{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"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":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835},{"id":"2402.17753","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","created":"2024-02-27","cited_by_count":830},{"id":"1903.07293","title":"Heterogeneous Graph Attention Network","created":"2019-03-18","cited_by_count":734},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327},{"id":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268},{"id":"2402.12875","title":"Chain of Thought Empowers Transformers to Solve Inherently Serial Problems","created":"2024-02-20","cited_by_count":260},{"id":"2006.15595","title":"Rethinking Positional Encoding in Language Pre-training","created":"2020-06-28","cited_by_count":197},{"id":"2207.00729","title":"The Parallelism Tradeoff: Limitations of Log-Precision Transformers","created":"2022-07-02","cited_by_count":193},{"id":"2203.16634","title":"Transformer Language Models without Positional Encodings Still Learn Positional Information","created":"2022-03-30","cited_by_count":150},{"id":"2106.16213","title":"Saturated Transformers are Constant-Depth Threshold Circuits","created":"2021-06-30","cited_by_count":139},{"id":"2204.05660","title":"NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks","created":"2022-04-12","cited_by_count":112},{"id":"2203.05797","title":"Long Time No See! Open-Domain Conversation with Long-Term Persona Memory","created":"2022-03-11","cited_by_count":108},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102},{"id":"2204.06618","title":"Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity","created":"2022-04-13","cited_by_count":93},{"id":"2407.07061","title":"Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence","created":"2024-07-09","cited_by_count":86},{"id":"2210.02671","title":"A Logic for Expressing Log-Precision Transformers","created":"2022-10-06","cited_by_count":67},{"id":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62},{"id":"2303.16504","title":"An Over-parameterized Exponential Regression","created":"2023-03-29","cited_by_count":45},{"id":"2310.04064","title":"How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation","created":"2023-10-06","cited_by_count":44},{"id":"2401.02777","title":"From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models","created":"2024-01-05","cited_by_count":43},{"id":"2402.04520","title":"On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis","created":"2024-02-07","cited_by_count":41},{"id":"2407.01079","title":"On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)","created":"2024-07-01","cited_by_count":40},{"id":"2407.15720","title":"Do Large Language Models Have Compositional Ability? An Investigation into Limitations and Scalability","created":"2024-07-22","cited_by_count":40},{"id":"2409.17422","title":"Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction","created":"2024-09-25","cited_by_count":39},{"id":"2404.03827","title":"Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models","created":"2024-04-04","cited_by_count":38},{"id":"2312.17346","title":"STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction","created":"2023-12-28","cited_by_count":35},{"id":"2405.05219","title":"Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers","created":"2024-05-08","cited_by_count":32},{"id":"2407.12874","title":"SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning","created":"2024-07-16","cited_by_count":32},{"id":"2405.16411","title":"Training Tensor Attention Efficiently: From Cubic to Almost Linear Time","created":"2024-05-26","cited_by_count":30},{"id":"2401.01989","title":"Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias","created":"2024-01-03","cited_by_count":28},{"id":"2402.09469","title":"Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs","created":"2024-02-12","cited_by_count":22},{"id":"2408.13233","title":"Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time","created":"2024-08-23","cited_by_count":22},{"id":"2410.11268","title":"Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent","created":"2024-10-15","cited_by_count":22},{"id":"2410.11261","title":"Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix","created":"2024-10-15","cited_by_count":20},{"id":"2211.00170","title":"What is my math transformer doing? -- Three results on interpretability and generalization","created":"2022-10-31","cited_by_count":19},{"id":"2408.12151","title":"A Tighter Complexity Analysis of SparseGPT","created":"2024-08-22","cited_by_count":19},{"id":"2410.09375","title":"Looped ReLU MLPs May Be All You Need as Practical Programmable Computers","created":"2024-10-12","cited_by_count":19},{"id":"2410.10165","title":"HSR-Enhanced Sparse Attention Acceleration","created":"2024-10-14","cited_by_count":19},{"id":"2410.23126","title":"Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codes","created":"2024-10-30","cited_by_count":19},{"id":"2402.14147","title":"Wikibench: Community-Driven Data Curation for AI Evaluation on Wikipedia","created":"2024-02-21","cited_by_count":18},{"id":"2407.14717","title":"Provable Differentially Private Computation of the Cross-Attention Mechanism","created":"2024-07-20","cited_by_count":14},{"id":"2210.08361","title":"A Nearly Optimal Size Coreset Algorithm with Nearly Linear Time","created":"2022-10-15","cited_by_count":13},{"id":"2410.09397","title":"On Fine-Grained I/O Complexity of Attention Backward Passes","created":"2024-10-12","cited_by_count":11},{"id":"2303.06210","title":"A Theoretical Analysis Of Nearest Neighbor Search On Approximate Near Neighbor Graph","created":"2023-03-10","cited_by_count":10},{"id":"2310.11291","title":"An Automatic Learning Rate Schedule Algorithm for Achieving Faster Convergence and Steeper Descent","created":"2023-10-17","cited_by_count":9},{"id":"2408.06395","title":"Fast John Ellipsoid Computation with Differential Privacy Optimization","created":"2024-08-12","cited_by_count":7},{"id":"2303.04555","title":"Streaming Kernel PCA Algorithm With Small Space","created":"2023-03-08","cited_by_count":5}],"next_cursor":null}