{"total":123,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539,"area":null},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2201.09873","title":"Transformers in Medical Imaging: A Survey","created":"2022-01-24","cited_by_count":245,"area":null},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241,"area":null},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","cited_by_count":228,"area":null},{"id":"2201.08821","title":"Representing Long-Range Context for Graph Neural Networks with Global Attention","created":"2022-01-21","cited_by_count":195,"area":null},{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188,"area":null},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162,"area":null},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"area":null},{"id":"2108.00708","title":"Group Fisher Pruning for Practical Network Compression","created":"2021-08-02","cited_by_count":131,"area":null},{"id":"2107.10845","title":"QuantumNAS: Noise-Adaptive Search for Robust Quantum Circuits","created":"2021-07-22","cited_by_count":98,"area":null},{"id":"2111.12763","title":"Sparse is Enough in Scaling Transformers","created":"2021-11-24","cited_by_count":86,"area":null},{"id":"2310.07707","title":"MatFormer: Nested Transformer for Elastic Inference","created":"2023-10-11","cited_by_count":85,"area":null},{"id":"2103.10619","title":"Scalable Vision Transformers with Hierarchical Pooling","created":"2021-03-19","cited_by_count":84,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2101.09336","title":"A Comprehensive Survey on Hardware-Aware Neural Architecture Search","created":"2021-01-22","cited_by_count":61,"area":null},{"id":"2105.14444","title":"NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search","created":"2021-05-30","cited_by_count":56,"area":null},{"id":"2111.14725","title":"Searching the Search Space of Vision Transformer","created":"2021-11-29","cited_by_count":41,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"area":null},{"id":"2102.07954","title":"AlphaNet: Improved Training of Supernets with Alpha-Divergence","created":"2021-02-16","cited_by_count":36,"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":"2203.12217","title":"Training-free Transformer Architecture Search","created":"2022-03-23","cited_by_count":33,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2107.13686","title":"AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models","created":"2021-07-29","cited_by_count":31,"area":null},{"id":"2310.16712","title":"LLM Performance Predictors are good initializers for Architecture Search","created":"2023-10-25","cited_by_count":29,"area":null},{"id":"2110.10030","title":"Accelerating Framework of Transformer by Hardware Design and Model Compression Co-Optimization","created":"2021-10-19","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":"2110.09310","title":"Energon: Towards Efficient Acceleration of Transformers Using Dynamic Sparse Attention","created":"2021-10-18","cited_by_count":26,"area":null},{"id":"2205.01500","title":"Meta Learning for Natural Language Processing: A Survey","created":"2022-05-03","cited_by_count":26,"area":null},{"id":"2303.04185","title":"Gradient-Free Structured Pruning with Unlabeled Data","created":"2023-03-07","cited_by_count":26,"area":null},{"id":"2302.14705","title":"AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers","created":"2023-02-28","cited_by_count":24,"area":null},{"id":"2202.07959","title":"EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation","created":"2022-02-16","cited_by_count":21,"area":null},{"id":"2105.15089","title":"Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model","created":"2021-05-31","cited_by_count":20,"area":null},{"id":"2203.12758","title":"Mokey: Enabling Narrow Fixed-Point Inference for Out-of-the-Box Floating-Point Transformer Models","created":"2022-03-23","cited_by_count":19,"area":null},{"id":"2105.03596","title":"Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms","created":"2021-05-08","cited_by_count":18,"area":null},{"id":"2304.03986","title":"SwiftTron: An Efficient Hardware Accelerator for Quantized Transformers","created":"2023-04-08","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":"2106.08630","title":"HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning","created":"2021-06-16","cited_by_count":16,"area":null},{"id":"2204.11797","title":"PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution","created":"2022-04-25","cited_by_count":16,"area":null},{"id":"2401.15347","title":"A Comprehensive Survey of Compression Algorithms for Language Models","created":"2024-01-27","cited_by_count":15,"area":null},{"id":"2106.02435","title":"You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient","created":"2021-06-04","cited_by_count":14,"area":null},{"id":"2108.01899","title":"Generic Neural Architecture Search via Regression","created":"2021-08-04","cited_by_count":14,"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":"2204.04705","title":"SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems","created":"2022-04-10","cited_by_count":14,"area":null},{"id":"2207.05022","title":"STI: Turbocharge NLP Inference at the Edge via Elastic Pipelining","created":"2022-07-11","cited_by_count":14,"area":null},{"id":"2304.06051","title":"Open-TransMind: A New Baseline and Benchmark for 1st Foundation Model Challenge of Intelligent Transportation","created":"2023-04-12","cited_by_count":14,"area":null},{"id":"2103.15750","title":"Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design","created":"2021-03-25","cited_by_count":13,"area":null},{"id":"2105.14669","title":"Memory-Efficient Differentiable Transformer Architecture Search","created":"2021-05-31","cited_by_count":13,"area":null},{"id":"2110.14895","title":"Pipeline Parallelism for Inference on Heterogeneous Edge Computing","created":"2021-10-28","cited_by_count":13,"area":null},{"id":"2109.07383","title":"RankNAS: Efficient Neural Architecture Search by Pairwise Ranking","created":"2021-09-15","cited_by_count":12,"area":null},{"id":"2110.08352","title":"Omni-sparsity DNN: Fast Sparsity Optimization for On-Device