{"total":20,"rows":[{"id":"2102.09544","title":"Combinatorial optimization and reasoning with graph neural networks","created":"2021-02-18","cited_by_count":268,"area":null},{"id":"2205.15659","title":"The CLRS Algorithmic Reasoning Benchmark","created":"2022-05-31","cited_by_count":106,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2203.15544","title":"Graph Neural Networks are Dynamic Programmers","created":"2022-03-29","cited_by_count":55,"area":null},{"id":"2410.02486","title":"Encryption-Friendly LLM Architecture","created":"2024-10-03","cited_by_count":17,"area":null},{"id":"2105.03928","title":"Which transformer architecture fits my data? A vocabulary bottleneck in self-attention","created":"2021-05-09","cited_by_count":16,"area":null},{"id":"2212.08541","title":"Learnable Commutative Monoids for Graph Neural Networks","created":"2022-12-16","cited_by_count":13,"area":null},{"id":"2603.11487","title":"Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks","created":"2026-03-12","cited_by_count":11,"area":null},{"id":"2309.06054","title":"Breaking through the learning plateaus of in-context learning in Transformer","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2602.05230","title":"ZeroS: Zero-Sum Linear Attention for Efficient Transformers","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2202.12411","title":"TrimBERT: Tailoring BERT for Trade-offs","created":"2022-02-24","cited_by_count":3,"area":null},{"id":"2602.12601","title":"HyperMLP: An Integrated Perspective for Sequence Modeling","created":"2026-02-13","cited_by_count":3,"area":null},{"id":"2602.23057","title":"Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2207.13423","title":"Rethinking Efficacy of Softmax for Lightweight Non-Local Neural Networks","created":"2022-07-27","cited_by_count":2,"area":null},{"id":"2410.15578","title":"Generalized Probabilistic Attention Mechanism in Transformers","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2510.09389","title":"Design Principles for Sequence Models via Coefficient Dynamics","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2108.03579","title":"Expressive Power and Loss Surfaces of Deep Learning Models","created":"2021-08-08","cited_by_count":0,"area":null},{"id":"2112.05343","title":"Blockwise Sequential Model Learning for Partially Observable Reinforcement Learning","created":"2021-12-10","cited_by_count":0,"area":null},{"id":"2607.22781","title":"What Softmax Throws Away: Mass-Aware Attention for Evidence Accumulation","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2610.13635","title":"PANDA: Prior-guided Attentional Dual-path Architecture","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}