{"list":"other","total":86,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"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":"2106.13008","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","created":"2021-06-24","cited_by_count":1676},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210},{"id":"1709.04875","title":"Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting","created":"2017-09-14","cited_by_count":1136},{"id":"2210.02186","title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis","created":"2022-10-05","cited_by_count":1058},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"1704.04110","title":"DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks","created":"2017-04-13","cited_by_count":1013},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"2310.06625","title":"iTransformer: Inverted Transformers Are Effective for Time Series Forecasting","created":"2023-10-10","cited_by_count":931},{"id":"1703.07015","title":"Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks","created":"2017-03-21","cited_by_count":879},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1906.00121","title":"Graph WaveNet for Deep Spatial-Temporal Graph Modeling","created":"2019-05-31","cited_by_count":829},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"1905.10437","title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","created":"2019-05-24","cited_by_count":753},{"id":"2005.11650","title":"Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks","created":"2020-05-24","cited_by_count":566},{"id":"2007.02842","title":"Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting","created":"2020-07-06","cited_by_count":530},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1911.08415","title":"GMAN: A Graph Multi-Attention Network for Traffic Prediction","created":"2019-11-11","cited_by_count":434},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"2405.14616","title":"TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting","created":"2024-05-23","cited_by_count":346},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328},{"id":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265},{"id":"2111.12594","title":"Conditional Object-Centric Learning from Video","created":"2021-11-24","cited_by_count":248},{"id":"2403.09338","title":"LocalMamba: Visual State Space Model with Windowed Selective Scan","created":"2024-03-14","cited_by_count":236},{"id":"2012.05208","title":"On the Binding Problem in Artificial Neural Networks","created":"2020-12-09","cited_by_count":233},{"id":"1911.12247","title":"Contrastive Learning of Structured World Models","created":"2019-11-27","cited_by_count":209},{"id":"1507.06228","title":"Training Very Deep Networks","created":"2015-07-22","cited_by_count":173},{"id":"1507.08750","title":"Action-Conditional Video Prediction using Deep Networks in Atari Games","created":"2015-07-31","cited_by_count":172},{"id":"2104.14917","title":"Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution","created":"2021-04-30","cited_by_count":157},{"id":"1509.06113","title":"Deep Spatial Autoencoders for Visuomotor Learning","created":"2015-09-21","cited_by_count":153},{"id":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147},{"id":"2202.09481","title":"TransDreamer: Reinforcement Learning with Transformer World Models","created":"2022-02-19","cited_by_count":143},{"id":"1705.10915","title":"Unsupervised Learning of Disentangled Representations from Video","created":"2017-05-31","cited_by_count":139},{"id":"2303.07109","title":"Transformer-based World Models Are Happy With 100k Interactions","created":"2023-03-13","cited_by_count":139},{"id":"1708.03498","title":"Neural Expectation Maximization","created":"2017-08-11","cited_by_count":123},{"id":"1901.07017","title":"Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs","created":"2019-01-21","cited_by_count":117},{"id":"2403.11144","title":"Is Mamba Effective for Time Series Forecasting?","created":"2024-03-17","cited_by_count":114},{"id":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106},{"id":"2303.14526","title":"Selective Structured State-Spaces for Long-Form Video Understanding","created":"2023-03-25","cited_by_count":105},{"id":"1706.01433","title":"Visual Interaction Networks","created":"2017-06-05","cited_by_count":95},{"id":"1612.08810","title":"The Predictron: End-To-End Learning and Planning","created":"2016-12-28","cited_by_count":93},{"id":"2403.11423","title":"VmambaIR: Visual State Space Model for Image Restoration","created":"2024-03-18","cited_by_count":90},{"id":"2211.14701","title":"Spatio-Temporal Meta-Graph Learning for Traffic Forecasting","created":"2022-11-27","cited_by_count":88},{"id":"2311.18257","title":"Diffusion Models Without Attention","created":"2023-11-30","cited_by_count":75},{"id":"2010.02054","title":"Improving Generative Imagination in Object-Centric World Models","created":"2020-10-05","cited_by_count":71},{"id":"1704.02254","title":"Recurrent Environment Simulators","created":"2017-04-07","cited_by_count":68},{"id":"2403.02148","title":"MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection","created":"2024-03-04","cited_by_count":60},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59},{"id":"1511.09249","title":"On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models","created":"2015-11-30","cited_by_count":55},{"id":"1804.11188","title":"Can recurrent neural networks warp time?","created":"2018-03-23","cited_by_count":55},{"id":"1605.07127","title":"Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks","created":"2016-05-23","cited_by_count":49},{"id":"2006.16225","title":"Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems","created":"2020-06-29","cited_by_count":48},{"id":"2402.03170","title":"Is Mamba Capable of In-Context Learning?","created":"2024-02-05","cited_by_count":45},{"id":"2402.05608","title":"Scalable Diffusion Models with State Space Backbone","created":"2024-02-08","cited_by_count":45},{"id":"1912.12773","title":"Learning Predictive Models From Observation and Interaction","created":"2019-12-30","cited_by_count":41},{"id":"2403.04253","title":"Mastering Memory Tasks with World Models","created":"2024-03-07","cited_by_count":38},{"id":"2403.17839","title":"ReMamber: Referring Image Segmentation with Mamba Twister","created":"2024-03-26","cited_by_count":38},{"id":"2111.07117","title":"Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views","created":"2021-11-13","cited_by_count":37},{"id":"1709.09480","title":"A Benchmark Environment Motivated by Industrial Control Problems","created":"2017-09-27","cited_by_count":31},{"id":"2212.00768","title":"Simplifying and Understanding State Space Models with Diagonal Linear RNNs","created":"2022-12-01","cited_by_count":23},{"id":"2309.03641","title":"Spiking Structured State Space Model for Monaural Speech Enhancement","created":"2023-09-07","cited_by_count":23},{"id":"2403.00818","title":"DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models","created":"2024-02-26","cited_by_count":22},{"id":"2403.05795","title":"ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes","created":"2024-03-09","cited_by_count":22},{"id":"2403.02600","title":"TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts","created":"2024-03-05","cited_by_count":18},{"id":"2406.12272","title":"Slot State Space Models","created":"2024-06-18","cited_by_count":17},{"id":"2208.03374","title":"Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter","created":"2022-08-05","cited_by_count":13},{"id":"2403.10935","title":"Understanding Robustness of Visual State Space Models for Image Classification","created":"2024-03-16","cited_by_count":12},{"id":"1602.02523","title":"Data-Efficient Reinforcement Learning in Continuous-State POMDPs","created":"2016-02-08","cited_by_count":2}],"next_cursor":null}