{"total":200,"rows":[{"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":"2102.09544","title":"Combinatorial optimization and reasoning with graph neural networks","created":"2021-02-18","cited_by_count":268,"area":null},{"id":"2103.00550","title":"A Survey on Deep Semi-supervised Learning","created":"2021-02-28","cited_by_count":251,"area":null},{"id":"2202.01344","title":"Formal Mathematics Statement Curriculum Learning","created":"2022-02-03","cited_by_count":142,"area":null},{"id":"2102.06203","title":"Proof Artifact Co-training for Theorem Proving with Language Models","created":"2021-02-11","cited_by_count":132,"area":"offlinerl"},{"id":"2502.14499","title":"MLGym: A New Framework and Benchmark for Advancing AI Research Agents","created":"2025-02-20","cited_by_count":124,"area":"agents"},{"id":"2106.04537","title":"Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks","created":"2021-06-08","cited_by_count":117,"area":null},{"id":"2205.11502","title":"On the Paradox of Learning to Reason from Data","created":"2022-05-23","cited_by_count":93,"area":"lr"},{"id":"2102.13303","title":"Graph-based Semi-supervised Learning: A Comprehensive Review","created":"2021-02-26","cited_by_count":79,"area":null},{"id":"2102.06858","title":"LTL2Action: Generalizing LTL Instructions for Multi-Task RL","created":"2021-02-13","cited_by_count":74,"area":null},{"id":"2102.03357","title":"Machine Learning for Electronic Design Automation: A Survey","created":"2021-01-10","cited_by_count":72,"area":null},{"id":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71,"area":null},{"id":"2305.19587","title":"Towards Omni-generalizable Neural Methods for Vehicle Routing Problems","created":"2023-05-31","cited_by_count":69,"area":null},{"id":"2305.15541","title":"Harnessing the Power of Large Language Models for Natural Language to First-Order Logic Translation","created":"2023-05-24","cited_by_count":59,"area":"alignment"},{"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":"2101.06223","title":"LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning","created":"2021-01-15","cited_by_count":46,"area":null},{"id":"2107.10201","title":"Learning a Large Neighborhood Search Algorithm for Mixed Integer Programs","created":"2021-07-21","cited_by_count":43,"area":null},{"id":"2302.00049","title":"Transformers Meet Directed Graphs","created":"2023-01-31","cited_by_count":40,"area":null},{"id":"2302.04451","title":"Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion","created":"2023-02-09","cited_by_count":40,"area":null},{"id":"2305.17010","title":"Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets","created":"2023-05-26","cited_by_count":40,"area":null},{"id":"2211.09961","title":"Path Independent Equilibrium Models Can Better Exploit Test-Time Computation","created":"2022-11-18","cited_by_count":38,"area":null},{"id":"2102.09756","title":"TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement Learning","created":"2021-02-19","cited_by_count":37,"area":null},{"id":"2111.14616","title":"DeepGate: Learning Neural Representations of Logic Gates","created":"2021-11-26","cited_by_count":37,"area":null},{"id":"2302.01578","title":"Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning","created":"2023-02-03","cited_by_count":37,"area":null},{"id":"2110.10942","title":"Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness","created":"2021-10-21","cited_by_count":35,"area":null},{"id":"2210.15304","title":"Explaining the Explainers in Graph Neural Networks: a Comparative Study","created":"2022-10-27","cited_by_count":35,"area":null},{"id":"2310.00836","title":"Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models","created":"2023-10-02","cited_by_count":35,"area":"lr"},{"id":"2310.13397","title":"Equivariant Deep Weight Space Alignment","created":"2023-10-20","cited_by_count":35,"area":null},{"id":"2507.15225","title":"Solving Formal Math Problems by Decomposition and Iterative Reflection","created":"2025-07-21","cited_by_count":35,"area":"lr"},{"id":"2202.05826","title":"End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking","created":"2022-02-11","cited_by_count":33,"area":"lr"},{"id":"2206.01962","title":"Formal Specifications from Natural Language","created":"2022-06-04","cited_by_count":33,"area":null},{"id":"2206.13211","title":"Modern graph neural networks do worse than classical greedy algorithms in solving combinatorial optimization problems like maximum independent set","created":"2022-06-27","cited_by_count":33,"area":null},{"id":"2207.05984","title":"Unsupervised Learning for Combinatorial Optimization with Principled Objective Relaxation","created":"2022-07-13","cited_by_count":32,"area":null},{"id":"2302.10258","title":"Neural Algorithmic Reasoning with Causal Regularisation","created":"2023-02-20","cited_by_count":31,"area":"lr"},{"id":"2106.07162","title":"Goal-Aware Neural SAT