{"total":106,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459,"area":"lr"},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320,"area":null},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637,"area":null},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167,"area":null},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886,"area":"lr"},{"id":"2102.09544","title":"Combinatorial optimization and reasoning with graph neural networks","created":"2021-02-18","cited_by_count":268,"area":null},{"id":"2101.10382","title":"Curriculum Learning: A Survey","created":"2021-01-25","cited_by_count":259,"area":null},{"id":"2307.03381","title":"Teaching Arithmetic to Small Transformers","created":"2023-07-07","cited_by_count":123,"area":null},{"id":"2205.15659","title":"The CLRS Algorithmic Reasoning Benchmark","created":"2022-05-31","cited_by_count":106,"area":null},{"id":"2504.05520","title":"Efficient Reinforcement Finetuning via Adaptive Curriculum Learning","created":"2025-04-07","cited_by_count":93,"area":"lr"},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"area":null},{"id":"2301.13105","title":"Generalization on the Unseen, Logic Reasoning and Degree Curriculum","created":"2023-01-30","cited_by_count":73,"area":null},{"id":"2405.18512","title":"Understanding Transformer Reasoning Capabilities via Graph Algorithms","created":"2024-05-28","cited_by_count":67,"area":"lr"},{"id":"2404.14662","title":"NExT: Teaching Large Language Models to Reason about Code Execution","created":"2024-04-23","cited_by_count":63,"area":"lr"},{"id":"2502.07316","title":"CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction","created":"2025-02-11","cited_by_count":55,"area":"lr"},{"id":"2210.05062","title":"Relational Attention: Generalizing Transformers for Graph-Structured Tasks","created":"2022-10-11","cited_by_count":41,"area":null},{"id":"2502.09650","title":"Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples","created":"2025-02-11","cited_by_count":37,"area":"alignment"},{"id":"2406.06467","title":"How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad","created":"2024-06-10","cited_by_count":36,"area":null},{"id":"2107.00101","title":"Latent Execution for Neural Program Synthesis","created":"2021-06-29","cited_by_count":35,"area":null},{"id":"2210.15889","title":"Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing","created":"2022-10-28","cited_by_count":35,"area":null},{"id":"2410.06209","title":"LeanAgent: Lifelong Learning for Formal Theorem Proving","created":"2024-10-08","cited_by_count":35,"area":"lr"},{"id":"2305.05383","title":"Code Execution with Pre-trained Language Models","created":"2023-05-08","cited_by_count":34,"area":null},{"id":"2109.13986","title":"Symbolic Brittleness in Sequence Models: on Systematic Generalization in Symbolic Mathematics","created":"2021-09-28","cited_by_count":27,"area":null},{"id":"2110.14056","title":"How to transfer algorithmic reasoning knowledge to learn new algorithms?","created":"2021-10-26","cited_by_count":22,"area":null},{"id":"2306.16921","title":"Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs","created":"2023-06-29","cited_by_count":22,"area":null},{"id":"2106.06080","title":"Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent","created":"2021-06-10","cited_by_count":21,"area":null},{"id":"2304.12877","title":"Proximal Curriculum for Reinforcement Learning Agents","created":"2023-04-25","cited_by_count":20,"area":null},{"id":"2301.13833","title":"A Mathematical Model for Curriculum Learning for Parities","created":"2023-01-31","cited_by_count":19,"area":null},{"id":"2110.03501","title":"Pretrained Language Models are Symbolic Mathematics Solvers too!","created":"2021-10-07","cited_by_count":17,"area":null},{"id":"2201.12032","title":"Neural Approximation of Graph Topological Features","created":"2022-01-28","cited_by_count":17,"area":null},{"id":"2306.13411","title":"Neural Algorithmic Reasoning Without Intermediate Supervision","created":"2023-06-23","cited_by_count":17,"area":null},{"id":"2307.13883","title":"ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis","created":"2023-07-26","cited_by_count":17,"area":null},{"id":"2105.09458","title":"MLBiNet: A Cross-Sentence Collective Event Detection Network","created":"2021-05-20","cited_by_count":15,"area":null},{"id":"2503.05703","title":"What I cannot execute, I do not understand: Training and Evaluating LLMs on Program Execution Traces","created":"2025-02-10","cited_by_count":12,"area":null},{"id":"2203.03771","title":"Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions","created":"2022-03-07","cited_by_count":11,"area":null},{"id":"2303.10138","title":"Generate, Transform, Answer: Question Specific Tool Synthesis for Tabular