{"total":168,"rows":[{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656,"area":null},{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497,"area":null},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241,"area":null},{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234,"area":null},{"id":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207,"area":null},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2206.04673","title":"Neural Prompt Search","created":"2022-06-09","cited_by_count":135,"area":null},{"id":"2212.08059","title":"Rethinking Vision Transformers for MobileNet Size and Speed","created":"2022-12-15","cited_by_count":121,"area":null},{"id":"2204.07154","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","created":"2022-04-14","cited_by_count":88,"area":null},{"id":"2306.07967","title":"One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning","created":"2023-06-13","cited_by_count":85,"area":null},{"id":"2205.13213","title":"Fast Vision Transformers with HiLo Attention","created":"2022-05-26","cited_by_count":78,"area":null},{"id":"2110.04869","title":"Global Vision Transformer Pruning with Hessian-Aware Saliency","created":"2021-10-10","cited_by_count":70,"area":null},{"id":"2201.00814","title":"Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space","created":"2022-01-03","cited_by_count":66,"area":null},{"id":"2306.06189","title":"FasterViT: Fast Vision Transformers with Hierarchical Attention","created":"2023-06-09","cited_by_count":65,"area":null},{"id":"2211.16056","title":"NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers","created":"2022-11-29","cited_by_count":61,"area":null},{"id":"2305.15896","title":"MixFormerV2: Efficient Fully Transformer Tracking","created":"2023-05-25","cited_by_count":57,"area":null},{"id":"2107.02960","title":"GLiT: Neural Architecture Search for Global and Local Image Transformer","created":"2021-07-07","cited_by_count":53,"area":null},{"id":"2203.15610","title":"LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT","created":"2022-03-29","cited_by_count":50,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2309.12673","title":"On Sparse Modern Hopfield Model","created":"2023-09-22","cited_by_count":42,"area":null},{"id":"2111.14725","title":"Searching the Search Space of Vision Transformer","created":"2021-11-29","cited_by_count":41,"area":null},{"id":"2302.01107","title":"A Survey on Efficient Training of Transformers","created":"2023-02-02","cited_by_count":39,"area":null},{"id":"2203.14509","title":"Automated Progressive Learning for Efficient Training of Vision Transformers","created":"2022-03-28","cited_by_count":37,"area":null},{"id":"2306.08107","title":"AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks","created":"2023-06-13","cited_by_count":35,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2312.03014","title":"Foundation Models for Weather and Climate Data Understanding: A Comprehensive Survey","created":"2023-12-05","cited_by_count":34,"area":null},{"id":"2203.12217","title":"Training-free Transformer Architecture Search","created":"2022-03-23","cited_by_count":33,"area":null},{"id":"2210.01035","title":"Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning","created":"2022-10-03","cited_by_count":33,"area":null},{"id":"2304.06306","title":"Efficient Multimodal Fusion via Interactive Prompting","created":"2023-04-13","cited_by_count":32,"area":null},{"id":"2211.10526","title":"Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference","created":"2022-11-18","cited_by_count":28,"area":null},{"id":"2403.19232","title":"AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search","created":"2024-03-28","cited_by_count":28,"area":null},{"id":"2201.06618","title":"VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer","created":"2022-01-17","cited_by_count":27,"area":null},{"id":"2206.09325","title":"EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm","created":"2022-06-19","cited_by_count":27,"area":null},{"id":"2111.05297","title":"Sliced Recursive Transformer","created":"2021-11-09","cited_by_count":26,"area":null},{"id":"2301.10936","title":"PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation","created":"2023-01-26","cited_by_count":25,"area":null},{"id":"2111.11802","title":"Pruning Self-attentions into Convolutional Layers in Single Path","created":"2021-11-23","cited_by_count":24,"area":null},{"id":"2207.01580","title":"Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks","created":"2022-07-04","cited_by_count":24,"area":null},{"id":"2301.03831","title":"Dynamic