{"total":124,"rows":[{"id":"2502.21074","title":"CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation","created":"2025-02-28","cited_by_count":225,"area":"lr"},{"id":"2404.08819","title":"The Illusion of State in State-Space Models","created":"2024-04-12","cited_by_count":187,"area":null},{"id":"2411.12537","title":"Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues","created":"2024-11-19","cited_by_count":101,"area":"ssm"},{"id":"2402.09268","title":"Transformers, parallel computation, and logarithmic depth","created":"2024-02-14","cited_by_count":79,"area":null},{"id":"2402.11917","title":"A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task","created":"2024-02-19","cited_by_count":49,"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":"2408.01367","title":"Transformers are Universal In-context Learners","created":"2024-08-02","cited_by_count":43,"area":null},{"id":"2404.04393","title":"Counting Like Transformers: Compiling Temporal Counting Logic Into Softmax Transformers","created":"2024-04-05","cited_by_count":39,"area":null},{"id":"2502.19249","title":"Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases","created":"2025-02-26","cited_by_count":37,"area":null},{"id":"2503.02854","title":"(How) Do Language Models Track State?","created":"2025-03-04","cited_by_count":34,"area":null},{"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":"2502.13063","title":"Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity","created":"2025-02-18","cited_by_count":28,"area":"inference"},{"id":"2411.07107","title":"Training Neural Networks as Recognizers of Formal Languages","created":"2024-11-11","cited_by_count":24,"area":"lr"},{"id":"2502.12317","title":"Can Language Models Learn Typologically Implausible Languages?","created":"2025-02-17","cited_by_count":23,"area":null},{"id":"2503.07932","title":"A Theory of Learning with Autoregressive Chain of Thought","created":"2025-03-11","cited_by_count":23,"area":"lr"},{"id":"2502.07827","title":"Implicit Language Models are RNNs: Balancing Parallelization and Expressivity","created":"2025-02-10","cited_by_count":22,"area":"lr"},{"id":"2410.19034","title":"Mixture of Parrots: Experts improve memorization more than reasoning","created":"2024-10-24","cited_by_count":21,"area":"moe"},{"id":"2505.18948","title":"Exact Expressive Power of Transformers with Padding","created":"2025-05-25","cited_by_count":19,"area":"lr"},{"id":"2506.12027","title":"Constant Bit-size Transformers Are Turing Complete","created":"2025-05-22","cited_by_count":19,"area":null},{"id":"2509.22284","title":"Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models","created":"2025-09-26","cited_by_count":16,"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":"2508.10111","title":"Constrained Decoding of Diffusion LLMs with Context-Free Grammars","created":"2025-08-13","cited_by_count":14,"area":null},{"id":"2507.12549","title":"The Serial Scaling Hypothesis","created":"2025-07-16","cited_by_count":13,"area":null},{"id":"2506.00744","title":"Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers","created":"2025-05-31","cited_by_count":12,"area":null},{"id":"2505.00926","title":"How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2503.14615","title":"Unique Hard Attention: A Tale of Two Sides","created":"2025-03-18","cited_by_count":10,"area":null},{"id":"2410.04271","title":"Fundamental Limitations on Subquadratic Alternatives to Transformers","created":"2024-10-05","cited_by_count":9,"area":"ssm"},{"id":"2411.17066","title":"Relations, Negations, and Numbers: Looking for Logic in Generative Text-to-Image Models","created":"2024-11-26","cited_by_count":9,"area":null},{"id":"2505.08140","title":"Lost in Transmission: When and Why LLMs Fail to Reason Globally","created":"2025-05-13","cited_by_count":9,"area":"lr"},{"id":"2505.11199","title":"The Counting Power of Transformers","created":"2025-05-16","cited_by_count":9,"area":null},{"id":"2505.15105","title":"Mechanistic evaluation of Transformers and state space models","created":"2025-05-21","cited_by_count":9,"area":"ssm"},{"id":"2507.10624","title":"Comprehension Without Competence: Architectural Limits of LLMs in Symbolic Computation and Reasoning","created":"2025-07-14","cited_by_count":9,"area":"lr"},{"id":"2511.20038","title":"Softmax Transformers are