Semantic Segmentation with Efficient Joint Source and Task Decoding","created":"2024-07-15","cited_by_count":4,"area":null},{"id":"2410.11428","title":"CTA-Net: A CNN-Transformer Aggregation Network for Improving Multi-Scale Feature Extraction","created":"2024-10-15","cited_by_count":4,"area":null},{"id":"2502.15021","title":"Thicker and Quicker: A Jumbo Token for Fast Plain Vision Transformers","created":"2025-02-20","cited_by_count":4,"area":null},{"id":"2509.04669","title":"VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation","created":"2025-09-04","cited_by_count":4,"area":"ssm"},{"id":"2410.22184","title":"Multi-Level Feature Distillation of Joint Teachers Trained on Distinct Image Datasets","created":"2024-10-29","cited_by_count":3,"area":"distill"},{"id":"2412.10995","title":"RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone","created":"2024-12-14","cited_by_count":3,"area":null},{"id":"2505.22195","title":"S2AFormer: Strip Self-Attention for Efficient Vision Transformer","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2506.10361","title":"FaceLiVT: Face Recognition using Linear Vision Transformer with Structural Reparameterization For Mobile Device","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2508.07312","title":"MobileViCLIP: An Efficient Video-Text Model for Mobile Devices","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2508.09000","title":"UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale","created":"2025-08-12","cited_by_count":3,"area":null},{"id":"2601.19908","title":"CHIME: Chiplet-based Heterogeneous Near-Memory Acceleration for Edge Multimodal LLM Inference","created":"2025-12-12","cited_by_count":3,"area":"mllm"},{"id":"2310.00096","title":"Towards Few-Call Model Stealing via Active Self-Paced Knowledge Distillation and Diffusion-Based Image Generation","created":"2023-09-29","cited_by_count":2,"area":"diffusion"},{"id":"2402.00564","title":"A Single Graph Convolution Is All You Need: Efficient Grayscale Image Classification","created":"2024-02-01","cited_by_count":2,"area":null},{"id":"2408.01797","title":"NuLite -- Lightweight and Fast Model for Nuclei Instance Segmentation and Classification","created":"2024-08-03","cited_by_count":2,"area":null},{"id":"2409.07896","title":"MambaMIC: An Efficient Baseline for Microscopic Image Classification with State Space Models","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2410.17661","title":"PETAH: Parameter Efficient Task Adaptation for Hybrid Transformers in a resource-limited Context","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2501.13341","title":"Multi-aspect Knowledge Distillation with Large Language Model","created":"2025-01-23","cited_by_count":2,"area":"distill"},{"id":"2511.09942","title":"AdaptViG: Adaptive Vision GNN with Exponential Decay Gating","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2305.13399","title":"Efficient Large-Scale Visual Representation Learning And Evaluation","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2308.11421","title":"TurboViT: Generating Fast Vision Transformers via Generative Architecture Search","created":"2023-08-22","cited_by_count":1,"area":null},{"id":"2309.13972","title":"Audio classification with Dilated Convolution with Learnable Spacings","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2406.02021","title":"FFNet: MetaMixer-based Efficient Convolutional Mixer Design","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2406.14239","title":"LeYOLO, New Embedded Architecture for Object Detection","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2502.17154","title":"MaxGlaViT: A novel lightweight vision transformer-based approach for early diagnosis of glaucoma stages from fundus images","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2503.17110","title":"Beyond Accuracy: What Matters in Designing Well-Behaved Image Classification Models?","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2504.04124","title":"EMF: Event Meta Formers for Event-based Real-time Traffic Object Detection","created":"2025-04-05","cited_by_count":1,"area":null},{"id":"2505.02655","title":"SCFormer: Structured Channel-wise Transformer with Cumulative Historical State for Multivariate Time Series Forecasting","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2508.10817","title":"Mobile-Friendly Deep Learning for Plant Disease Detection: A Lightweight CNN Benchmark Across 101 Classes of 33 Crops","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2509.25570","title":"AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2510.13740","title":"Multi-Scale High-Resolution Logarithmic Grapher Module for Efficient Vision GNNs","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2602.20161","title":"Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2603.18004","title":"Unified Spatio-Temporal Token Scoring for Efficient Video VLMs","created":"2026-03-18","cited_by_count":1,"area":"mllm"},{"id":"2606.02092","title":"LALE: Lightweight-Transformer Architecture for Land-Cover Estimation","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.20909","title":"BELDE: Building a Large-scale Earth-observation Land-cover Dataset for Europe","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2307.12301","title":"Image Outlier Detection Without Training using RANSAC","created":"2023-07-23","cited_by_count":0,"area":null},{"id":"2310.01770","title":"A simple connection from loss flatness to compressed neural representations","created":"2023-10-03","cited_by_count":0,"area":null},{"id":"2311.05707","title":"FMViT: A multiple-frequency mixing Vision Transformer","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2312.09588","title":"NeuroFlow: Development of lightweight and efficient model integration scheduling strategy for autonomous driving system","created":"2023-12-15","cited_by_count":0,"area":null},{"id":"2403.15004","title":"ParFormer: A Vision Transformer with Parallel Mixer and Sparse Channel Attention Patch Embedding","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2404.15608","title":"Understanding and Improving CNNs with Complex Structure Tensor: A Biometrics Study","created":"2024-04-24","cited_by_count":0,"area":null}],"next_cursor":"100"}