{"total":129,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715,"area":null},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419,"area":null},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337,"area":null},{"id":"2306.04637","title":"Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection","created":"2023-06-07","cited_by_count":298,"area":null},{"id":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294,"area":"lr"},{"id":"2402.12875","title":"Chain of Thought Empowers Transformers to Solve Inherently Serial Problems","created":"2024-02-20","cited_by_count":260,"area":"lr"},{"id":"2301.13196","title":"Looped Transformers as Programmable Computers","created":"2023-01-30","cited_by_count":237,"area":null},{"id":"2207.02098","title":"Neural Networks and the Chomsky Hierarchy","created":"2022-07-05","cited_by_count":217,"area":null},{"id":"2207.00729","title":"The Parallelism Tradeoff: Limitations of Log-Precision Transformers","created":"2022-07-02","cited_by_count":193,"area":null},{"id":"2106.16213","title":"Saturated Transformers are Constant-Depth Threshold Circuits","created":"2021-06-30","cited_by_count":139,"area":null},{"id":"2306.02896","title":"Representational Strengths and Limitations of Transformers","created":"2023-06-05","cited_by_count":133,"area":null},{"id":"2311.00208","title":"What Formal Languages Can Transformers Express? A Survey","created":"2023-11-01","cited_by_count":124,"area":null},{"id":"2105.11115","title":"Self-Attention Networks Can Process Bounded Hierarchical Languages","created":"2021-05-24","cited_by_count":105,"area":null},{"id":"2107.13163","title":"Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers","created":"2021-07-28","cited_by_count":102,"area":null},{"id":"2310.17513","title":"The Expressive Power of Low-Rank Adaptation","created":"2023-10-26","cited_by_count":102,"area":"diffusion"},{"id":"2204.06618","title":"Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity","created":"2022-04-13","cited_by_count":93,"area":null},{"id":"2310.08566","title":"Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining","created":"2023-10-12","cited_by_count":83,"area":"offlinerl"},{"id":"2507.06203","title":"A Survey on Latent Reasoning","created":"2025-07-08","cited_by_count":81,"area":"lr"},{"id":"2210.02671","title":"A Logic for Expressing Log-Precision Transformers","created":"2022-10-06","cited_by_count":67,"area":"lr"},{"id":"2410.08292","title":"Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?","created":"2024-10-10","cited_by_count":65,"area":null},{"id":"2106.04690","title":"Handcrafted Backdoors in Deep Neural Networks","created":"2021-06-08","cited_by_count":63,"area":null},{"id":"2310.03016","title":"Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions","created":"2023-10-04","cited_by_count":63,"area":null},{"id":"2210.01753","title":"HYPRO: A Hybridly Normalized Probabilistic Model for Long-Horizon Prediction of Event Sequences","created":"2022-10-04","cited_by_count":57,"area":null},{"id":"2209.15059","title":"Provably expressive temporal graph networks","created":"2022-09-29","cited_by_count":56,"area":null},{"id":"2205.14210","title":"MIP-GNN: A Data-Driven Framework for Guiding Combinatorial Solvers","created":"2022-05-27","cited_by_count":49,"area":null},{"id":"2106.03764","title":"On the Expressive Power of Self-Attention Matrices","created":"2021-06-07","cited_by_count":47,"area":null},{"id":"2301.04589","title":"Memory Augmented Large Language Models are Computationally Universal","created":"2023-01-10","cited_by_count":47,"area":null},{"id":"2405.17394","title":"The Expressive Capacity of State Space Models: A Formal Language Perspective","created":"2024-05-27","cited_by_count":46,"area":null},{"id":"2304.13276","title":"The Closeness of In-Context Learning and Weight Shifting for Softmax Regression","created":"2023-04-26","cited_by_count":41,"area":null},{"id":"2307.11353","title":"What can a Single Attention Layer Learn? A Study Through the Random Features Lens","created":"2023-07-21","cited_by_count":40,"area":null},{"id":"2103.04886","title":"Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks","created":"2021-03-08","cited_by_count":39,"area":null},{"id":"2106.05268","title":"Vector Symbolic Architectures as a Computing Framework for Emerging Hardware","created":"2021-06-09","cited_by_count":35,"area":null},{"id":"2305.18699","title":"Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input","created":"2023-05-30","cited_by_count":32,"area":null},{"id":"2406.02128","title":"Iteration Head: A Mechanistic Study of