Data","created":"2023-03-17","cited_by_count":11,"area":null},{"id":"2202.08393","title":"Robust Reinforcement Learning via Genetic Curriculum","created":"2022-02-17","cited_by_count":10,"area":null},{"id":"2106.04696","title":"Curriculum Design for Teaching via Demonstrations: Theory and Applications","created":"2021-06-08","cited_by_count":9,"area":"offlinerl"},{"id":"2112.08273","title":"Programming Knowledge Tracing: A Comprehensive Dataset and A New Model","created":"2021-12-11","cited_by_count":9,"area":null},{"id":"2402.11628","title":"Discrete Neural Algorithmic Reasoning","created":"2024-02-18","cited_by_count":9,"area":null},{"id":"2301.01661","title":"RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning","created":"2023-01-04","cited_by_count":8,"area":null},{"id":"2302.02343","title":"LExecutor: Learning-Guided Execution","created":"2023-02-05","cited_by_count":7,"area":null},{"id":"2310.00796","title":"SIP: Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulation","created":"2023-10-01","cited_by_count":7,"area":null},{"id":"2204.03758","title":"Compositional Generalization and Decomposition in Neural Program Synthesis","created":"2022-04-07","cited_by_count":6,"area":null},{"id":"2306.09222","title":"Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2308.01674","title":"End-to-End Reinforcement Learning of Koopman Models for Economic Nonlinear Model Predictive Control","created":"2023-08-03","cited_by_count":6,"area":null},{"id":"2101.04921","title":"Neural Sequence-to-grid Module for Learning Symbolic Rules","created":"2021-01-13","cited_by_count":5,"area":null},{"id":"2206.04730","title":"A Neural Network Architecture for Program Understanding Inspired by Human Behaviors","created":"2022-05-10","cited_by_count":5,"area":null},{"id":"2210.00313","title":"CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family","created":"2022-10-01","cited_by_count":5,"area":null},{"id":"2407.07853","title":"Progressive Growing of Patch Size: Resource-Efficient Curriculum Learning for Dense Prediction Tasks","created":"2024-07-10","cited_by_count":5,"area":null},{"id":"2411.15212","title":"Effective Analog ICs Floorplanning with Relational Graph Neural Networks and Reinforcement Learning","created":"2024-11-20","cited_by_count":5,"area":null},{"id":"2503.22832","title":"L0-Reasoning Bench: Evaluating Procedural Correctness in Language Models via Simple Program Execution","created":"2025-03-28","cited_by_count":5,"area":"lr"},{"id":"2510.24170","title":"SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic Preconditioning","created":"2025-10-28","cited_by_count":5,"area":null},{"id":"2311.08157","title":"TransformCode: A Contrastive Learning Framework for Code Embedding via Subtree Transformation","created":"2023-11-10","cited_by_count":4,"area":null},{"id":"2407.08597","title":"Learning Program Behavioral Models from Synthesized Input-Output Pairs","created":"2024-07-11","cited_by_count":4,"area":null},{"id":"2407.11019","title":"Efficacy of Various Large Language Models in Generating Smart Contracts","created":"2024-06-28","cited_by_count":4,"area":null},{"id":"2410.08165","title":"Chain-of-Sketch: Enabling Global Visual Reasoning","created":"2024-10-10","cited_by_count":4,"area":"lr"},{"id":"2502.16763","title":"Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2505.17703","title":"Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2510.23629","title":"Chain of Execution Supervision Promotes General Reasoning in Large Language Models","created":"2025-10-24","cited_by_count":4,"area":"lr"},{"id":"2507.07498","title":"Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code","created":"2025-07-10","cited_by_count":3,"area":"lr"},{"id":"2205.10003","title":"InDistill: Information flow-preserving knowledge distillation for model compression","created":"2022-05-20","cited_by_count":2,"area":"distill"},{"id":"2208.05782","title":"Comparison and Analysis of New Curriculum Criteria for End-to-End ASR","created":"2022-08-10","cited_by_count":2,"area":null},{"id":"2212.05178","title":"State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictions","created":"2022-12-10","cited_by_count":2,"area":null},{"id":"2304.09276","title":"Towards a Neural Lambda Calculus: Neurosymbolic AI Applied to the Foundations of Functional Programming","created":"2023-04-18","cited_by_count":2,"area":null},{"id":"2506.18777","title":"Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2508.19873","title":"Beyond Shallow Heuristics: Leveraging Human Intuition for Curriculum Learning","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2510.16007","title":"Layer-Aware Influence for Online Data Valuation Estimation","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2103.00737","title":"Meta-Learning an Inference Algorithm