{"list":"other","total":97,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"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":"2106.13008","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","created":"2021-06-24","cited_by_count":1676},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2310.06625","title":"iTransformer: Inverted Transformers Are Effective for Time Series Forecasting","created":"2023-10-10","cited_by_count":931},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"1905.10437","title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","created":"2019-05-24","cited_by_count":753},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632},{"id":"1907.00235","title":"Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting","created":"2019-06-29","cited_by_count":607},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"id":"2402.03885","title":"MOMENT: A Family of Open Time-series Foundation Models","created":"2024-02-06","cited_by_count":482},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2205.14415","title":"Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting","created":"2022-05-28","cited_by_count":391},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"2106.09305","title":"SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction","created":"2021-06-17","cited_by_count":338},{"id":"2304.08424","title":"Long-term Forecasting with TiDE: Time-series Dense Encoder","created":"2023-04-17","cited_by_count":332},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"1901.10738","title":"Unsupervised Scalable Representation Learning for Multivariate Time Series","created":"2019-01-30","cited_by_count":269},{"id":"2011.07231","title":"ActBERT: Learning Global-Local Video-Text Representations","created":"2020-11-14","cited_by_count":267},{"id":"2402.19072","title":"TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables","created":"2024-02-29","cited_by_count":248},{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213},{"id":"2402.02368","title":"Timer: Generative Pre-trained Transformers Are Large Time Series Models","created":"2024-02-04","cited_by_count":208},{"id":"2407.13278","title":"Deep Time Series Models: A Comprehensive Survey and Benchmark","created":"2024-07-18","cited_by_count":197},{"id":"2308.08241","title":"TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series","created":"2023-08-16","cited_by_count":169},{"id":"2406.16964","title":"Are Language Models Actually Useful for Time Series Forecasting?","created":"2024-06-22","cited_by_count":168},{"id":"1904.01949","title":"Automatic diagnosis of the 12-lead ECG using a deep neural network","created":"2019-04-02","cited_by_count":164},{"id":"2207.01186","title":"Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures","created":"2022-07-04","cited_by_count":160},{"id":"2202.01381","title":"ETSformer: Exponential Smoothing Transformers for Time-series Forecasting","created":"2022-02-03","cited_by_count":148},{"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":"2201.05078","title":"CLIP-Event: Connecting Text and Images with Event Structures","created":"2022-01-13","cited_by_count":86},{"id":"1506.00327","title":"Imaging Time-Series to Improve Classification and Imputation","created":"2015-06-01","cited_by_count":85},{"id":"2204.02968","title":"Temporal Alignment Networks for Long-term Video","created":"2022-04-06","cited_by_count":84},{"id":"2303.12799","title":"Time Series as Images: Vision Transformer for Irregularly Sampled Time Series","created":"2023-03-01","cited_by_count":79},{"id":"2502.04395","title":"Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting","created":"2025-02-06","cited_by_count":63},{"id":"2303.12311","title":"Frozen Language Model Helps ECG Zero-Shot Learning","created":"2023-03-22","cited_by_count":62},{"id":"2210.06031","title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","created":"2022-10-12","cited_by_count":59},{"id":"2402.16132","title":"LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting","created":"2024-02-25","cited_by_count":59},{"id":"2502.18482","title":"MixLLM: Dynamic Routing in Mixed Large Language Models","created":"2025-02-09","cited_by_count":59},{"id":"2302.12721","title":"LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version","created":"2023-02-24","cited_by_count":50},{"id":"2402.02713","title":"Position: What Can Large Language Models Tell Us about Time Series Analysis","created":"2024-02-05","cited_by_count":47},{"id":"2204.01018","title":"TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting","created":"2022-04-03","cited_by_count":44},{"id":"2207.10362","title":"LocVTP: