{"list":"other","total":96,"rows":[{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"1709.01686","title":"BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks","created":"2017-09-06","cited_by_count":596},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408},{"id":"2201.05596","title":"DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale","created":"2022-01-14","cited_by_count":404},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362},{"id":"2004.12993","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","created":"2020-04-27","cited_by_count":332},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310},{"id":"2006.04152","title":"BERT Loses Patience: Fast and Robust Inference with Early Exit","created":"2020-06-07","cited_by_count":273},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253},{"id":"2308.00951","title":"From Sparse to Soft Mixtures of Experts","created":"2023-08-02","cited_by_count":248},{"id":"2111.15668","title":"AdaViT: Adaptive Vision Transformers for Efficient Image Recognition","created":"2021-11-30","cited_by_count":228},{"id":"2303.17604","title":"Token Merging for Fast Stable Diffusion","created":"2023-03-30","cited_by_count":224},{"id":"1907.04840","title":"Sparse Networks from Scratch: Faster Training without Losing Performance","created":"2019-07-10","cited_by_count":213},{"id":"2206.02770","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts","created":"2022-06-06","cited_by_count":203},{"id":"2402.01739","title":"OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models","created":"2024-01-29","cited_by_count":187},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183},{"id":"1511.06297","title":"Conditional Computation in Neural Networks for faster models","created":"2015-11-19","cited_by_count":167},{"id":"1702.07811","title":"Adaptive Neural Networks for Efficient Inference","created":"2017-02-25","cited_by_count":163},{"id":"1909.00015","title":"Adaptively Sparse Transformers","created":"2019-08-30","cited_by_count":155},{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152},{"id":"1904.03375","title":"Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling","created":"2019-04-06","cited_by_count":151},{"id":"2209.01667","title":"A Review of Sparse Expert Models in Deep Learning","created":"2022-09-04","cited_by_count":148},{"id":"2205.06266","title":"Lifting the Curse of Multilinguality by Pre-training Modular Transformers","created":"2022-05-12","cited_by_count":146},{"id":"2110.07560","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","created":"2021-10-14","cited_by_count":144},{"id":"2106.12620","title":"IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers","created":"2021-06-23","cited_by_count":127},{"id":"1711.01239","title":"Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning","created":"2017-11-03","cited_by_count":126},{"id":"2312.01026","title":"Token Fusion: Bridging the Gap between Token Pruning and Token Merging","created":"2023-12-02","cited_by_count":125},{"id":"2103.04505","title":"Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges","created":"2021-03-08","cited_by_count":115},{"id":"2110.04260","title":"Taming Sparsely Activated Transformer with Stochastic Experts","created":"2021-10-08","cited_by_count":113},{"id":"1912.03203","title":"Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference","created":"2019-12-06","cited_by_count":91},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90},{"id":"2111.12763","title":"Sparse is Enough in Scaling Transformers","created":"2021-11-24","cited_by_count":86},{"id":"2206.04046","title":"Sparse Mixture-of-Experts are Domain Generalizable Learners","created":"2022-06-08","cited_by_count":85},{"id":"2303.09752","title":"CoLT5: Faster Long-Range Transformers with Conditional Computation","created":"2023-03-17","cited_by_count":84},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83},{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82},{"id":"1902.07816","title":"Mixture Models for Diverse Machine Translation: Tricks of the Trade","created":"2019-02-20","cited_by_count":77},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73},{"id":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72},{"id":"2004.12814","title":"Why should we add early exits to neural networks?","created":"2020-04-27","cited_by_count":70},{"id":"2202.12015","title":"Learning to Merge Tokens in Vision Transformers","created":"2022-02-24","cited_by_count":65},{"id":"2402.05859","title":"Learning to Route Among Specialized Experts for Zero-Shot Generalization","created":"2024-02-08","cited_by_count":65},{"id":"2205.12647","title":"Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation","created":"2022-05-25","cited_by_count":62},{"id":"2210.05144","title":"Mixture of Attention Heads: Selecting Attention Heads Per