{"total":170,"rows":[{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732,"area":null},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514,"area":"ssm"},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502,"area":null},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499,"area":null},{"id":"2407.04620","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","created":"2024-07-05","cited_by_count":355,"area":"ssm"},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354,"area":null},{"id":"2212.13345","title":"The Forward-Forward Algorithm: Some Preliminary Investigations","created":"2022-12-27","cited_by_count":266,"area":null},{"id":"2207.06881","title":"Recurrent Memory Transformer","created":"2022-07-14","cited_by_count":203,"area":null},{"id":"2404.07143","title":"Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention","created":"2024-04-10","cited_by_count":200,"area":null},{"id":"2502.05167","title":"NoLiMa: Long-Context Evaluation Beyond Literal Matching","created":"2025-02-07","cited_by_count":126,"area":null},{"id":"2102.12627","title":"How to represent part-whole hierarchies in a neural network","created":"2021-02-25","cited_by_count":123,"area":null},{"id":"2402.04347","title":"The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry","created":"2024-02-06","cited_by_count":120,"area":null},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107,"area":null},{"id":"2309.05858","title":"Uncovering mesa-optimization algorithms in Transformers","created":"2023-09-11","cited_by_count":100,"area":null},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"area":null},{"id":"2409.07146","title":"Gated Slot Attention for Efficient Linear-Time Sequence Modeling","created":"2024-09-11","cited_by_count":76,"area":null},{"id":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"area":null},{"id":"2402.18510","title":"RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval","created":"2024-02-28","cited_by_count":64,"area":null},{"id":"2112.04035","title":"Relating transformers to models and neural representations of the hippocampal formation","created":"2021-12-07","cited_by_count":62,"area":null},{"id":"2506.05233","title":"MesaNet: Sequence Modeling by Locally Optimal Test-Time Training","created":"2025-06-05","cited_by_count":47,"area":null},{"id":"2202.05798","title":"The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention","created":"2022-02-11","cited_by_count":46,"area":null},{"id":"2207.00787","title":"Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation","created":"2022-07-02","cited_by_count":46,"area":null},{"id":"2312.03414","title":"Compressed Context Memory For Online Language Model Interaction","created":"2023-12-06","cited_by_count":43,"area":null},{"id":"2202.05780","title":"A Modern Self-Referential Weight Matrix That Learns to Modify Itself","created":"2022-02-11","cited_by_count":41,"area":null},{"id":"2406.09347","title":"Separations in the Representational Capabilities of Transformers and Recurrent Architectures","created":"2024-06-13","cited_by_count":29,"area":null},{"id":"2210.04243","title":"Fine-Tuning Pre-trained Transformers into Decaying Fast Weights","created":"2022-10-09","cited_by_count":26,"area":null},{"id":"2411.05877","title":"Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass","created":"2024-11-08","cited_by_count":26,"area":null},{"id":"2502.01567","title":"Latent Thought Models with Variational Bayes Inference-Time Computation","created":"2025-02-03","cited_by_count":25,"area":"lr"},{"id":"2310.18780","title":"Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions","created":"2023-10-28","cited_by_count":24,"area":null},{"id":"2501.02950","title":"Key-value memory in the brain","created":"2025-01-06","cited_by_count":24,"area":null},{"id":"2208.08349","title":"Open Long-Tailed Recognition in a Dynamic World","created":"2022-08-17","cited_by_count":21,"area":null},{"id":"2212.02475","title":"Meta-Learning Fast Weight Language Models","created":"2022-12-05","cited_by_count":21,"area":null},{"id":"2104.13424","title":"Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution","created":"2021-04-27","cited_by_count":20,"area":null},{"id":"2310.16076","title":"Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions","created":"2023-10-24","cited_by_count":20,"area":null},{"id":"2604.06169","title":"In-Place Test-Time Training","created":"2026-04-07","cited_by_count":20,"area":null},{"id":"2102.10212","title":"Hard-Attention for Scalable Image Classification","created":"2021-02-20","cited_by_count":18,"area":null},{"id":"2307.01189","title":"Trainable