Video-Text Pre-training for Temporal Localization","created":"2022-07-21","cited_by_count":44},{"id":"2106.09212","title":"Long-Short Temporal Contrastive Learning of Video Transformers","created":"2021-06-17","cited_by_count":42},{"id":"2310.20071","title":"FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space","created":"2023-10-30","cited_by_count":33},{"id":"2309.04612","title":"Self-optimizing Feature Generation via Categorical Hashing Representation and Hierarchical Reinforcement Crossing","created":"2023-09-08","cited_by_count":30},{"id":"2405.16203","title":"Evolutionary Large Language Model for Automated Feature Transformation","created":"2024-05-25","cited_by_count":29},{"id":"2402.09617","title":"LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendations","created":"2024-02-14","cited_by_count":24},{"id":"1904.08064","title":"Forecasting with time series imaging","created":"2019-04-17","cited_by_count":22},{"id":"2403.03838","title":"Feature Selection as Deep Sequential Generative Learning","created":"2024-03-06","cited_by_count":21},{"id":"2405.16879","title":"Unsupervised Generative Feature Transformation via Graph Contrastive Pre-training and Multi-objective Fine-tuning","created":"2024-05-27","cited_by_count":21},{"id":"2402.02475","title":"TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling","created":"2024-02-04","cited_by_count":20},{"id":"2405.11272","title":"Double Correction Framework for Denoising Recommendation","created":"2024-05-18","cited_by_count":19},{"id":"1704.03152","title":"Deep Multimodal Representation Learning from Temporal Data","created":"2017-04-11","cited_by_count":17},{"id":"2501.08620","title":"CT-PatchTST: Channel-Time Patch Time-Series Transformer for Long-Term Renewable Energy Forecasting","created":"2025-01-15","cited_by_count":16},{"id":"2403.04015","title":"Knockoff-Guided Feature Selection via A Single Pre-trained Reinforced Agent","created":"2024-03-06","cited_by_count":15},{"id":"2404.17157","title":"Neuro-Symbolic Embedding for Short and Effective Feature Selection via Autoregressive Generation","created":"2024-04-26","cited_by_count":14},{"id":"2502.08828","title":"A Survey on Data-Centric AI: Tabular Learning from Reinforcement Learning and Generative AI Perspective","created":"2025-02-12","cited_by_count":14},{"id":"2405.15783","title":"Multimodality Invariant Learning for Multimedia-Based New Item Recommendation","created":"2024-04-28","cited_by_count":13},{"id":"2505.15152","title":"Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature Transformation","created":"2025-05-21","cited_by_count":13},{"id":"2305.16556","title":"LANISTR: Multimodal Learning from Structured and Unstructured Data","created":"2023-05-26","cited_by_count":11},{"id":"2504.21304","title":"Unsupervised Feature Transformation via In-context Generation, Generator-critic LLM Agents, and Duet-play Teaming","created":"2025-04-30","cited_by_count":11},{"id":"2303.12370","title":"Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos","created":"2023-03-22","cited_by_count":10},{"id":"2505.15076","title":"Agentic Feature Augmentation: Unifying Selection and Generation with Teaming, Planning, and Memories","created":"2025-05-21","cited_by_count":9},{"id":"2404.01165","title":"LITE: Modeling Environmental Ecosystems with Multimodal Large Language Models","created":"2024-04-01","cited_by_count":7},{"id":"2409.08530","title":"Integration of Mamba and Transformer -- MAT for Long-Short Range Time Series Forecasting with Application to Weather Dynamics","created":"2024-09-13","cited_by_count":7},{"id":"2506.08552","title":"Efficient Post-Training Refinement of Latent Reasoning in Large Language Models","created":"2025-06-10","cited_by_count":7},{"id":"2506.09085","title":"LLM-ML Teaming: Integrated Symbolic Decoding and Gradient Search for Valid and Stable Generative Feature Transformation","created":"2025-06-10","cited_by_count":5},{"id":"2405.16083","title":"From Orthogonality to Dependency: Learning Disentangled Representation for Multi-Modal Time-Series Sensing Signals","created":"2024-05-25","cited_by_count":4},{"id":"2505.15572","title":"Bridging the Domain Gap in Equation Distillation with Reinforcement Feedback","created":"2025-05-21","cited_by_count":4},{"id":"2505.18204","title":"Brownian Bridge Augmented Surrogate Simulation and Injection Planning for Geological CO$_2$ Storage","created":"2025-05-21","cited_by_count":4},{"id":"2506.09084","title":"PageLLM: A Multi-Grained Reward Framework for Whole-Page Optimization with Large Language Models","created":"2025-06-10","cited_by_count":2}],"next_cursor":null}