Chain-of-Thought","created":"2024-06-04","cited_by_count":31,"area":"lr"},{"id":"2406.09347","title":"Separations in the Representational Capabilities of Transformers and Recurrent Architectures","created":"2024-06-13","cited_by_count":29,"area":null},{"id":"2502.02393","title":"Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers","created":"2025-02-04","cited_by_count":28,"area":"lr"},{"id":"2101.12322","title":"Position, Padding and Predictions: A Deeper Look at Position Information in CNNs","created":"2021-01-28","cited_by_count":26,"area":null},{"id":"2211.01233","title":"Attention-based Neural Cellular Automata","created":"2022-11-02","cited_by_count":26,"area":null},{"id":"2407.03310","title":"Universal Length Generalization with Turing Programs","created":"2024-07-03","cited_by_count":25,"area":null},{"id":"2410.13857","title":"How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs","created":"2024-10-17","cited_by_count":24,"area":"lr"},{"id":"2406.06893","title":"Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot","created":"2024-06-11","cited_by_count":22,"area":null},{"id":"2402.01929","title":"Sample, estimate, aggregate: A recipe for causal discovery foundation models","created":"2024-02-02","cited_by_count":21,"area":null},{"id":"2409.15318","title":"On the Complexity of Neural Computation in Superposition","created":"2024-09-05","cited_by_count":21,"area":"mechinterp"},{"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,"area":"ssm"},{"id":"2305.17026","title":"How Powerful are Decoder-Only Transformer Neural Models?","created":"2023-05-26","cited_by_count":20,"area":null},{"id":"2402.13934","title":"Do Efficient Transformers Really Save Computation?","created":"2024-02-21","cited_by_count":20,"area":null},{"id":"2305.18869","title":"Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning","created":"2023-05-30","cited_by_count":19,"area":"lr"},{"id":"2306.13945","title":"Large Sequence Models for Sequential Decision-Making: A Survey","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2405.16674","title":"Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory","created":"2024-05-26","cited_by_count":19,"area":null},{"id":"2410.09375","title":"Looped ReLU MLPs May Be All You Need as Practical Programmable Computers","created":"2024-10-12","cited_by_count":19,"area":null},{"id":"2111.01353","title":"Can Vision Transformers Perform Convolution?","created":"2021-11-02","cited_by_count":18,"area":null},{"id":"2305.14699","title":"Can Transformers Learn to Solve Problems Recursively?","created":"2023-05-24","cited_by_count":17,"area":null},{"id":"2307.01189","title":"Trainable Transformer in Transformer","created":"2023-07-03","cited_by_count":17,"area":null},{"id":"2303.14310","title":"GPT is becoming a Turing machine: Here are some ways to program it","created":"2023-03-25","cited_by_count":16,"area":null},{"id":"2410.07432","title":"Can Transformers Reason Logically? A Study in SAT Solving","created":"2024-10-09","cited_by_count":16,"area":"lr"},{"id":"2110.08323","title":"On Learning the Transformer Kernel","created":"2021-10-15","cited_by_count":15,"area":null},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2406.08787","title":"A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices","created":"2024-06-13","cited_by_count":15,"area":null},{"id":"2410.03170","title":"Autoregressive Large Language Models are Computationally Universal","created":"2024-10-04","cited_by_count":15,"area":null},{"id":"2412.09925","title":"Simulating Hard Attention Using Soft Attention","created":"2024-12-13","cited_by_count":15,"area":null},{"id":"2505.23623","title":"Characterizing the Expressivity of Fixed-Precision Transformer Language Models","created":"2025-05-29","cited_by_count":14,"area":null},{"id":"2404.04452","title":"Vision transformers in domain adaptation and domain generalization: a study of robustness","created":"2024-04-05","cited_by_count":11,"area":null},{"id":"2410.21698","title":"On the Role of Depth and Looping for In-Context Learning with Task Diversity","created":"2024-10-29","cited_by_count":11,"area":null},{"id":"2309.11197","title":"The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute","created":"2023-09-20","cited_by_count":10,"area":null},{"id":"2406.04089","title":"On Limitation of Transformer for Learning HMMs","created":"2024-06-06","cited_by_count":10,"area":null},{"id":"2411.01992","title":"Ask, and it shall be given: On the Turing completeness of prompting","created":"2024-11-04","cited_by_count":10,"area":null},{"id":"2501.04299","title":"Circuit Complexity Bounds for Visual Autoregressive