{"total":70,"rows":[{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167,"area":null},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2102.09544","title":"Combinatorial optimization and reasoning with graph neural networks","created":"2021-02-18","cited_by_count":268,"area":null},{"id":"2102.13019","title":"Investigating the Limitations of Transformers with Simple Arithmetic Tasks","created":"2021-02-25","cited_by_count":139,"area":null},{"id":"2205.15659","title":"The CLRS Algorithmic Reasoning Benchmark","created":"2022-05-31","cited_by_count":106,"area":null},{"id":"2103.13136","title":"Representing Numbers in NLP: a Survey and a Vision","created":"2021-03-24","cited_by_count":83,"area":null},{"id":"2103.01937","title":"Neural Production Systems: Learning Rule-Governed Visual Dynamics","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2306.15400","title":"Length Generalization in Arithmetic Transformers","created":"2023-06-27","cited_by_count":66,"area":null},{"id":"2112.01898","title":"Linear algebra with transformers","created":"2021-12-03","cited_by_count":63,"area":null},{"id":"2204.07697","title":"Theory of Graph Neural Networks: Representation and Learning","created":"2022-04-16","cited_by_count":61,"area":null},{"id":"2201.04600","title":"Deep Symbolic Regression for Recurrent Sequences","created":"2022-01-12","cited_by_count":54,"area":null},{"id":"2101.08366","title":"Quadratic Residual Networks: A New Class of Neural Networks for Solving Forward and Inverse Problems in Physics Involving PDEs","created":"2021-01-20","cited_by_count":43,"area":null},{"id":"2210.05062","title":"Relational Attention: Generalizing Transformers for Graph-Structured Tasks","created":"2022-10-11","cited_by_count":41,"area":null},{"id":"2308.15594","title":"Learning the greatest common divisor: explaining transformer predictions","created":"2023-08-29","cited_by_count":33,"area":null},{"id":"2106.11905","title":"Dangers of Bayesian Model Averaging under Covariate Shift","created":"2021-06-22","cited_by_count":31,"area":null},{"id":"2207.04785","title":"SALSA: Attacking Lattice Cryptography with Transformers","created":"2022-07-11","cited_by_count":28,"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":"2207.00529","title":"Deep Learning and Symbolic Regression for Discovering Parametric Equations","created":"2022-07-01","cited_by_count":23,"area":null},{"id":"2311.04128","title":"Generative learning for nonlinear dynamics","created":"2023-11-07","cited_by_count":22,"area":null},{"id":"2303.07735","title":"Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models","created":"2023-03-14","cited_by_count":18,"area":"lr"},{"id":"2101.05186","title":"MC-LSTM: Mass-Conserving LSTM","created":"2021-01-13","cited_by_count":17,"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":"2306.13411","title":"Neural Algorithmic Reasoning Without Intermediate Supervision","created":"2023-06-23","cited_by_count":17,"area":null},{"id":"2403.00323","title":"Softened Symbol Grounding for Neuro-symbolic Systems","created":"2024-03-01","cited_by_count":16,"area":null},{"id":"2109.04672","title":"Investigating Numeracy Learning Ability of a Text-to-Text Transfer Model","created":"2021-09-10","cited_by_count":13,"area":null},{"id":"2110.01839","title":"Truth-Conditional Captioning of Time Series Data","created":"2021-10-05","cited_by_count":11,"area":null},{"id":"2208.11445","title":"Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models","created":"2022-08-24","cited_by_count":10,"area":null},{"id":"2402.02334","title":"Arithmetic Feature Interaction Is Necessary for Deep Tabular Learning","created":"2024-02-04","cited_by_count":8,"area":null},{"id":"2207.02536","title":"Transformers discover an elementary calculation system exploiting local attention and grid-like problem representation","created":"2022-07-06","cited_by_count":7,"area":"lr"},{"id":"2509.16825","title":"KANO: Kolmogorov-Arnold Neural Operator","created":"2025-09-20","cited_by_count":7,"area":null},{"id":"2205.09067","title":"Automatic Rule Induction for Interpretable Semi-Supervised Learning","created":"2022-05-18","cited_by_count":6,"area":null},{"id":"2308.10487","title":"Deciphering Raw Data in Neuro-Symbolic Learning with Provable Guarantees","created":"2023-08-21","cited_by_count":6,"area":"lr"},{"id":"2310.10062","title":"A Comprehensive Evaluation of Tool-Assisted Generation Strategies","created":"2023-10-16","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":"2105.07957","title":"Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers","created":"2021-05-17","cited_by_count":5,"area":null},{"id":"2106.06210","title":"Learning to Pool in Graph Neural Networks for Extrapolation","created":"2021-06-11","cited_by_count":4,"area":null},{"id":"2205.12245","title":"Asynchronous