{"list":"other","total":60,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337},{"id":"1709.02540","title":"The Expressive Power of Neural Networks: A View from the Width","created":"2017-09-08","cited_by_count":320},{"id":"2305.15771","title":"On the Planning Abilities of Large Language Models : A Critical Investigation","created":"2023-05-25","cited_by_count":312},{"id":"2503.07365","title":"MM-Eureka: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning","created":"2025-03-10","cited_by_count":303},{"id":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294},{"id":"1407.4443","title":"On the Complexity of Best Arm Identification in Multi-Armed Bandit Models","created":"2014-07-16","cited_by_count":286},{"id":"2402.12875","title":"Chain of Thought Empowers Transformers to Solve Inherently Serial Problems","created":"2024-02-20","cited_by_count":260},{"id":"2101.10382","title":"Curriculum Learning: A Survey","created":"2021-01-25","cited_by_count":259},{"id":"1704.03003","title":"Automated Curriculum Learning for Neural Networks","created":"2017-04-10","cited_by_count":257},{"id":"2502.06768","title":"Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions","created":"2025-02-10","cited_by_count":214},{"id":"2503.10460","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","created":"2025-03-13","cited_by_count":175},{"id":"2307.03576","title":"One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention","created":"2023-07-07","cited_by_count":170},{"id":"1810.08033","title":"Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality","created":"2018-10-18","cited_by_count":162},{"id":"2404.03683","title":"Stream of Search (SoS): Learning to Search in Language","created":"2024-04-01","cited_by_count":145},{"id":"2302.11055","title":"SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics","created":"2023-02-21","cited_by_count":143},{"id":"2402.14735","title":"How Transformers Learn Causal Structure with Gradient Descent","created":"2024-02-22","cited_by_count":118},{"id":"2310.05249","title":"In-Context Convergence of Transformers","created":"2023-10-08","cited_by_count":115},{"id":"1802.03796","title":"Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks","created":"2018-02-11","cited_by_count":114},{"id":"2304.03843","title":"Why think step by step? Reasoning emerges from the locality of experience","created":"2023-04-07","cited_by_count":103},{"id":"2407.13690","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","created":"2024-06-18","cited_by_count":95},{"id":"2303.07971","title":"A Theory of Emergent In-Context Learning as Implicit Structure Induction","created":"2023-03-14","cited_by_count":86},{"id":"2002.07400","title":"Learning Parities with Neural Networks","created":"2020-02-18","cited_by_count":78},{"id":"2301.13105","title":"Generalization on the Unseen, Logic Reasoning and Degree Curriculum","created":"2023-01-30","cited_by_count":73},{"id":"2402.08164","title":"On Limitations of the Transformer Architecture","created":"2024-02-13","cited_by_count":63},{"id":"2412.06538","title":"Understanding Factual Recall in Transformers via Associative Memories","created":"2024-12-09","cited_by_count":51},{"id":"2409.10559","title":"Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers","created":"2024-09-09","cited_by_count":50},{"id":"2410.08633","title":"Transformers Provably Solve Parity Efficiently with Chain of Thought","created":"2024-10-11","cited_by_count":50},{"id":"1910.12799","title":"Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space","created":"2019-10-28","cited_by_count":46},{"id":"2402.01258","title":"Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape","created":"2024-02-02","cited_by_count":46},{"id":"2509.15194","title":"Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation","created":"2025-09-18","cited_by_count":45},{"id":"2504.04022","title":"Rethinking Reflection in Pre-Training","created":"2025-04-05","cited_by_count":43},{"id":"2103.01210","title":"Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels","created":"2021-03-01","cited_by_count":41},{"id":"2408.10147","title":"In-Context Learning with Representations: Contextual Generalization of Trained Transformers","created":"2024-08-19","cited_by_count":38},{"id":"2503.07453","title":"Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration","created":"2025-03-10","cited_by_count":36},{"id":"2505.23683","title":"Learning Compositional Functions with Transformers from Easy-to-Hard Data","created":"2025-05-29","cited_by_count":36},{"id":"1602.05161","title":"Fast Learning Requires Good Memory: A Time-Space Lower Bound for Parity Learning","created":"2016-02-16","cited_by_count":33},{"id":"1812.03472","title":"Theory of Curriculum Learning, with Convex Loss Functions","created":"2018-12-09","cited_by_count":33},{"id":"2502.21212","title":"Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought","created":"2025-02-28","cited_by_count":32},{"id":"2502.01612","title":"Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges","created":"2025-02-03","cited_by_count":31},{"id":"2410.05459","title":"From Sparse Dependence to Sparse Attention: Unveiling How Chain-of-Thought Enhances Transformer Sample Efficiency","created":"2024-10-07","cited_by_count":29},{"id":"2108.04190","title":"On the Power of Differentiable Learning versus PAC and SQ Learning","created":"2021-08-09","cited_by_count":28},{"id":"2502.02393","title":"Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers","created":"2025-02-04","cited_by_count":28},{"id":"2106.08068","title":"An Analytical Theory of Curriculum Learning in Teacher-Student Networks","created":"2021-06-15","cited_by_count":27},{"id":"2403.10348","title":"Denoising Task Difficulty-based Curriculum for Training Diffusion Models","created":"2024-03-15","cited_by_count":27},{"id":"2502.01694","title":"Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation","created":"2025-02-02","cited_by_count":25},{"id":"2311.13110","title":"White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?","created":"2023-11-22","cited_by_count":23},{"id":"2306.16921","title":"Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs","created":"2023-06-29","cited_by_count":22},{"id":"2301.13833","title":"A Mathematical Model for Curriculum Learning for Parities","created":"2023-01-31","cited_by_count":19},{"id":"2506.18110","title":"RL for Reasoning by Adaptively Revealing Rationales","created":"2025-06-22","cited_by_count":16},{"id":"2410.05464","title":"Progressive distillation induces an implicit curriculum","created":"2024-10-07","cited_by_count":15},{"id":"2410.02167","title":"Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis","created":"2024-10-03","cited_by_count":14},{"id":"2302.04658","title":"The Sample Complexity of Approximate Rejection Sampling with Applications to Smoothed Online Learning","created":"2023-02-09","cited_by_count":13},{"id":"2502.08991","title":"Task Generalization With AutoRegressive Compositional Structure: Can Learning From $D$ Tasks Generalize to $D^{T}$ Tasks?","created":"2025-02-13","cited_by_count":11},{"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},{"id":"2406.01589","title":"Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks","created":"2024-06-03","cited_by_count":9},{"id":"2508.08222","title":"Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent","created":"2025-08-11","cited_by_count":7},{"id":"2501.12997","title":"Ehrenfeucht-Haussler Rank and Chain of Thought","created":"2025-01-22","cited_by_count":6},{"id":"2506.10647","title":"Data Shifts Hurt CoT: A Theoretical Study","created":"2025-06-12","cited_by_count":2}],"next_cursor":null}