{"total":1454,"rows":[{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326,"area":null},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598,"area":null},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186,"area":null},{"id":"2106.13008","title":"Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting","created":"2021-06-24","cited_by_count":1676,"area":null},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620,"area":null},{"id":"2205.13504","title":"Are Transformers Effective for Time Series Forecasting?","created":"2022-05-26","cited_by_count":1424,"area":null},{"id":"2308.14508","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","created":"2023-08-28","cited_by_count":1417,"area":null},{"id":"2310.08560","title":"MemGPT: Towards LLMs as Operating Systems","created":"2023-10-12","cited_by_count":1389,"area":null},{"id":"2201.12740","title":"FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting","created":"2022-01-30","cited_by_count":1210,"area":null},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104,"area":null},{"id":"2210.02186","title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis","created":"2022-10-05","cited_by_count":1058,"area":null},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984,"area":null},{"id":"2310.06625","title":"iTransformer: Inverted Transformers Are Effective for Time Series Forecasting","created":"2023-10-10","cited_by_count":931,"area":null},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827,"area":null},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740,"area":null},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713,"area":null},{"id":"2410.10813","title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","created":"2024-10-14","cited_by_count":707,"area":null},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700,"area":null},{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632,"area":null},{"id":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590,"area":null},{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539,"area":null},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527,"area":null},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519,"area":null},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499,"area":null},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2110.02642","title":"Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy","created":"2021-10-06","cited_by_count":394,"area":null},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393,"area":null},{"id":"2205.14415","title":"Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting","created":"2022-05-28","cited_by_count":391,"area":null},{"id":"2101.05783","title":"Persistent Anti-Muslim Bias in Large Language Models","created":"2021-01-14","cited_by_count":377,"area":null},{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363,"area":null},{"id":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362,"area":null},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354,"area":null},{"id":"2306.03091","title":"RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems","created":"2023-06-05","cited_by_count":353,"area":null},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347,"area":null},{"id":"2405.14616","title":"TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting","created":"2024-05-23","cited_by_count":346,"area":null},{"id":"2104.02112","title":"Efficient Attentions for Long Document Summarization","created":"2021-04-05","cited_by_count":345,"area":null},{"id":"2106.09305","title":"SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction","created":"2021-06-17","cited_by_count":338,"area":null},{"id":"2302.14376","title":"GNOT: A General Neural Operator Transformer for Operator Learning","created":"2023-02-28","cited_by_count":336,"area":null},{"id":"2402.02366","title":"Transolver: A Fast Transformer Solver for PDEs on General Geometries","created":"2024-02-04","cited_by_count":326,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2110.00976","title":"LexGLUE: A Benchmark Dataset for Legal Language Understanding in English","created":"2021-10-03","cited_by_count":310,"area":null},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2107.07567","title":"Beyond Goldfish Memory: Long-Term Open-Domain Conversation","created":"2021-07-15","cited_by_count":267,"area":null},{"id":"2103.03841","title":"Generating Images with Sparse Representations","created":"2021-03-05","cited_by_count":266,"area":null},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265,"area":null},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2111.13587","title":"Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers","created":"2021-11-24","cited_by_count":248,"area":null},{"id":"2309.12307","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","created":"2023-09-21","cited_by_count":244,"area":null},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241,"area":null},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237,"area":null},{"id":"2102.01951","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","created":"2021-02-03","cited_by_count":230,"area":null},{"id":"2206.06522","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","created":"2022-06-13","cited_by_count":230,"area":null},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226,"area":null},{"id":"2203.08913","title":"Memorizing Transformers","created":"2022-03-16","cited_by_count":226,"area":null},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224,"area":null},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224,"area":null},{"id":"2402.14905","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","created":"2024-02-22","cited_by_count":223,"area":null},{"id":"2305.16300","title":"Landmark Attention: Random-Access Infinite Context Length for Transformers","created":"2023-05-25","cited_by_count":213,"area":null},{"id":"2103.15358","title":"Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding","created":"2021-03-29","cited_by_count":207,"area":null},{"id":"2106.09553","title":"Large-Scale Chemical Language Representations Capture Molecular Structure and Properties","created":"2021-06-17","cited_by_count":206,"area":null},{"id":"2307.02486","title":"LongNet: Scaling Transformers to 1,000,000,000 Tokens","created":"2023-07-05","cited_by_count":204,"area":null},{"id":"2208.09399","title":"Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models","created":"2022-08-19","cited_by_count":198,"area":null},{"id":"2201.08821","title":"Representing Long-Range Context for Graph Neural Networks with Global Attention","created":"2022-01-21","cited_by_count":195,"area":null},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191,"area":null},{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2101.05779","title":"Structured Prediction as Translation between Augmented Natural Languages","created":"2021-01-14","cited_by_count":183,"area":null},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2101.07448","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-01-19","cited_by_count":176,"area":null},{"id":"2310.04948","title":"TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting","created":"2023-10-08","cited_by_count":174,"area":null},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172,"area":null},{"id":"2311.06184","title":"Frequency-domain MLPs are More Effective Learners in Time Series Forecasting","created":"2023-11-10","cited_by_count":172,"area":null},{"id":"2308.00442","title":"FLatten Transformer: Vision Transformer using Focused Linear Attention","created":"2023-08-01","cited_by_count":171,"area":null},{"id":"2305.07185","title":"MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers","created":"2023-05-12","cited_by_count":170,"area":null},{"id":"2106.07476","title":"Training Graph Neural Networks with 1000 Layers","created":"2021-06-14","cited_by_count":169,"area":null},{"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,"area":null},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167,"area":null},{"id":"2206.02680","title":"Separable Self-attention for Mobile Vision Transformers","created":"2022-06-06","cited_by_count":163,"area":null},{"id":"2204.09656","title":"A Fast Post-Training Pruning Framework for Transformers","created":"2022-03-29","cited_by_count":162,"area":null},{"id":"2303.14189","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","created":"2023-03-24","cited_by_count":162,"area":null},{"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,"area":null},{"id":"2404.05892","title":"Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence","created":"2024-04-08","cited_by_count":159,"area":null},{"id":"2108.06314","title":"A Dataset for Answering Time-Sensitive Questions","created":"2021-08-13","cited_by_count":154,"area":null},{"id":"2112.05682","title":"Self-attention Does Not Need $O(n^2)$ Memory","created":"2021-12-10","cited_by_count":154,"area":null},{"id":"2202.01381","title":"ETSformer: Exponential Smoothing Transformers for Time-series Forecasting","created":"2022-02-03","cited_by_count":148,"area":null},{"id":"2106.05667","title":"GraphiT: Encoding Graph Structure in Transformers","created":"2021-06-10","cited_by_count":147,"area":null},{"id":"2205.08897","title":"FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting","created":"2022-05-18","cited_by_count":147,"area":null},{"id":"2201.12886","title":"N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting","created":"2022-01-30","cited_by_count":146,"area":null},{"id":"2303.00748","title":"Efficient and Explicit Modelling of Image Hierarchies for Image Restoration","created":"2023-03-01","cited_by_count":145,"area":null},{"id":"2310.09751","title":"UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting","created":"2023-10-15","cited_by_count":144,"area":null},{"id":"2109.12948","title":"Understanding and Overcoming the Challenges of Efficient Transformer Quantization","created":"2021-09-27","cited_by_count":141,"area":null},{"id":"2209.04881","title":"On The Computational Complexity of Self-Attention","created":"2022-09-11","cited_by_count":139,"area":null},{"id":"2209.12951","title":"Liquid Structural State-Space Models","created":"2022-09-26","cited_by_count":136,"area":null},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null}],"next_cursor":"100"}