{"total":63,"rows":[{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565,"area":null},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","cited_by_count":228,"area":null},{"id":"2301.05712","title":"A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends","created":"2023-01-13","cited_by_count":207,"area":null},{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188,"area":null},{"id":"2204.03645","title":"DaViT: Dual Attention Vision Transformers","created":"2022-04-07","cited_by_count":175,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2106.12620","title":"IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers","created":"2021-06-23","cited_by_count":127,"area":null},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126,"area":null},{"id":"2203.13278","title":"Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis","created":"2022-03-24","cited_by_count":86,"area":null},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2304.10970","title":"Can GPT-4 Perform Neural Architecture Search?","created":"2023-04-21","cited_by_count":74,"area":null},{"id":"2309.10438","title":"AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration","created":"2023-09-19","cited_by_count":70,"area":"diffusion"},{"id":"2106.10784","title":"iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients","created":"2021-06-21","cited_by_count":51,"area":null},{"id":"2105.15168","title":"MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens","created":"2021-05-31","cited_by_count":46,"area":null},{"id":"2211.08110","title":"HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers","created":"2022-11-15","cited_by_count":46,"area":"inference"},{"id":"2111.14725","title":"Searching the Search Space of Vision Transformer","created":"2021-11-29","cited_by_count":41,"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":"2106.13700","title":"ViTAS: Vision Transformer Architecture Search","created":"2021-06-25","cited_by_count":31,"area":null},{"id":"2203.12856","title":"Beyond Fixation: Dynamic Window Visual Transformer","created":"2022-03-24","cited_by_count":28,"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":"2111.11802","title":"Pruning Self-attentions into Convolutional Layers in Single Path","created":"2021-11-23","cited_by_count":24,"area":null},{"id":"2312.00634","title":"A Recent Survey of Vision Transformers for Medical Image Segmentation","created":"2023-12-01","cited_by_count":23,"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":"2203.15380","title":"SepViT: Separable Vision Transformer","created":"2022-03-29","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":"2210.05832","title":"SaiT: Sparse Vision Transformers through Adaptive Token Pruning","created":"2022-10-11","cited_by_count":15,"area":"inference"},{"id":"2108.01899","title":"Generic Neural Architecture Search via Regression","created":"2021-08-04","cited_by_count":14,"area":null},{"id":"2108.09671","title":"Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift","created":"2021-08-22","cited_by_count":14,"area":null},{"id":"2304.03282","title":"Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention","created":"2023-04-06","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":"2109.00642","title":"Searching for Efficient Multi-Stage Vision Transformers","created":"2021-09-01","cited_by_count":9,"area":null},{"id":"2204.05941","title":"Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search","created":"2022-04-12","cited_by_count":9,"area":null},{"id":"2206.06292","title":"MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing","created":"2022-06-13","cited_by_count":9,"area":null},{"id":"2106.07550","title":"Attention mechanisms and deep learning for machine vision: A survey of the state of the art","created":"2021-06-03","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":"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":"2111.13204","title":"BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule","created":"2021-11-25","cited_by_count":5,"area":null},{"id":"2209.13139","title":"Searching a High-Performance Feature Extractor for Text Recognition Network","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2304.03481","title":"PSLT: A Light-weight Vision Transformer with Ladder Self-Attention and Progressive Shift","created":"2023-04-07","cited_by_count":5,"area":null},{"id":"2403.05064","title":"Unsupervised Graph Neural Architecture Search with Disentangled Self-supervision","created":"2024-03-08","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":"2410.00350","title":"Efficient Training of Large Vision Models via Advanced Automated Progressive Learning","created":"2024-09-06","cited_by_count":5,"area":"diffusion"},{"id":"2504.12971","title":"Transferrable Surrogates in Expressive Neural Architecture Search Spaces","created":"2025-04-17","cited_by_count":5,"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":"2311.04950","title":"Lightweight Diffusion Models with Distillation-Based Block Neural Architecture Search","created":"2023-11-08","cited_by_count":4,"area":"diffusion"},{"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":"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":"2204.04918","title":"When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search","created":"2022-04-11","cited_by_count":3,"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":"2305.09211","title":"CB-HVTNet: A channel-boosted hybrid vision transformer network for lymphocyte assessment in histopathological images","created":"2023-05-16","cited_by_count":2,"area":null},{"id":"2308.10064","title":"Efficient Representation Learning for Healthcare with Cross-Architectural Self-Supervision","created":"2023-08-19","cited_by_count":2,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2203.08130","title":"One Network Doesn't Rule Them All: Moving Beyond Handcrafted Architectures in Self-Supervised Learning","created":"2022-03-15","cited_by_count":1,"area":null},{"id":"2409.17566","title":"Flexiffusion: Segment-wise Neural Architecture Search for Flexible Denoising Schedule","created":"2024-09-26","cited_by_count":1,"area":"diffusion"},{"id":"2506.02488","title":"Flexiffusion: Training-Free Segment-Wise Neural Architecture Search for Efficient Diffusion Models","created":"2025-06-03","cited_by_count":1,"area":"diffusion"},{"id":"2511.21136","title":"Efficient Training for Human Video Generation with Entropy-Guided Prioritized Progressive Learning","created":"2025-11-26","cited_by_count":1,"area":"diffusion"},{"id":"2207.03006","title":"MaiT: Leverage Attention Masks for More Efficient Image Transformers","created":"2022-07-06","cited_by_count":0,"area":null},{"id":"2310.15074","title":"MGAS: Multi-Granularity Architecture Search for Trade-Off Between Model Effectiveness and Efficiency","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2411.10077","title":"Hierarchical mutual distillation for multi-view fusion: Learning from all possible view combinations","created":"2024-11-15","cited_by_count":0,"area":null},{"id":"2511.21122","title":"Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models","created":"2025-11-26","cited_by_count":0,"area":null}],"next_cursor":null}