Solver","created":"2021-06-14","cited_by_count":28,"area":null},{"id":"2208.10227","title":"One Model, Any CSP: Graph Neural Networks as Fast Global Search Heuristics for Constraint Satisfaction","created":"2022-08-22","cited_by_count":27,"area":null},{"id":"2109.05536","title":"Link Scheduling using Graph Neural Networks","created":"2021-09-12","cited_by_count":26,"area":null},{"id":"2106.11072","title":"Techniques for Symbol Grounding with SATNet","created":"2021-06-16","cited_by_count":24,"area":null},{"id":"2202.08396","title":"Augment with Care: Contrastive Learning for Combinatorial Problems","created":"2022-02-17","cited_by_count":22,"area":null},{"id":"2203.04755","title":"Machine Learning Methods in Solving the Boolean Satisfiability Problem","created":"2022-03-02","cited_by_count":22,"area":null},{"id":"2301.03116","title":"Unsupervised Learning for Combinatorial Optimization Needs Meta-Learning","created":"2023-01-08","cited_by_count":20,"area":null},{"id":"2110.14053","title":"NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks","created":"2021-10-26","cited_by_count":19,"area":null},{"id":"2112.09054","title":"Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability","created":"2021-12-16","cited_by_count":18,"area":null},{"id":"2207.11542","title":"Annealed Training for Combinatorial Optimization on Graphs","created":"2022-07-23","cited_by_count":18,"area":null},{"id":"2211.03880","title":"NSNet: A General Neural Probabilistic Framework for Satisfiability Problems","created":"2022-11-07","cited_by_count":18,"area":null},{"id":"2309.16941","title":"G4SATBench: Benchmarking and Advancing SAT Solving with Graph Neural Networks","created":"2023-09-29","cited_by_count":18,"area":null},{"id":"2107.11864","title":"Neural Circuit Synthesis from Specification Patterns","created":"2021-07-25","cited_by_count":17,"area":null},{"id":"2309.16965","title":"Controlling Continuous Relaxation for Combinatorial Optimization","created":"2023-09-29","cited_by_count":16,"area":null},{"id":"2407.13917","title":"LinSATNet: The Positive Linear Satisfiability Neural Networks","created":"2024-07-18","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":"2106.03906","title":"Learning to Guide a Saturation-Based Theorem Prover","created":"2021-06-07","cited_by_count":15,"area":null},{"id":"2211.03074","title":"A Survey on Influence Maximization: From an ML-Based Combinatorial Optimization","created":"2022-11-06","cited_by_count":15,"area":null},{"id":"2402.10705","title":"AutoSAT: Automatically Optimize SAT Solvers via Large Language Models","created":"2024-02-16","cited_by_count":15,"area":null},{"id":"2209.00953","title":"SATformer: Transformer-Based UNSAT Core Learning","created":"2022-09-02","cited_by_count":14,"area":null},{"id":"2302.02104","title":"HardSATGEN: Understanding the Difficulty of Hard SAT Formula Generation and A Strong Structure-Hardness-Aware Baseline","created":"2023-02-04","cited_by_count":12,"area":null},{"id":"2307.04347","title":"Injecting Logical Constraints into Neural Networks via Straight-Through Estimators","created":"2023-07-10","cited_by_count":12,"area":null},{"id":"2309.12253","title":"SALSA-CLRS: A Sparse and Scalable Benchmark for Algorithmic Reasoning","created":"2023-09-21","cited_by_count":12,"area":null},{"id":"2310.14161","title":"Promoting Generalization for Exact Solvers via Adversarial Instance Augmentation","created":"2023-10-22","cited_by_count":12,"area":null},{"id":"2205.13745","title":"DeepSAT: An EDA-Driven Learning Framework for SAT","created":"2022-05-27","cited_by_count":11,"area":null},{"id":"2210.11633","title":"Graphically Structured Diffusion Models","created":"2022-10-20","cited_by_count":11,"area":"diffusion"},{"id":"2310.00526","title":"Are Graph Neural Networks Optimal Approximation Algorithms?","created":"2023-10-01","cited_by_count":11,"area":null},{"id":"2201.06216","title":"Learning to Reformulate for Linear Programming","created":"2022-01-17","cited_by_count":10,"area":null},{"id":"2312.11522","title":"Assessing SATNet's Ability to Solve the Symbol Grounding Problem","created":"2023-12-13","cited_by_count":10,"area":null},{"id":"2107.07116","title":"Transformer-based Machine Learning for Fast SAT Solvers and Logic Synthesis","created":"2021-07-15","cited_by_count":9,"area":null},{"id":"2410.04968","title":"Collaboration! Towards Robust Neural Methods for Routing Problems","created":"2024-10-07","cited_by_count":9,"area":null},{"id":"2412.08457","title":"Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection","created":"2024-12-11","cited_by_count":9,"area":"lr"},{"id":"2102.11485","title":"Generalized Equivariance and Preferential Labeling for GNN Node Classification","created":"2021-02-23","cited_by_count":7,"area":null},{"id":"2401.05960","title":"Machine Learning Insides OptVerse AI Solver: Design Principles and Applications","created":"2024-01-11","cited_by_count":7,"area":null},{"id":"2403.04017","title":"Learning Guided