Token","created":"2022-10-11","cited_by_count":60},{"id":"2303.17605","title":"SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer","created":"2023-03-30","cited_by_count":60},{"id":"2308.04657","title":"Which Tokens to Use? Investigating Token Reduction in Vision Transformers","created":"2023-08-09","cited_by_count":60},{"id":"2104.13400","title":"FrameExit: Conditional Early Exiting for Efficient Video Recognition","created":"2021-04-27","cited_by_count":59},{"id":"2105.14217","title":"Less is More: Pay Less Attention in Vision Transformers","created":"2021-05-29","cited_by_count":53},{"id":"2205.15769","title":"Concept-level Debugging of Part-Prototype Networks","created":"2022-05-31","cited_by_count":52},{"id":"2306.07050","title":"Revisiting Token Pruning for Object Detection and Instance Segmentation","created":"2023-06-12","cited_by_count":50},{"id":"2009.13239","title":"Scalable Transfer Learning with Expert Models","created":"2020-09-28","cited_by_count":49},{"id":"2105.09259","title":"Learning Language Specific Sub-network for Multilingual Machine Translation","created":"2021-05-19","cited_by_count":48},{"id":"2209.08310","title":"Learning to Weight Samples for Dynamic Early-exiting Networks","created":"2022-09-17","cited_by_count":44},{"id":"2211.11152","title":"You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model","created":"2022-11-21","cited_by_count":43},{"id":"2203.13240","title":"Token Dropping for Efficient BERT Pretraining","created":"2022-03-24","cited_by_count":42},{"id":"2106.05409","title":"Zero Time Waste: Recycling Predictions in Early Exit Neural Networks","created":"2021-06-09","cited_by_count":39},{"id":"2402.07573","title":"Goal-Oriented and Semantic Communication in 6G AI-Native Networks: The 6G-GOALS Approach","created":"2024-02-12","cited_by_count":39},{"id":"2305.18390","title":"Emergent Modularity in Pre-trained Transformers","created":"2023-05-28","cited_by_count":37},{"id":"2206.02713","title":"Is a Modular Architecture Enough?","created":"2022-06-06","cited_by_count":36},{"id":"2310.07096","title":"Sparse Universal Transformer","created":"2023-10-11","cited_by_count":32},{"id":"2006.16581","title":"Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images","created":"2020-06-30","cited_by_count":28},{"id":"2202.13914","title":"Combining Modular Skills in Multitask Learning","created":"2022-02-28","cited_by_count":28},{"id":"2302.06586","title":"Stitchable Neural Networks","created":"2023-02-13","cited_by_count":26},{"id":"2401.15969","title":"Routers in Vision Mixture of Experts: An Empirical Study","created":"2024-01-29","cited_by_count":23},{"id":"2402.15175","title":"Unified View of Grokking, Double Descent and Emergent Abilities: A Perspective from Circuits Competition","created":"2024-02-23","cited_by_count":23},{"id":"2301.13195","title":"Adaptive Computation with Elastic Input Sequence","created":"2023-01-30","cited_by_count":22},{"id":"2307.02321","title":"MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers","created":"2023-07-05","cited_by_count":20},{"id":"1510.02879","title":"Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain","created":"2015-10-10","cited_by_count":19},{"id":"2311.03035","title":"GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation","created":"2023-11-06","cited_by_count":19},{"id":"2106.03527","title":"Multi-Exit Semantic Segmentation Networks","created":"2021-06-07","cited_by_count":18},{"id":"2111.00230","title":"Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning","created":"2021-10-30","cited_by_count":16},{"id":"2306.04529","title":"Git-Theta: A Git Extension for Collaborative Development of Machine Learning Models","created":"2023-06-07","cited_by_count":15},{"id":"2109.12188","title":"Predicting Attention Sparsity in Transformers","created":"2021-09-24","cited_by_count":13},{"id":"2104.10461","title":"Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning","created":"2021-04-21","cited_by_count":9},{"id":"2203.12559","title":"A Scalable Model Specialization Framework for Training and Inference using Submodels and its Application to Speech Model Personalization","created":"2022-03-23","cited_by_count":8},{"id":"2206.00254","title":"A Unified Multi-Task Semantic Communication System with Domain Adaptation","created":"2022-06-01","cited_by_count":7},{"id":"2312.10193","title":"Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference","created":"2023-12-15","cited_by_count":6},{"id":"2301.07473","title":"Discrete Latent Structure in Neural Networks","created":"2023-01-18","cited_by_count":5},{"id":"2301.12168","title":"Anticipate, Ensemble and Prune: Improving Convolutional Neural Networks via Aggregated Early Exits","created":"2023-01-28","cited_by_count":3},{"id":"2304.10306","title":"FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits","created":"2023-04-20","cited_by_count":3}],"next_cursor":null}