Grained Encoder for Vision Transformers","created":"2023-01-10","cited_by_count":24,"area":null},{"id":"2311.11413","title":"Large Pre-trained time series models for cross-domain Time series analysis tasks","created":"2023-11-19","cited_by_count":23,"area":null},{"id":"2303.06908","title":"CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention","created":"2023-03-13","cited_by_count":18,"area":null},{"id":"2305.00603","title":"Consolidator: Mergeable Adapter with Grouped Connections for Visual Adaptation","created":"2023-04-30","cited_by_count":18,"area":null},{"id":"2207.13955","title":"Neural Architecture Search on Efficient Transformers and Beyond","created":"2022-07-28","cited_by_count":17,"area":null},{"id":"2208.04321","title":"Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment","created":"2022-08-08","cited_by_count":17,"area":null},{"id":"2111.11124","title":"Mesa: A Memory-saving Training Framework for Transformers","created":"2021-11-22","cited_by_count":16,"area":null},{"id":"2111.13336","title":"MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection","created":"2021-11-26","cited_by_count":16,"area":null},{"id":"2203.15380","title":"SepViT: Separable Vision Transformer","created":"2022-03-29","cited_by_count":16,"area":null},{"id":"2407.02348","title":"Agreement-Based Cascading for Efficient Inference","created":"2024-07-02","cited_by_count":16,"area":null},{"id":"2501.06907","title":"Deep Learning and Foundation Models for Weather Prediction: A Survey","created":"2025-01-12","cited_by_count":16,"area":null},{"id":"2202.11921","title":"Auto-scaling Vision Transformers without Training","created":"2022-02-24","cited_by_count":15,"area":null},{"id":"2203.02094","title":"LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models","created":"2022-03-04","cited_by_count":14,"area":null},{"id":"2406.03722","title":"Offline Multi-Objective Optimization","created":"2024-06-06","cited_by_count":14,"area":null},{"id":"2309.05015","title":"DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices","created":"2023-09-10","cited_by_count":13,"area":null},{"id":"2207.03677","title":"SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning","created":"2022-07-08","cited_by_count":12,"area":null},{"id":"2312.16733","title":"SuperServe: Fine-Grained Inference Serving for Unpredictable Workloads","created":"2023-12-27","cited_by_count":12,"area":null},{"id":"2404.13528","title":"SmartMem: Layout Transformation Elimination and Adaptation for Efficient DNN Execution on Mobile","created":"2024-04-21","cited_by_count":12,"area":null},{"id":"2202.06268","title":"BViT: Broad Attention based Vision Transformer","created":"2022-02-13","cited_by_count":10,"area":null},{"id":"2203.01587","title":"Multi-Tailed Vision Transformer for Efficient Inference","created":"2022-03-03","cited_by_count":10,"area":null},{"id":"2210.13889","title":"Clinically-Inspired Multi-Agent Transformers for Disease Trajectory Forecasting from Multimodal Data","created":"2022-10-25","cited_by_count":10,"area":null},{"id":"2303.09730","title":"ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices","created":"2023-03-17","cited_by_count":10,"area":null},{"id":"2405.10299","title":"HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models","created":"2024-05-16","cited_by_count":10,"area":null},{"id":"2407.05010","title":"PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference","created":"2024-07-06","cited_by_count":10,"area":null},{"id":"2310.16898","title":"MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory","created":"2023-10-25","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":"2403.18708","title":"Dense Vision Transformer Compression with Few Samples","created":"2024-03-27","cited_by_count":9,"area":null},{"id":"2109.00240","title":"Joint Graph Learning and Matching for Semantic Feature Correspondence","created":"2021-09-01","cited_by_count":8,"area":null},{"id":"2205.08119","title":"ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks","created":"2022-05-17","cited_by_count":8,"area":null},{"id":"2403.15835","title":"Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression","created":"2024-03-23","cited_by_count":8,"area":null},{"id":"2410.11674","title":"LLM-Mixer: Multiscale Mixing in LLMs for Time Series Forecasting","created":"2024-10-15","cited_by_count":8,"area":null},{"id":"2207.10341","title":"UFO: Unified Feature Optimization","created":"2022-07-21","cited_by_count":7,"area":null},{"id":"2211.01484","title":"Data