Turing-Complete","created":"2025-11-25","cited_by_count":9,"area":"lr"},{"id":"2404.02040","title":"Transformers as Transducers","created":"2024-04-02","cited_by_count":8,"area":null},{"id":"2503.16048","title":"Meta-Learning Neural Mechanisms rather than Bayesian Priors","created":"2025-03-20","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":"2506.10918","title":"Sequential-Parallel Duality in Prefix Scannable Models","created":"2025-06-12","cited_by_count":8,"area":"ssm"},{"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":"2603.03612","title":"Why Are Linear RNNs More Parallelizable?","created":"2026-03-04","cited_by_count":8,"area":null},{"id":"2503.01544","title":"Compositional Reasoning with Transformers, RNNs, and Chain of Thought","created":"2025-03-03","cited_by_count":6,"area":"lr"},{"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":"2509.25611","title":"Transformers through the lens of support-preserving maps between measures","created":"2025-09-30","cited_by_count":6,"area":null},{"id":"2510.00368","title":"The Transformer Cookbook","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2602.14814","title":"Learning State-Tracking from Code Using Linear RNNs","created":"2026-02-16","cited_by_count":6,"area":null},{"id":"2605.30233","title":"Do Language Models Track Entities Across State Changes?","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2405.18548","title":"Transformer Encoder Satisfiability: Complexity and Impact on Formal Reasoning","created":"2024-05-28","cited_by_count":5,"area":null},{"id":"2410.10101","title":"Learning Linear Attention in Polynomial Time","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2411.05943","title":"Quantifying artificial intelligence through algorithmic generalization","created":"2024-11-08","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":"2507.07544","title":"Position: We Need An Algorithmic Understanding of Generative AI","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2508.16745","title":"Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling","created":"2025-08-22","cited_by_count":4,"area":"lr"},{"id":"2510.02524","title":"Unraveling Syntax: Language Modeling and the Substructure of Grammars","created":"2025-10-02","cited_by_count":4,"area":null},{"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,"area":null},{"id":"2510.19315","title":"Transformers are Inherently Succinct","created":"2025-10-22","cited_by_count":4,"area":null},{"id":"2512.00003","title":"Efficient Turing Machine Simulation with Transformers","created":"2025-09-28","cited_by_count":4,"area":"lr"},{"id":"2603.02238","title":"Length Generalization Bounds for Transformers","created":"2026-02-13","cited_by_count":4,"area":null},{"id":"2409.12446","title":"Neural Networks Generalize on Low Complexity Data","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2503.10542","title":"Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2503.22076","title":"Concise One-Layer Transformers Can Do Function Evaluation (Sometimes)","created":"2025-03-28","cited_by_count":3,"area":null},{"id":"2505.10606","title":"Continuity and Isolation Lead to Doubts or Dilemmas in Large Language Models","created":"2025-05-15","cited_by_count":3,"area":null},{"id":"2509.09001","title":"Fast attention mechanisms: a tale of parallelism","created":"2025-09-10","cited_by_count":3,"area":null},{"id":"2602.05999","title":"On the Role of Computation in Reinforcement Learning","created":"2026-02-05","cited_by_count":3,"area":"deeprl"},{"id":"2602.11175","title":"Barriers to Discrete Reasoning with Transformers: A Survey Across Depth, Exactness, and Bandwidth","created":"2026-01-19","cited_by_count":3,"area":null},{"id":"2604.17121","title":"The Topological Trouble With Transformers","created":"2026-04-18","cited_by_count":3,"area":null},{"id":"2605.09867","title":"Continuous Latent Contexts Enable Efficient Online Learning in Transformers","created":"2026-05-11","cited_by_count":3,"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":"2506.05229","title":"Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2506.12220","title":"Two Heads Are Better than One: Simulating Large Transformers with Small Ones","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2509.10414","title":"Is In-Context Learning Learning?","created":"2025-09-12","cited_by_count":2,"area":null},{"id":"2510.04834","title":"On the Hardness of Learning