{"list":"other","total":94,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1912.02762","title":"Normalizing Flows for Probabilistic Modeling and Inference","created":"2019-12-05","cited_by_count":1323},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2305.11206","title":"LIMA: Less Is More for Alignment","created":"2023-05-18","cited_by_count":1100},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"1810.01367","title":"FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models","created":"2018-10-02","cited_by_count":594},{"id":"2209.12152","title":"All are Worth Words: A ViT Backbone for Diffusion Models","created":"2022-09-25","cited_by_count":502},{"id":"2410.12557","title":"One Step Diffusion via Shortcut Models","created":"2024-10-16","cited_by_count":391},{"id":"2212.14024","title":"Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP","created":"2022-12-28","cited_by_count":318},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"2002.02798","title":"How to train your neural ODE: the world of Jacobian and kinetic regularization","created":"2020-02-07","cited_by_count":228},{"id":"2303.01861","title":"Diffusion Models are Minimax Optimal Distribution Estimators","created":"2023-03-03","cited_by_count":165},{"id":"2306.02896","title":"Representational Strengths and Limitations of Transformers","created":"2023-06-05","cited_by_count":133},{"id":"2406.14852","title":"Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models","created":"2024-06-21","cited_by_count":113},{"id":"2310.10123","title":"AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion","created":"2023-10-16","cited_by_count":100},{"id":"2007.04504","title":"Learning Differential Equations that are Easy to Solve","created":"2020-07-09","cited_by_count":81},{"id":"2305.08298","title":"Symbol tuning improves in-context learning in language models","created":"2023-05-15","cited_by_count":75},{"id":"2112.07628","title":"Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time","created":"2021-12-14","cited_by_count":62},{"id":"2402.15602","title":"Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions","created":"2024-02-23","cited_by_count":47},{"id":"2305.03486","title":"Iterative $\\alpha$-(de)Blending: a Minimalist Deterministic Diffusion Model","created":"2023-05-05","cited_by_count":46},{"id":"2303.16504","title":"An Over-parameterized Exponential Regression","created":"2023-03-29","cited_by_count":45},{"id":"2405.19592","title":"Why Larger Language Models Do In-context Learning Differently?","created":"2024-05-30","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":"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":"2412.12444","title":"LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers","created":"2024-12-17","cited_by_count":37},{"id":"2312.17346","title":"STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction","created":"2023-12-28","cited_by_count":35},{"id":"2307.02419","title":"In-Context Learning for Attention Scheme: from Single Softmax Regression to Multiple Softmax Regression via a Tensor Trick","created":"2023-07-05","cited_by_count":32},{"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":"2402.13973","title":"Linear-Time Graph Neural Networks for Scalable Recommendations","created":"2024-02-21","cited_by_count":31},{"id":"2402.15017","title":"Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning","created":"2024-02-22","cited_by_count":31},{"id":"2501.06425","title":"Tensor Product Attention Is All You Need","created":"2025-01-11","cited_by_count":31},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30},{"id":"2405.16411","title":"Training Tensor Attention Efficiently: From Cubic to Almost Linear Time","created":"2024-05-26","cited_by_count":30},{"id":"2306.02295","title":"A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models","created":"2023-06-04","cited_by_count":29},{"id":"2303.00106","title":"The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning","created":"2023-02-28","cited_by_count":27},{"id":"2411.07602","title":"Circuit Complexity Bounds for RoPE-based Transformer Architecture","created":"2024-11-12","cited_by_count":26},{"id":"2406.05871","title":"OmniControlNet: Dual-stage Integration for Conditional Image Generation","created":"2024-06-09","cited_by_count":24},{"id":"2310.16305","title":"Dolfin: Diffusion Layout Transformers without Autoencoder","created":"2023-10-25","cited_by_count":23},{"id":"2412.15579","title":"Score-based Generative Diffusion Models for Social Recommendations","created":"2024-12-20","cited_by_count":23},{"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":"2411.16525","title":"Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency","created":"2024-11-25","cited_by_count":22},{"id":"2411.17522","title":"On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality","created":"2024-11-26","cited_by_count":22},{"id":"2412.06148","title":"The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity","created":"2024-12-09","cited_by_count":21},{"id":"2410.11261","title":"Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix","created":"2024-10-15","cited_by_count":20},{"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":"2310.12408","title":"Provable Guarantees for Neural Networks via Gradient Feature Learning","created":"2023-10-19","cited_by_count":14},{"id":"2407.13621","title":"Differential Privacy Mechanisms in Neural Tangent Kernel Regression","created":"2024-07-18","cited_by_count":14},{"id":"2407.14717","title":"Provable Differentially Private Computation of the Cross-Attention Mechanism","created":"2024-07-20","cited_by_count":14},{"id":"2501.06444","title":"On the Computational Capability of Graph Neural Networks: A Circuit Complexity Bound Perspective","created":"2025-01-11","cited_by_count":14},{"id":"2201.05715","title":"Taylor-Lagrange Neural Ordinary Differential Equations: Toward Fast Training and Evaluation of Neural ODEs","created":"2022-01-14","cited_by_count":13},{"id":"2210.08361","title":"A Nearly Optimal Size Coreset Algorithm with Nearly Linear Time","created":"2022-10-15","cited_by_count":13},{"id":"2412.17316","title":"RoPE Attention Can Be Trained in Almost Linear Time","created":"2024-12-23","cited_by_count":13},{"id":"2303.07527","title":"Domain Generalization via Nuclear Norm Regularization","created":"2023-03-13","cited_by_count":12},{"id":"2410.09397","title":"On Fine-Grained I/O Complexity of Attention Backward Passes","created":"2024-10-12","cited_by_count":11},{"id":"2110.02667","title":"Attentive Walk-Aggregating Graph Neural Networks","created":"2021-10-06","cited_by_count":10},{"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":"2502.00690","title":"Dissecting Submission Limit in Desk-Rejections: A Mathematical Analysis of Fairness in AI Conference Policies","created":"2025-02-02","cited_by_count":9},{"id":"2502.06167","title":"Universal Approximation of Visual Autoregressive Transformers","created":"2025-02-10","cited_by_count":9},{"id":"2412.06061","title":"Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond","created":"2024-12-08","cited_by_count":8},{"id":"2408.06395","title":"Fast John Ellipsoid Computation with Differential Privacy Optimization","created":"2024-08-12","cited_by_count":7},{"id":"2408.14018","title":"Quantum Speedups for Approximating the John Ellipsoid","created":"2024-08-26","cited_by_count":6},{"id":"2411.16549","title":"In-Context Deep Learning via Transformer Models","created":"2024-11-25","cited_by_count":6},{"id":"2501.10688","title":"Neural Algorithmic Reasoning for Hypergraphs with Looped Transformers","created":"2025-01-18","cited_by_count":4},{"id":"2503.01314","title":"Scaling Law Phenomena Across Regression Paradigms: Multiple and Kernel Approaches","created":"2025-03-03","cited_by_count":4},{"id":"2309.15458","title":"LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints","created":"2023-09-27","cited_by_count":3},{"id":"2502.16912","title":"When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?","created":"2025-02-24","cited_by_count":3},{"id":"2402.02718","title":"Denoising Time Cycle Modeling for Recommendation","created":"2024-02-05","cited_by_count":2}],"next_cursor":null}