Transformer in Transformer","created":"2023-07-03","cited_by_count":17,"area":null},{"id":"2310.08049","title":"Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability","created":"2023-10-12","cited_by_count":17,"area":null},{"id":"2310.13807","title":"Learning to (Learn at Test Time)","created":"2023-10-20","cited_by_count":17,"area":null},{"id":"2409.11593","title":"Self-Contrastive Forward-Forward Algorithm","created":"2024-09-17","cited_by_count":17,"area":null},{"id":"2309.08045","title":"Traveling Waves Encode the Recent Past and Enhance Sequence Learning","created":"2023-09-03","cited_by_count":16,"area":null},{"id":"2502.12920","title":"Lightweight Online Adaption for Time Series Foundation Model Forecasts","created":"2025-02-18","cited_by_count":16,"area":null},{"id":"2205.14794","title":"Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning","created":"2022-05-30","cited_by_count":13,"area":null},{"id":"2409.13265","title":"Towards LifeSpan Cognitive Systems","created":"2024-09-20","cited_by_count":13,"area":null},{"id":"2601.00671","title":"Fast-weight Product Key Memory","created":"2026-01-02","cited_by_count":13,"area":null},{"id":"2506.00744","title":"Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers","created":"2025-05-31","cited_by_count":12,"area":null},{"id":"2104.01198","title":"Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories","created":"2021-04-02","cited_by_count":11,"area":null},{"id":"2108.07895","title":"Adaptive Convolutions with Per-pixel Dynamic Filter Atom","created":"2021-08-17","cited_by_count":11,"area":null},{"id":"2603.12255","title":"Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training","created":"2026-03-12","cited_by_count":11,"area":null},{"id":"2204.05424","title":"A Call for Clarity in Beam Search: How It Works and When It Stops","created":"2022-04-11","cited_by_count":10,"area":null},{"id":"2305.14376","title":"PTGB: Pre-Train Graph Neural Networks for Brain Network Analysis","created":"2023-05-20","cited_by_count":10,"area":null},{"id":"2410.10132","title":"Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning","created":"2024-10-14","cited_by_count":9,"area":"deeprl"},{"id":"2505.15105","title":"Mechanistic evaluation of Transformers and state space models","created":"2025-05-21","cited_by_count":9,"area":"ssm"},{"id":"2210.13569","title":"Characterizing Verbatim Short-Term Memory in Neural Language Models","created":"2022-10-24","cited_by_count":8,"area":null},{"id":"2508.08435","title":"Fast weight programming and linear transformers: from machine learning to neurobiology","created":"2025-08-11","cited_by_count":8,"area":null},{"id":"2603.01761","title":"Position: Modular Memory is the Key to Continual Learning Agents","created":"2026-03-02","cited_by_count":8,"area":"lr"},{"id":"2202.08371","title":"The Quarks of Attention","created":"2022-02-15","cited_by_count":7,"area":null},{"id":"2309.01775","title":"Gated recurrent neural networks discover attention","created":"2023-09-04","cited_by_count":7,"area":null},{"id":"2503.00838","title":"Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Models","created":"2025-03-02","cited_by_count":7,"area":null},{"id":"2509.21936","title":"Statistical Advantage of Softmax Attention: Insights from Single-Location Regression","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2605.20670","title":"LT2: Linear-Time Looped Transformers","created":"2026-05-20","cited_by_count":7,"area":null},{"id":"2607.26760","title":"Metis: Memory Foundation Model","created":"2026-07-29","cited_by_count":7,"area":"lr"},{"id":"2206.14048","title":"Short-Term Plasticity Neurons Learning to Learn and Forget","created":"2022-06-28","cited_by_count":6,"area":null},{"id":"2407.05591","title":"On the Power of Convolution Augmented Transformer","created":"2024-07-08","cited_by_count":6,"area":null},{"id":"2501.00659","title":"Why Are Positional Encodings Nonessential for Deep Autoregressive Transformers? Revisiting a Petroglyph","created":"2024-12-31","cited_by_count":6,"area":null},{"id":"2601.12906","title":"Gated Differentiable Working Memory for Long-Context Language Modeling","created":"2026-01-19","cited_by_count":6,"area":null},{"id":"2605.12484","title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2606.22793","title":"A Formula-Driven Survey and Research Agenda for On-Policy Distillation","created":"2026-06-22","cited_by_count":6,"area":"distill"},{"id":"2106.10771","title":"Multirate Training of Neural Networks","created":"2021-06-20","cited_by_count":5,"area":null},{"id":"2204.09047","title":"Learning Theory of Mind via Dynamic