Regular Expressions","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2510.27118","title":"Probability Distributions Computed by Autoregressive Transformers","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2601.19467","title":"On the Expressiveness of State Space Models via Temporal Logics","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2606.01765","title":"An Algebraic View of the Expressivity of Recurrent Language Models","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2607.22361","title":"Indexing: the Beginning and the End","created":"2026-07-24","cited_by_count":2,"area":null},{"id":"2406.05564","title":"Automata Extraction from Transformers","created":"2024-06-08","cited_by_count":1,"area":null},{"id":"2407.10949","title":"Representing Rule-based Chatbots with Transformers","created":"2024-07-15","cited_by_count":1,"area":null},{"id":"2407.18601","title":"Reorganizing attention-space geometry with expressive attention","created":"2024-07-26","cited_by_count":1,"area":null},{"id":"2408.09544","title":"No Such Thing as a General Learner: Language models and their dual optimization","created":"2024-08-18","cited_by_count":1,"area":null},{"id":"2409.06978","title":"Large Language Models and the Extended Church-Turing Thesis","created":"2024-09-11","cited_by_count":1,"area":null},{"id":"2503.04848","title":"Three tiers of computation in transformers and in brain architectures","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2506.18739","title":"On the Existence of Universal Simulators of Attention","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2507.21257","title":"CompoST: A Benchmark for Analyzing the Ability of LLMs To Compositionally Interpret Questions in a QALD Setting","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2508.04461","title":"Small transformer architectures for task switching","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2509.24024","title":"The Role of Logic and Automata in Understanding Transformers","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2602.10538","title":"Why Agentic Theorem Prover Works: A Statistical Provability Theory of Mathematical Reasoning Models","created":"2026-02-11","cited_by_count":1,"area":"lr"},{"id":"2603.05573","title":"Why Depth Matters in Parallelizable Sequence Models: A Lie Algebraic View","created":"2026-03-05","cited_by_count":1,"area":"ssm"},{"id":"2603.16689","title":"Predictive Statistics Shape Emergent World Representations of Grid Walkers","created":"2026-03-17","cited_by_count":1,"area":"wm"},{"id":"2605.26035","title":"Length Generalization with Log-Depth Recurrent Units","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2605.30523","title":"Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2605.31558","title":"Positional versus Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length Generalization","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.00376","title":"The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes Necessary","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.08768","title":"Understanding the Parameter Space Geometry of Transformers Encoding Boolean Functions","created":"2026-06-07","cited_by_count":1,"area":null},{"id":"2606.17522","title":"An expressivity analysis of hierarchical modelling in deep transformers via bounded-depth grammars","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2606.26454","title":"Data-driven Machine Learning Cannot Reach Symbolic-level Logical Reasoning -- The Limit of the Scaling Law","created":"2026-06-24","cited_by_count":1,"area":"lr"},{"id":"2404.10200","title":"TEL'M: Test and Evaluation of Language Models","created":"2024-04-16","cited_by_count":0,"area":null},{"id":"2411.08003","title":"Can adversarial attacks by large language models be attributed?","created":"2024-11-12","cited_by_count":0,"area":null},{"id":"2504.15349","title":"Exploring Compositional Generalization (in COGS/ReCOGS_pos) by Transformers using Restricted Access Sequence Processing (RASP)","created":"2025-04-21","cited_by_count":0,"area":null},{"id":"2506.19125","title":"Transformer Circuits Can Realize Clustering Algorithms","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2512.20954","title":"Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models","created":"2025-12-24","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}