{"list":"other","total":63,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"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":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"1911.05507","title":"Compressive Transformers for Long-Range Sequence Modelling","created":"2019-11-13","cited_by_count":726},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"1905.06922","title":"On Variational Bounds of Mutual Information","created":"2019-05-16","cited_by_count":559},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2407.04620","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","created":"2024-07-05","cited_by_count":355},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333},{"id":"2405.04517","title":"xLSTM: Extended Long Short-Term Memory","created":"2024-05-07","cited_by_count":327},{"id":"1907.13625","title":"On Mutual Information Maximization for Representation Learning","created":"2019-07-31","cited_by_count":316},{"id":"2309.17452","title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","created":"2023-09-29","cited_by_count":282},{"id":"2307.02486","title":"LongNet: Scaling Transformers to 1,000,000,000 Tokens","created":"2023-07-05","cited_by_count":204},{"id":"2304.04370","title":"OpenAGI: When LLM Meets Domain Experts","created":"2023-04-10","cited_by_count":197},{"id":"1905.07799","title":"Adaptive Attention Span in Transformers","created":"2019-05-19","cited_by_count":149},{"id":"2402.01092","title":"A Dynamical Model of Neural Scaling Laws","created":"2024-02-02","cited_by_count":111},{"id":"1909.02108","title":"Quantum Natural Gradient","created":"2019-09-04","cited_by_count":106},{"id":"2107.02192","title":"Long-Short Transformer: Efficient Transformers for Language and Vision","created":"2021-07-05","cited_by_count":102},{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79},{"id":"2004.14941","title":"The Information Bottleneck Problem and Its Applications in Machine Learning","created":"2020-04-30","cited_by_count":66},{"id":"2401.04658","title":"Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models","created":"2024-01-09","cited_by_count":57},{"id":"1411.2003","title":"Efficient Estimation of Mutual Information for Strongly Dependent Variables","created":"2014-11-07","cited_by_count":46},{"id":"1606.06737","title":"Criticality in Formal Languages and Statistical Physics","created":"2016-06-21","cited_by_count":35},{"id":"2406.00132","title":"QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation","created":"2024-05-31","cited_by_count":23},{"id":"2312.00111","title":"Multimodal Foundation Models for Material Property Prediction and Discovery","created":"2023-11-30","cited_by_count":19},{"id":"2101.07243","title":"Gauge Invariant and Anyonic Symmetric Transformer and RNN Quantum States for Quantum Lattice Models","created":"2021-01-18","cited_by_count":18},{"id":"1905.04271","title":"Mutual Information Scaling and Expressive Power of Sequence Models","created":"2019-05-10","cited_by_count":14},{"id":"2206.12363","title":"From Tensor Network Quantum States to Tensorial Recurrent Neural Networks","created":"2022-06-24","cited_by_count":14},{"id":"2103.06872","title":"Tensor networks and efficient descriptions of classical data","created":"2021-03-11","cited_by_count":13},{"id":"2212.06835","title":"Simulating 2+1D Lattice Quantum Electrodynamics at Finite Density with Neural Flow Wavefunctions","created":"2022-12-14","cited_by_count":10},{"id":"2108.02200","title":"Spacetime Neural Network for High Dimensional Quantum Dynamics","created":"2021-08-04","cited_by_count":9},{"id":"2407.20228","title":"FlexAttention for Efficient High-Resolution Vision-Language Models","created":"2024-07-29","cited_by_count":9},{"id":"2304.01996","title":"ANTN: Bridging Autoregressive Neural Networks and Tensor Networks for Quantum Many-Body Simulation","created":"2023-04-04","cited_by_count":8},{"id":"2406.06576","title":"OccamLLM: Fast and Exact Language Model Arithmetic in a Single Step","created":"2024-06-04","cited_by_count":7}],"next_cursor":null}