Traits Attribution","created":"2022-04-17","cited_by_count":5,"area":null},{"id":"2302.00930","title":"Adaptive Siamese Tracking with a Compact Latent Network","created":"2023-02-02","cited_by_count":5,"area":null},{"id":"2506.01153","title":"Weight-Space Linear Recurrent Neural Networks","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2507.00449","title":"Overcoming Long-Context Limitations of State-Space Models via Context-Dependent Sparse Attention","created":"2025-07-01","cited_by_count":5,"area":null},{"id":"2608.13416","title":"StreamTTT: Reconciling Real-Time Perception and Long-Term Memory in Streaming VLMs","created":"2026-08-13","cited_by_count":5,"area":null},{"id":"2112.15545","title":"Training and Generating Neural Networks in Compressed Weight Space","created":"2021-12-31","cited_by_count":4,"area":null},{"id":"2202.02363","title":"Meta-Reinforcement Learning with Self-Modifying Networks","created":"2022-02-04","cited_by_count":4,"area":null},{"id":"2205.11713","title":"Thalamus: a brain-inspired algorithm for biologically-plausible continual learning and disentangled representations","created":"2022-05-24","cited_by_count":4,"area":null},{"id":"2302.03235","title":"Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs","created":"2023-02-07","cited_by_count":4,"area":null},{"id":"2501.00712","title":"Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding","created":"2025-01-01","cited_by_count":4,"area":"lr"},{"id":"2501.14256","title":"DKT2: Revisiting Applicable and Comprehensive Knowledge Tracing in Large-Scale Data","created":"2025-01-24","cited_by_count":4,"area":null},{"id":"2502.01578","title":"ReGLA: Refining Gated Linear Attention","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2605.05838","title":"MDN: Parallelizing Stepwise Momentum for Delta Linear Attention","created":"2026-05-07","cited_by_count":4,"area":null},{"id":"2607.25380","title":"Memory for Large Language Models","created":"2026-07-28","cited_by_count":4,"area":null},{"id":"2209.13635","title":"Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning","created":"2022-09-27","cited_by_count":3,"area":null},{"id":"2407.17771","title":"Banyan: Improved Representation Learning with Explicit Structure","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2410.11687","title":"Learning in the Recurrent State: Gradient Descent with Linear Recurrent Networks","created":"2024-10-15","cited_by_count":3,"area":null},{"id":"2410.15678","title":"Revealing and Mitigating the Local Pattern Shortcuts of Mamba","created":"2024-10-21","cited_by_count":3,"area":"ssm"},{"id":"2605.02920","title":"Where to Bind Matters: Hebbian Fast Weights in Vision Transformers for Few-Shot Character Recognition","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2606.30461","title":"MuonSSM: Orthogonalizing State Space Models for Sequence Modeling","created":"2026-06-29","cited_by_count":3,"area":"ssm"},{"id":"2608.07110","title":"Modular TTT: Rethinking Test-Time Training as Composable Modules","created":"2026-08-07","cited_by_count":3,"area":null},{"id":"2106.05317","title":"Attentional Meta-learners for Few-shot Polythetic Classification","created":"2021-06-09","cited_by_count":2,"area":null},{"id":"2301.02809","title":"A Brain-inspired Memory Transformation based Differentiable Neural Computer for Reasoning-based Question Answering","created":"2023-01-07","cited_by_count":2,"area":null},{"id":"2402.01557","title":"Deep Continuous Networks","created":"2024-02-02","cited_by_count":2,"area":null},{"id":"2406.01012","title":"Attention-based Iterative Decomposition for Tensor Product Representation","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2410.19382","title":"Multi-Agent Reinforcement Learning with Selective State-Space Models","created":"2024-10-25","cited_by_count":2,"area":"ssm"},{"id":"2504.20109","title":"Personalized Artificial General Intelligence (AGI) via Neuroscience-Inspired Continuous Learning Systems","created":"2025-04-27","cited_by_count":2,"area":null},{"id":"2510.19105","title":"MetaCluster: Enabling Deep Compression of Kolmogorov-Arnold Network","created":"2025-10-21","cited_by_count":2,"area":null},{"id":"2510.27258","title":"Higher-order Linear Attention","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2605.22884","title":"Tensor Cache: Eviction-conditioned Associative Memory for Transformers","created":"2026-05-21","cited_by_count":2,"area":"inference"},{"id":"2606.02775","title":"AURA: Action-Gated Memory for Robot Policies at Constant VRAM","created":"2026-06-01","cited_by_count":2,"area":"inference"}],"next_cursor":"100"}