{"total":33,"rows":[{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2312.09299","title":"Weight subcloning: direct initialization of transformers using larger pretrained ones","created":"2023-12-14","cited_by_count":30,"area":null},{"id":"2110.04035","title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","created":"2021-10-08","cited_by_count":23,"area":null},{"id":"2203.08887","title":"On Redundancy and Diversity in Cell-based Neural Architecture Search","created":"2022-03-16","cited_by_count":18,"area":null},{"id":"2111.10007","title":"FBNetV5: Neural Architecture Search for Multiple Tasks in One Run","created":"2021-11-19","cited_by_count":15,"area":null},{"id":"2411.10606","title":"AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment","created":"2024-11-15","cited_by_count":12,"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":"2308.07650","title":"EQ-Net: Elastic Quantization Neural Networks","created":"2023-08-15","cited_by_count":10,"area":null},{"id":"2309.06612","title":"Harmonic-NAS: Hardware-Aware Multimodal Neural Architecture Search on Resource-constrained Devices","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2207.07858","title":"The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network","created":"2022-07-16","cited_by_count":7,"area":null},{"id":"2602.03396","title":"Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspective","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2204.12833","title":"Transfer Learning with Pre-trained Conditional Generative Models","created":"2022-04-27","cited_by_count":4,"area":null},{"id":"2206.01366","title":"Supernet Training for Federated Image Classification under System Heterogeneity","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2208.08569","title":"ObfuNAS: A Neural Architecture Search-based DNN Obfuscation Approach","created":"2022-08-17","cited_by_count":4,"area":null},{"id":"2309.01947","title":"TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models","created":"2023-09-05","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":"2405.19915","title":"P$^2$-ViT: Power-of-Two Post-Training Quantization and Acceleration for Fully Quantized Vision Transformer","created":"2024-05-30","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":"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":"2307.03110","title":"LISSNAS: Locality-based Iterative Search Space Shrinkage for Neural Architecture Search","created":"2023-07-06","cited_by_count":2,"area":null},{"id":"2405.04536","title":"When Training-Free NAS Meets Vision Transformer: A Neural Tangent Kernel Perspective","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2203.13921","title":"A Semi-Decoupled Approach to Fast and Optimal Hardware-Software Co-Design of Neural Accelerators","created":"2022-03-25","cited_by_count":1,"area":null},{"id":"2312.16392","title":"Adaptive Depth Networks with Skippable Sub-Paths","created":"2023-12-27","cited_by_count":1,"area":null},{"id":"2402.13204","title":"SONATA: Self-adaptive Evolutionary Framework for Hardware-aware Neural Architecture Search","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2409.04829","title":"NASH: Neural Architecture and Accelerator Search for Multiplication-Reduced Hybrid Models","created":"2024-09-07","cited_by_count":1,"area":null},{"id":"2207.05420","title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","created":"2022-07-12","cited_by_count":0,"area":null},{"id":"2212.03415","title":"Slimmable Pruned Neural Networks","created":"2022-12-07","cited_by_count":0,"area":null},{"id":"2310.19820","title":"NetDistiller: Empowering Tiny Deep Learning via In-Situ Distillation","created":"2023-10-24","cited_by_count":0,"area":null},{"id":"2408.15484","title":"NAS-BNN: Neural Architecture Search for Binary Neural Networks","created":"2024-08-28","cited_by_count":0,"area":null},{"id":"2501.03782","title":"Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2507.11549","title":"A Memory-Efficient Framework for Deformable Transformer with Neural Architecture Search","created":"2025-07-13","cited_by_count":0,"area":null},{"id":"2511.22355","title":"AutoTailor: Automatic and Efficient Adaptive Model Deployment for Diverse Edge Devices","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2608.08489","title":"No Unique Minimizer, No Problem: On the Consistency of Robust Neural Classifiers","created":"2026-08-09","cited_by_count":0,"area":null}],"next_cursor":null}