Neural Networks for Learning in Graphs","created":"2022-05-24","cited_by_count":4,"area":null},{"id":"2301.04605","title":"Exploring the Approximation Capabilities of Multiplicative Neural Networks for Smooth Functions","created":"2023-01-11","cited_by_count":4,"area":null},{"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":"2503.02379","title":"Teaching Metric Distance to Discrete Autoregressive Language Models","created":"2025-03-04","cited_by_count":4,"area":"lr"},{"id":"2207.06240","title":"Physics Informed Symbolic Networks","created":"2022-07-11","cited_by_count":3,"area":null},{"id":"2211.07727","title":"Logical Tasks for Measuring Extrapolation and Rule Comprehension","created":"2022-11-14","cited_by_count":3,"area":"lr"},{"id":"2405.16658","title":"Acceleration of Grokking in Learning Arithmetic Operations via Kolmogorov-Arnold Representation","created":"2024-05-26","cited_by_count":3,"area":null},{"id":"2606.31845","title":"Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors","created":"2026-06-30","cited_by_count":3,"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":"2310.05145","title":"NeuralFastLAS: Fast Logic-Based Learning from Raw Data","created":"2023-10-08","cited_by_count":2,"area":null},{"id":"2103.16795","title":"Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation","created":"2021-03-31","cited_by_count":1,"area":null},{"id":"2207.14643","title":"Open World Learning Graph Convolution for Latency Estimation in Routing Networks","created":"2022-07-08","cited_by_count":1,"area":null},{"id":"2301.06870","title":"Learning to solve arithmetic problems with a virtual abacus","created":"2023-01-17","cited_by_count":1,"area":null},{"id":"2306.17249","title":"A Hybrid System for Systematic Generalization in Simple Arithmetic Problems","created":"2023-06-29","cited_by_count":1,"area":"lr"},{"id":"2601.13953","title":"Differentiable Logic Synthesis: Spectral Coefficient Selection via Sinkhorn-Constrained Composition","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2601.15714","title":"Even GPT-5.2 Can't Count to Five: The Case for Zero-Error Horizons in Trustworthy LLMs","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2601.18702","title":"From Fuzzy to Exact: The Halo Architecture for Infinite-Depth Reasoning via Rational Arithmetic","created":"2026-01-26","cited_by_count":1,"area":"lr"},{"id":"2608.00418","title":"Making Transformers Logical","created":"2026-08-01","cited_by_count":1,"area":null},{"id":"2103.06198","title":"Relational Weight Priors in Neural Networks for Abstract Pattern Learning and Language Modelling","created":"2021-03-10","cited_by_count":0,"area":null},{"id":"2110.05177","title":"Learning Division with Neural Arithmetic Logic Modules","created":"2021-10-11","cited_by_count":0,"area":null},{"id":"2211.05624","title":"Improving the Robustness of Neural Multiplication Units with Reversible Stochasticity","created":"2022-11-10","cited_by_count":0,"area":null},{"id":"2304.08880","title":"NPS: A Framework for Accurate Program Sampling Using Graph Neural Network","created":"2023-04-18","cited_by_count":0,"area":null},{"id":"2309.06382","title":"Ensemble Mask Networks","created":"2023-09-12","cited_by_count":0,"area":null},{"id":"2407.14430","title":"The Extrapolation Power of Implicit Models","created":"2024-07-19","cited_by_count":0,"area":null},{"id":"2503.02773","title":"Prime Convolutional Model: Breaking the Ground for Theoretical Explainability","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2509.08180","title":"The Domain Mixed Unit: A New Neural Arithmetic Layer","created":"2025-09-09","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},{"id":"2603.28248","title":"Reasoning as Energy Minimization over Structured Latent Trajectories","created":"2026-03-30","cited_by_count":0,"area":"lr"},{"id":"2604.11284","title":"THEIA: Learning Complete Kleene Three-Valued Logic in a Pure-Neural Modular Architecture","created":"2026-04-13","cited_by_count":0,"area":"mechinterp"},{"id":"2606.00045","title":"Universal Quantum Transformer","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2606.01372","title":"BRo-JEPA: Learning Modular Transformations in Latent Space","created":"2026-05-31","cited_by_count":0,"area":"wm"},{"id":"2608.20360","title":"TriPLU: Bypassing the Gate with Direct Trilinear Product FFNs in Tiny Language Models","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2609.32927","title":"The Geometry of Logic: Stratification Induces Semantic Structure and Robust Reasoning","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2610.05143","title":"Arithmetic Actor Heads and Training Stabilization for Out-of-Distribution Reinforcement Learning","created":"2026-10-04","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}