{"list":"other","total":75,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"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":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"2211.14730","title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","created":"2022-11-27","cited_by_count":2039},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2106.13008","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","created":"2021-06-24","cited_by_count":1676},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"2310.06625","title":"iTransformer: Inverted Transformers Are Effective for Time Series Forecasting","created":"2023-10-10","cited_by_count":931},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"1703.07015","title":"Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks","created":"2017-03-21","cited_by_count":879},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"2310.10688","title":"A decoder-only foundation model for time-series forecasting","created":"2023-10-14","cited_by_count":692},{"id":"1801.04062","title":"MINE: Mutual Information Neural Estimation","created":"2018-01-12","cited_by_count":683},{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"2402.02592","title":"Unified Training of Universal Time Series Forecasting Transformers","created":"2024-02-04","cited_by_count":614},{"id":"1905.06922","title":"On Variational Bounds of Mutual Information","created":"2019-05-16","cited_by_count":559},{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497},{"id":"2402.03885","title":"MOMENT: A Family of Open Time-series Foundation Models","created":"2024-02-06","cited_by_count":482},{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399},{"id":"2205.14415","title":"Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting","created":"2022-05-28","cited_by_count":391},{"id":"2105.06643","title":"Monash Time Series Forecasting Archive","created":"2021-05-14","cited_by_count":267},{"id":"2404.02258","title":"Mixture-of-Depths: Dynamically allocating compute in transformer-based language models","created":"2024-04-02","cited_by_count":258},{"id":"2308.00951","title":"From Sparse to Soft Mixtures of Experts","created":"2023-08-02","cited_by_count":248},{"id":"2303.06053","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","created":"2023-03-10","cited_by_count":240},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237},{"id":"2410.10393","title":"GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation","created":"2024-10-14","cited_by_count":212},{"id":"2212.05055","title":"Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints","created":"2022-12-09","cited_by_count":209},{"id":"2402.02368","title":"Timer: Generative Pre-trained Transformers Are Large Time Series Models","created":"2024-02-04","cited_by_count":208},{"id":"2307.03756","title":"FITS: Modeling Time Series with $10k$ Parameters","created":"2023-07-06","cited_by_count":195},{"id":"2404.13628","title":"Mixture of LoRA Experts","created":"2024-04-21","cited_by_count":181},{"id":"2502.00816","title":"Sundial: A Family of Highly Capable Time Series Foundation Models","created":"2025-02-02","cited_by_count":180},{"id":"2204.09179","title":"On the Representation Collapse of Sparse Mixture of Experts","created":"2022-04-20","cited_by_count":157},{"id":"2310.09751","title":"UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting","created":"2023-10-15","cited_by_count":144},{"id":"2210.17451","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","created":"2022-10-31","cited_by_count":137},{"id":"2406.16554","title":"LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training","created":"2024-06-24","cited_by_count":123},{"id":"2410.16032","title":"TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis","created":"2024-10-21","cited_by_count":116},{"id":"2310.08278","title":"Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting","created":"2023-10-12","cited_by_count":113},{"id":"2403.00131","title":"UniTS: A Unified Multi-Task Time Series Model","created":"2024-02-29","cited_by_count":94},{"id":"2410.04803","title":"Timer-XL: Long-Context Transformers for Unified Time Series Forecasting","created":"2024-10-07","cited_by_count":87},{"id":"2505.14766","title":"This Time is Different: An Observability Perspective on Time Series Foundation Models","created":"2025-05-20","cited_by_count":68},{"id":"2402.02370","title":"AutoTimes: Autoregressive Time Series Forecasters via Large Language Models","created":"2024-02-04","cited_by_count":65},{"id":"2412.14711","title":"ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing","created":"2024-12-19","cited_by_count":54},{"id":"2409.20371","title":"Frequency Adaptive Normalization For Non-stationary Time Series Forecasting","created":"2024-09-30","cited_by_count":47},{"id":"2503.07649","title":"TS-RAG: Retrieval-Augmented Generation based Time Series Foundation Models are Stronger Zero-Shot Forecaster","created":"2025-03-06","cited_by_count":40},{"id":"2510.14510","title":"Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective","created":"2025-10-16","cited_by_count":39},{"id":"2410.24087","title":"In-Context Fine-Tuning for Time-Series Foundation Models","created":"2024-10-31","cited_by_count":35},{"id":"2404.15045","title":"Multi-Head Mixture-of-Experts","created":"2024-04-23","cited_by_count":31},{"id":"2409.02732","title":"Approximating mutual information of high-dimensional variables using learned representations","created":"2024-09-03","cited_by_count":21},{"id":"2409.12915","title":"Exploring Representations and Interventions in Time Series Foundation Models","created":"2024-09-19","cited_by_count":20},{"id":"2305.20025","title":"Mutual Information Estimation via $f$-Divergence and Data Derangements","created":"2023-05-31","cited_by_count":17},{"id":"2502.10235","title":"AdaPTS: Adapting Univariate Foundation Models to Probabilistic Multivariate Time Series Forecasting","created":"2025-02-14","cited_by_count":15},{"id":"2506.14087","title":"Multi-Scale Finetuning for Encoder-based Time Series Foundation Models","created":"2025-06-17","cited_by_count":14},{"id":"2604.09780","title":"The Myth of Expert Specialization in MoEs: Why Routing Reflects Geometry, Not Necessarily Domain Expertise","created":"2026-04-10","cited_by_count":13},{"id":"2409.11302","title":"Beyond LoRA: Exploring Efficient Fine-Tuning Techniques for Time Series Foundational Models","created":"2024-09-17","cited_by_count":10},{"id":"2510.25207","title":"Selective Learning for Deep Time Series Forecasting","created":"2025-10-29","cited_by_count":8},{"id":"2501.13074","title":"Autonomy-of-Experts Models","created":"2025-01-22","cited_by_count":7},{"id":"2510.19710","title":"SEMPO: Lightweight Foundation Models for Time Series Forecasting","created":"2025-10-22","cited_by_count":7},{"id":"2511.10971","title":"ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization","created":"2025-11-14","cited_by_count":7},{"id":"2503.16991","title":"TRACE: Time SeRies PArameter EffiCient FinE-tuning","created":"2025-03-21","cited_by_count":6},{"id":"2510.03339","title":"Pool Me Wisely: On the Effect of Pooling in Transformer-Based Models","created":"2025-10-02","cited_by_count":6},{"id":"2511.15324","title":"On the Internal Semantics of Time-Series Foundation Models","created":"2025-11-19","cited_by_count":5},{"id":"2510.16448","title":"Input Domain Aware MoE: Decoupling Routing Decisions from Task Optimization in Mixture of Experts","created":"2025-10-18","cited_by_count":3},{"id":"2603.11869","title":"On the Role of Reversible Instance Normalization","created":"2026-03-12","cited_by_count":2},{"id":"2604.00801","title":"Routing-Free Mixture-of-Experts","created":"2026-04-01","cited_by_count":2},{"id":"2510.25262","title":"IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning","created":"2025-10-29","cited_by_count":1}],"next_cursor":null}