Level Lottery Ticket Hypothesis for Vision Transformers","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2303.15569","title":"Core-Periphery Principle Guided Redesign of Self-Attention in Transformers","created":"2023-03-27","cited_by_count":7,"area":null},{"id":"2407.18930","title":"Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition","created":"2024-07-10","cited_by_count":7,"area":null},{"id":"2109.10060","title":"DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers","created":"2021-09-21","cited_by_count":6,"area":null},{"id":"2203.06841","title":"STDAN: Deformable Attention Network for Space-Time Video Super-Resolution","created":"2022-03-14","cited_by_count":6,"area":null},{"id":"2301.13803","title":"Fairness-aware Vision Transformer via Debiased Self-Attention","created":"2023-01-31","cited_by_count":6,"area":null},{"id":"2404.13648","title":"Data-independent Module-aware Pruning for Hierarchical Vision Transformers","created":"2024-04-21","cited_by_count":6,"area":null},{"id":"2412.04786","title":"Slicing Vision Transformer for Flexible Inference","created":"2024-12-06","cited_by_count":6,"area":null},{"id":"2509.26037","title":"CoLLM-NAS: Collaborative Large Language Models for Efficient Knowledge-Guided Neural Architecture Search","created":"2025-09-30","cited_by_count":6,"area":null},{"id":"2201.12725","title":"Generalized Global Ranking-Aware Neural Architecture Ranker for Efficient Image Classifier Search","created":"2022-01-30","cited_by_count":5,"area":null},{"id":"2203.09041","title":"DATA: Domain-Aware and Task-Aware Self-supervised Learning","created":"2022-03-17","cited_by_count":5,"area":null},{"id":"2302.07734","title":"TFormer: A Transmission-Friendly ViT Model for IoT Devices","created":"2023-02-15","cited_by_count":5,"area":null},{"id":"2310.05654","title":"No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling","created":"2023-10-09","cited_by_count":5,"area":null},{"id":"2402.02105","title":"ParZC: Parametric Zero-Cost Proxies for Efficient NAS","created":"2024-02-03","cited_by_count":5,"area":null},{"id":"2405.20838","title":"einspace: Searching for Neural Architectures from Fundamental Operations","created":"2024-05-31","cited_by_count":5,"area":null},{"id":"2502.04592","title":"CAMEF: Causal-Augmented Multi-Modality Event-Driven Financial Forecasting by Integrating Time Series Patterns and Salient Macroeconomic Announcements","created":"2025-02-07","cited_by_count":5,"area":null},{"id":"2504.02168","title":"MDP: Multidimensional Vision Model Pruning with Latency Constraint","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2504.12971","title":"Transferrable Surrogates in Expressive Neural Architecture Search Spaces","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2505.07300","title":"L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformers","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2210.07634","title":"Pareto-aware Neural Architecture Generation for Diverse Computational Budgets","created":"2022-10-14","cited_by_count":4,"area":null},{"id":"2306.09295","title":"Neural Fine-Tuning Search for Few-Shot Learning","created":"2023-06-15","cited_by_count":4,"area":null},{"id":"2307.08300","title":"ShiftNAS: Improving One-shot NAS via Probability Shift","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2312.10440","title":"Weight-Entanglement Meets Gradient-Based Neural Architecture Search","created":"2023-12-16","cited_by_count":4,"area":null},{"id":"2403.01326","title":"DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions","created":"2024-03-02","cited_by_count":4,"area":null},{"id":"2403.05406","title":"Considering Nonstationary within Multivariate Time Series with Variational Hierarchical Transformer for Forecasting","created":"2024-03-08","cited_by_count":4,"area":null},{"id":"2407.18175","title":"Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers","created":"2024-07-25","cited_by_count":4,"area":null},{"id":"2503.04118","title":"TimeFound: A Foundation Model for Time Series Forecasting","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2503.10740","title":"Subnet-Aware Dynamic Supernet Training for Neural Architecture Search","created":"2025-03-13","cited_by_count":4,"area":null},{"id":"2308.11331","title":"GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training","created":"2023-08-22","cited_by_count":3,"area":null},{"id":"2310.01180","title":"Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing","created":"2023-10-02","cited_by_count":3,"area":null}],"next_cursor":"100"}