for Probabilistic Programs","created":"2021-03-01","cited_by_count":1,"area":null},{"id":"2105.08568","title":"Fixed $\\beta$-VAE Encoding for Curious Exploration in Complex 3D Environments","created":"2021-05-18","cited_by_count":1,"area":null},{"id":"2110.09138","title":"State-Space Constraints Can Improve the Generalisation of the Differentiable Neural Computer to Input Sequences With Unseen Length","created":"2021-10-18","cited_by_count":1,"area":null},{"id":"2211.07959","title":"The Lean Data Scientist: Recent Advances towards Overcoming the Data Bottleneck","created":"2022-11-15","cited_by_count":1,"area":null},{"id":"2303.15349","title":"Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse Skills","created":"2023-03-27","cited_by_count":1,"area":"moe"},{"id":"2304.00989","title":"Neuro-Symbolic Execution of Generic Source Code","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2310.05178","title":"Optimizing Large Language Models to Expedite the Development of Smart Contracts","created":"2023-10-08","cited_by_count":1,"area":null},{"id":"2402.15393","title":"NeuralSolver: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks","created":"2024-02-23","cited_by_count":1,"area":null},{"id":"2403.04001","title":"Bidirectional Progressive Neural Networks with Episodic Return Progress for Emergent Task Sequencing and Robotic Skill Transfer","created":"2024-03-06","cited_by_count":1,"area":"deeprl"},{"id":"2406.06354","title":"On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions","created":"2024-06-10","cited_by_count":1,"area":null},{"id":"2503.01906","title":"Learning to Chain Operations by Routing Information Through a Global Workspace","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2510.22849","title":"Once Upon an Input: Reasoning via Per-Instance Program Synthesis","created":"2025-10-26","cited_by_count":1,"area":"lr"},{"id":"2601.19094","title":"FloydNet: A Learning Paradigm for Global Relational Reasoning","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2603.09951","title":"Towards a Neural Debugger for Python","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2603.26828","title":"Arithmetic OOD Failure Unfolds in Stages in Minimal GPTs","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2604.25166","title":"Training Transformers as a Universal Computer","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2007.00425","title":"Interaction-limited Inverse Reinforcement Learning","created":"2020-07-01","cited_by_count":0,"area":"offlinerl"},{"id":"2106.06762","title":"Solving Graph-based Public Good Games with Tree Search and Imitation Learning","created":"2021-06-12","cited_by_count":0,"area":"offlinerl"},{"id":"2106.08569","title":"Curriculum generation using Autoencoder based continuous optimization","created":"2021-06-16","cited_by_count":0,"area":null},{"id":"2108.09696","title":"Spatial Transformer Networks for Curriculum Learning","created":"2021-08-22","cited_by_count":0,"area":null},{"id":"2112.04630","title":"Towards Neural Functional Program Evaluation","created":"2021-12-09","cited_by_count":0,"area":null},{"id":"2211.06441","title":"Metaphors We Learn By","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2211.06929","title":"Goal-Conditioned Reinforcement Learning in the Presence of an Adversary","created":"2022-11-13","cited_by_count":0,"area":null},{"id":"2301.06216","title":"CogReact: A Reinforced Framework to Model Human Cognitive Reaction Modulated by Dynamic Intervention","created":"2023-01-15","cited_by_count":0,"area":null},{"id":"2304.08243","title":"Stochastic Code Generation","created":"2023-04-14","cited_by_count":0,"area":null},{"id":"2306.03480","title":"GSHOT: Few-shot Generative Modeling of Labeled Graphs","created":"2023-06-06","cited_by_count":0,"area":null},{"id":"2404.02450","title":"Task Agnostic Architecture for Algorithm Induction via Implicit Composition","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2409.17490","title":"MathDSL: A Domain-Specific Language for Concise Mathematical Solutions Via Program Synthesis","created":"2024-09-26","cited_by_count":0,"area":"deeprl"},{"id":"2509.25073","title":"An empirical study on the limitation of Transformers in program trace generation","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2510.15387","title":"Advancing Routing-Awareness in Analog ICs Floorplanning","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2601.12095","title":"Neural Isomorphic Fields: A Transformer-based Algebraic Numerical Embedding","created":"2026-01-17","cited_by_count":0,"area":null},{"id":"2602.09112","title":"A Small-Scale System for Autoregressive Program Synthesis Enabling Controlled Experimentation","created":"2026-02-09","cited_by_count":0,"area":null}],"next_cursor":"100"}