Automated Reasoning: A Brief Survey","created":"2024-03-06","cited_by_count":7,"area":"lr"},{"id":"2205.11638","title":"DOGE-Train: Discrete Optimization on GPU with End-to-end Training","created":"2022-05-23","cited_by_count":6,"area":null},{"id":"2212.04934","title":"Learning Graph Algorithms With Recurrent Graph Neural Networks","created":"2022-12-09","cited_by_count":6,"area":null},{"id":"2312.10589","title":"NN-Steiner: A Mixed Neural-algorithmic Approach for the Rectilinear Steiner Minimum Tree Problem","created":"2023-12-17","cited_by_count":6,"area":null},{"id":"2405.06677","title":"ATG: Benchmarking Automated Theorem Generation for Generative Language Models","created":"2024-05-05","cited_by_count":6,"area":null},{"id":"2502.15794","title":"Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction","created":"2025-02-18","cited_by_count":6,"area":"deeprl"},{"id":"2110.10054","title":"Generating Symbolic Reasoning Problems with Transformer GANs","created":"2021-10-19","cited_by_count":5,"area":null},{"id":"2111.07568","title":"Can Graph Neural Networks Learn to Solve MaxSAT Problem?","created":"2021-11-15","cited_by_count":5,"area":null},{"id":"2204.01366","title":"Learning to solve Minimum Cost Multicuts efficiently using Edge-Weighted Graph Convolutional Neural Networks","created":"2022-04-04","cited_by_count":5,"area":null},{"id":"2210.09082","title":"A Solver-Free Framework for Scalable Learning in Neural ILP Architectures","created":"2022-10-17","cited_by_count":5,"area":null},{"id":"2310.05309","title":"Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Methods","created":"2023-10-08","cited_by_count":5,"area":null},{"id":"2403.06026","title":"Towards a Generic Representation of Combinatorial Problems for Learning-Based Approaches","created":"2024-03-09","cited_by_count":5,"area":null},{"id":"2405.11024","title":"GraSS: Combining Graph Neural Networks with Expert Knowledge for SAT Solver Selection","created":"2024-05-17","cited_by_count":5,"area":null},{"id":"2406.13125","title":"A Unified Framework for Combinatorial Optimization Based on Graph Neural Networks","created":"2024-06-19","cited_by_count":5,"area":null},{"id":"2410.22597","title":"Are Large-Language Models Graph Algorithmic Reasoners?","created":"2024-10-29","cited_by_count":5,"area":"lr"},{"id":"2106.06210","title":"Learning to Pool in Graph Neural Networks for Extrapolation","created":"2021-06-11","cited_by_count":4,"area":null},{"id":"2108.08368","title":"Computing Steiner Trees using Graph Neural Networks","created":"2021-08-18","cited_by_count":4,"area":null},{"id":"2206.13998","title":"Learning Symmetric Rules with SATNet","created":"2022-06-28","cited_by_count":4,"area":null},{"id":"2209.06589","title":"Towards Better Generalization with Flexible Representation of Multi-Module Graph Neural Networks","created":"2022-09-14","cited_by_count":4,"area":null},{"id":"2212.00121","title":"Denoising Diffusion for Sampling SAT Solutions","created":"2022-11-30","cited_by_count":4,"area":"diffusion"},{"id":"2308.11652","title":"Accelerating Exact Combinatorial Optimization via RL-based Initialization -- A Case Study in Scheduling","created":"2023-08-19","cited_by_count":4,"area":null},{"id":"2312.16423","title":"General Method for Solving Four Types of SAT Problems","created":"2023-12-27","cited_by_count":4,"area":null},{"id":"2502.02446","title":"Towards graph neural networks for provably solving convex optimization problems","created":"2025-02-04","cited_by_count":4,"area":null},{"id":"2505.00291","title":"Repetition Makes Perfect: Recurrent Graph Neural Networks Match Message-Passing Limit","created":"2025-05-01","cited_by_count":4,"area":null},{"id":"2505.16053","title":"Learning from Algorithm Feedback: One-Shot SAT Solver Guidance with GNNs","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2107.02418","title":"Probabilistic Graph Reasoning for Natural Proof Generation","created":"2021-07-06","cited_by_count":3,"area":null},{"id":"2302.00272","title":"W2SAT: Learning to generate SAT instances from Weighted Literal Incidence Graphs","created":"2023-02-01","cited_by_count":3,"area":null},{"id":"2304.08738","title":"Addressing Variable Dependency in GNN-based SAT Solving","created":"2023-04-18","cited_by_count":3,"area":null},{"id":"2312.14836","title":"Learning Lagrangian Multipliers for the Travelling Salesman Problem","created":"2023-12-22","cited_by_count":3,"area":null},{"id":"2401.12131","title":"NeuroSynt: A Neuro-symbolic Portfolio Solver for Reactive Synthesis","created":"2024-01-22","cited_by_count":3,"area":null},{"id":"2402.03640","title":"torchmSAT: A GPU-Accelerated Approximation To The Maximum Satisfiability Problem","created":"2024-02-06","cited_by_count":3,"area":null},{"id":"2408.15418","title":"Understanding GNNs for Boolean Satisfiability through Approximation Algorithms","created":"2024-08-27","cited_by_count":3,"area":null}],"next_cursor":"100"}