Model","created":"2025-01-08","cited_by_count":10,"area":null},{"id":"2106.02253","title":"X-volution: On the unification of convolution and self-attention","created":"2021-06-04","cited_by_count":9,"area":null},{"id":"2301.10497","title":"E(n)-equivariant Graph Neural Cellular Automata","created":"2023-01-25","cited_by_count":9,"area":null},{"id":"2309.14691","title":"On the Computational Complexity and Formal Hierarchy of Second Order Recurrent Neural Networks","created":"2023-09-26","cited_by_count":8,"area":null},{"id":"2404.08710","title":"Do Large Language Models Learn Human-Like Strategic Preferences?","created":"2024-04-11","cited_by_count":8,"area":null},{"id":"2409.12182","title":"LifeGPT: Topology-Agnostic Generative Pretrained Transformer Model for Cellular Automata","created":"2024-09-03","cited_by_count":8,"area":null},{"id":"2505.21024","title":"Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2508.08435","title":"Fast weight programming and linear transformers: from machine learning to neurobiology","created":"2025-08-11","cited_by_count":8,"area":null},{"id":"2112.09174","title":"Learning Bounded Context-Free-Grammar via LSTM and the Transformer:Difference and Explanations","created":"2021-12-16","cited_by_count":7,"area":null},{"id":"2510.13903","title":"Benefits and Limitations of Communication in Multi-Agent Reasoning","created":"2025-10-14","cited_by_count":7,"area":"lr"},{"id":"2605.20670","title":"LT2: Linear-Time Looped Transformers","created":"2026-05-20","cited_by_count":7,"area":null},{"id":"2408.12065","title":"Transformers As Approximations of Solomonoff Induction","created":"2024-08-22","cited_by_count":6,"area":null},{"id":"2505.21785","title":"Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2506.05200","title":"Transformers Meet In-Context Learning: A Universal Approximation Theory","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2506.15690","title":"LLM Web Dynamics: Tracing Model Collapse in a Network of LLMs","created":"2025-05-26","cited_by_count":6,"area":"synth"},{"id":"2410.10101","title":"Learning Linear Attention in Polynomial Time","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2504.20213","title":"Can Large Language Models Learn Formal Logic? A Data-Driven Training and Evaluation Framework","created":"2025-04-28","cited_by_count":5,"area":"lr"},{"id":"2106.14251","title":"Pairing Conceptual Modeling with Machine Learning","created":"2021-06-27","cited_by_count":3,"area":null},{"id":"2210.06741","title":"Why self-attention is Natural for Sequence-to-Sequence Problems? A Perspective from Symmetries","created":"2022-10-13","cited_by_count":3,"area":null},{"id":"2302.01921","title":"Transformers in Action Recognition: A Review on Temporal Modeling","created":"2022-12-29","cited_by_count":3,"area":null},{"id":"2409.12446","title":"Neural Networks Generalize on Low Complexity Data","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2501.15857","title":"Are Transformers Able to Reason by Connecting Separated Knowledge in Training Data?","created":"2025-01-27","cited_by_count":3,"area":null},{"id":"2509.20615","title":"Latent Twins","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2511.07104","title":"A Theoretical Analysis of Detecting Large Model-Generated Time Series","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2207.06652","title":"Everyone's Preference Changes Differently: Weighted Multi-Interest Retrieval Model","created":"2022-07-14","cited_by_count":2,"area":null},{"id":"2309.00857","title":"Evaluating Transformer's Ability to Learn Mildly Context-Sensitive Languages","created":"2023-09-02","cited_by_count":2,"area":null},{"id":"2502.01432","title":"Emergent Stack Representations in Modeling Counter Languages Using Transformers","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2511.08028","title":"Generalizable Insights for Graph Transformers in Theory and Practice","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2602.05120","title":"Certifiable Boolean Reasoning Is Universal","created":"2026-02-04","cited_by_count":2,"area":"lr"},{"id":"2603.24780","title":"Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2605.10878","title":"Neural Weight Norm = Kolmogorov Complexity","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2606.04678","title":"Test-Time Compute Scaling for ASR with Depth-Conditioned Looped Transformers","created":"2026-06-03","cited_by_count":2,"area":"lr"},{"id":"2103.05497","title":"Symbolic integration by integrating learning models with different strengths and weaknesses","created":"2021-03-09","cited_by_count":1,"area":null}],"next_cursor":"100"}