{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"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":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"2310.10688","title":"A decoder-only foundation model for time-series forecasting","created":"2023-10-14","cited_by_count":692},{"id":"2402.02592","title":"Unified Training of Universal Time Series Forecasting Transformers","created":"2024-02-04","cited_by_count":614},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"2406.06484","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","created":"2024-06-10","cited_by_count":396},{"id":"2203.14343","title":"Diagonal State Spaces are as Effective as Structured State Spaces","created":"2022-03-27","cited_by_count":350},{"id":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"2207.02098","title":"Neural Networks and the Chomsky Hierarchy","created":"2022-07-05","cited_by_count":217},{"id":"2410.10393","title":"GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation","created":"2024-10-14","cited_by_count":212},{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191},{"id":"2404.08819","title":"The Illusion of State in State-Space Models","created":"2024-04-12","cited_by_count":187},{"id":"2406.07522","title":"Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling","created":"2024-06-11","cited_by_count":174},{"id":"2405.16712","title":"Zamba: A Compact 7B SSM Hybrid Model","created":"2024-05-26","cited_by_count":124},{"id":"2408.15237","title":"The Mamba in the Llama: Distilling and Accelerating Hybrid Models","created":"2024-08-27","cited_by_count":122},{"id":"2505.23719","title":"TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning","created":"2025-05-29","cited_by_count":120},{"id":"1805.04908","title":"On the Practical Computational Power of Finite Precision RNNs for Language Recognition","created":"2018-05-13","cited_by_count":117},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104},{"id":"2411.12537","title":"Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues","created":"2024-11-19","cited_by_count":101},{"id":"2306.00946","title":"Exposing Attention Glitches with Flip-Flop Language Modeling","created":"2023-06-01","cited_by_count":75},{"id":"2502.10297","title":"DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products","created":"2025-02-14","cited_by_count":75},{"id":"2408.10189","title":"Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models","created":"2024-08-19","cited_by_count":67},{"id":"1906.01615","title":"Sequential Neural Networks as Automata","created":"2019-06-04","cited_by_count":54},{"id":"2405.06640","title":"Linearizing Large Language Models","created":"2024-05-10","cited_by_count":51},{"id":"2407.07874","title":"Toto: Time Series Optimized Transformer for Observability","created":"2024-07-10","cited_by_count":48},{"id":"2502.14458","title":"Llamba: Scaling Distilled Recurrent Models for Efficient Language Processing","created":"2025-02-20","cited_by_count":35},{"id":"2503.01496","title":"Liger: Linearizing Large Language Models to Gated Recurrent Structures","created":"2025-03-03","cited_by_count":33},{"id":"2512.15489","title":"Nemotron-Math: Efficient Long-Context Distillation of Mathematical Reasoning from Multi-Mode Supervision","created":"2025-12-17","cited_by_count":26},{"id":"2505.03005","title":"RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale","created":"2025-05-05","cited_by_count":24},{"id":"2503.13427","title":"xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference","created":"2025-03-17","cited_by_count":18},{"id":"2603.03612","title":"Why Are Linear RNNs More Parallelizable?","created":"2026-03-04","cited_by_count":8},{"id":"2602.14814","title":"Learning State-Tracking from Code Using Linear RNNs","created":"2026-02-16","cited_by_count":6},{"id":"2510.05364","title":"The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures","created":"2025-10-06","cited_by_count":4},{"id":"2510.02228","title":"xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity","created":"2025-10-02","cited_by_count":3},{"id":"2603.15590","title":"Effective Distillation to Hybrid xLSTM Architectures","created":"2026-03-16","cited_by_count":3}],"next_cursor":null}