Streaming E2E ASR via Supernet","created":"2021-10-15","cited_by_count":12,"area":null},{"id":"2205.11656","title":"FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?","created":"2022-05-23","cited_by_count":12,"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":"2302.06117","title":"The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment","created":"2023-02-13","cited_by_count":11,"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":"2102.06336","title":"Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices","created":"2021-02-12","cited_by_count":9,"area":null},{"id":"2109.00642","title":"Searching for Efficient Multi-Stage Vision Transformers","created":"2021-09-01","cited_by_count":9,"area":null},{"id":"2303.15742","title":"System-status-aware Adaptive Network for Online Streaming Video Understanding","created":"2023-03-28","cited_by_count":9,"area":null},{"id":"2306.00288","title":"Training-free Neural Architecture Search for RNNs and Transformers","created":"2023-06-01","cited_by_count":9,"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":"2310.03971","title":"Quantized Transformer Language Model Implementations on Edge Devices","created":"2023-10-06","cited_by_count":9,"area":null},{"id":"2111.01203","title":"One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search","created":"2021-11-01","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":"2210.00640","title":"Wide Attention Is The Way Forward For Transformers?","created":"2022-10-02","cited_by_count":8,"area":null},{"id":"2104.07874","title":"Translational NLP: A New Paradigm and General Principles for Natural Language Processing Research","created":"2021-04-16","cited_by_count":7,"area":null},{"id":"2207.07187","title":"NASRec: Weight Sharing Neural Architecture Search for Recommender Systems","created":"2022-07-14","cited_by_count":7,"area":null},{"id":"2207.10341","title":"UFO: Unified Feature Optimization","created":"2022-07-21","cited_by_count":7,"area":null},{"id":"2402.07545","title":"TransAxx: Efficient Transformers with Approximate Computing","created":"2024-02-12","cited_by_count":7,"area":null},{"id":"2505.01386","title":"CATransformers: Carbon Aware Transformers Through Joint Model-Hardware Optimization","created":"2025-05-02","cited_by_count":7,"area":null},{"id":"2509.05657","title":"LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding","created":"2025-09-06","cited_by_count":7,"area":null},{"id":"2110.04711","title":"SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions","created":"2021-10-10","cited_by_count":6,"area":null},{"id":"2205.10358","title":"A Hardware-Aware Framework for Accelerating Neural Architecture Search Across Modalities","created":"2022-05-19","cited_by_count":6,"area":null},{"id":"2111.15106","title":"MAPLE: Microprocessor A Priori for Latency Estimation","created":"2021-11-30","cited_by_count":5,"area":null},{"id":"2208.10861","title":"FocusFormer: Focusing on What We Need via Architecture Sampler","created":"2022-08-23","cited_by_count":5,"area":null},{"id":"2210.13361","title":"NASA: Neural Architecture Search and Acceleration for Hardware Inspired Hybrid Networks","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2303.13121","title":"DetOFA: Efficient Training of Once-for-All Networks for Object Detection Using Path Filter","created":"2023-03-23","cited_by_count":5,"area":null},{"id":"2107.08199","title":"Dynamic Transformer for Efficient Machine Translation on Embedded Devices","created":"2021-07-17","cited_by_count":4,"area":null},{"id":"2308.15609","title":"InstaTune: Instantaneous Neural Architecture Search During Fine-Tuning","created":"2023-08-29","cited_by_count":4,"area":null},{"id":"2309.09003","title":"RingMo-lite: A Remote Sensing Multi-task Lightweight Network with CNN-Transformer Hybrid Framework","created":"2023-09-16","cited_by_count":4,"area":null},{"id":"2311.04943","title":"MathNAS: If Blocks Have a Role in Mathematical Architecture Design","created":"2023-11-08","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":"2403.00353","title":"MS-Net: A Multi-Path Sparse Model for Motion Prediction in Multi-Scenes","created":"2024-03-01","cited_by_count":4,"area":null},{"id":"2405.00888","title":"DynaMo: Accelerating Language Model Inference with Dynamic Multi-Token Sampling","created":"2024-05-01","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":"2510.17700","title":"Elastic ViTs from Pretrained Models without Retraining","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2106.04010","title":"FEAR: A Simple Lightweight Method to Rank Architectures","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2201.12854","title":"Fast Monte-Carlo Approximation of the Attention Mechanism","created":"2022-01-30","cited_by_count":3,"area":null},{"id":"2204.02601","title":"Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency","created":"2022-04-06","cited_by_count":3,"area":null},{"id":"2204.12950","title":"MAPLE-Edge: A Runtime Latency Predictor for Edge Devices","created":"2022-04-27","cited_by_count":3,"area":null},{"id":"2301.09262","title":"AttMEMO : Accelerating Transformers with Memoization on Big Memory Systems","created":"2023-01-23","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},{"id":"2403.07921","title":"Merino: Entropy-driven Design for Generative Language Models on IoT Devices","created":"2024-02-28","cited_by_count":3,"area":null},{"id":"2405.20202","title":"One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2109.08003","title":"The NiuTrans System for the WMT21 Efficiency Task","created":"2021-09-16","cited_by_count":2,"area":null},{"id":"2111.07547","title":"Searching for TrioNet: Combining Convolution with Local and Global Self-Attention","created":"2021-11-15","cited_by_count":2,"area":null},{"id":"2204.03916","title":"A Survey of Supernet Optimization and its Applications: Spatial and Temporal Optimization for Neural Architecture Search","created":"2022-04-08","cited_by_count":2,"area":null},{"id":"2212.08330","title":"Convolution-enhanced Evolving Attention Networks","created":"2022-12-16","cited_by_count":2,"area":null}],"next_cursor":"100"}