{"total":50,"rows":[{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2309.04827","title":"Neurons in Large Language Models: Dead, N-gram, Positional","created":"2023-09-09","cited_by_count":88,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","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":"2111.07736","title":"Continual Learning via Local Module Composition","created":"2021-11-15","cited_by_count":63,"area":null},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40,"area":null},{"id":"2305.18390","title":"Emergent Modularity in Pre-trained Transformers","created":"2023-05-28","cited_by_count":37,"area":null},{"id":"2105.08710","title":"Fast and Slow Learning of Recurrent Independent Mechanisms","created":"2021-05-18","cited_by_count":36,"area":null},{"id":"2211.03831","title":"Multi-Head Adapter Routing for Cross-Task Generalization","created":"2022-11-07","cited_by_count":33,"area":null},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2202.13914","title":"Combining Modular Skills in Multitask Learning","created":"2022-02-28","cited_by_count":28,"area":null},{"id":"2207.07730","title":"How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2111.12485","title":"Understanding the Dynamics of DNNs Using Graph Modularity","created":"2021-11-24","cited_by_count":26,"area":null},{"id":"2110.06399","title":"Dynamic Inference with Neural Interpreters","created":"2021-10-12","cited_by_count":24,"area":null},{"id":"2207.04136","title":"CompoSuite: A Compositional Reinforcement Learning Benchmark","created":"2022-07-08","cited_by_count":21,"area":null},{"id":"2312.12340","title":"Scalable Geometric Fracture Assembly via Co-creation Space among Assemblers","created":"2023-12-19","cited_by_count":14,"area":null},{"id":"2406.05816","title":"Attention as a Hypernetwork","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2403.01909","title":"Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey","created":"2024-03-04","cited_by_count":12,"area":null},{"id":"2110.08058","title":"Quantifying Local Specialization in Deep Neural Networks","created":"2021-10-13","cited_by_count":10,"area":null},{"id":"2510.02630","title":"HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance","created":"2025-10-03","cited_by_count":10,"area":null},{"id":"2306.15686","title":"Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning","created":"2023-06-23","cited_by_count":9,"area":null},{"id":"2112.09456","title":"Compositional Learning-based Planning for Vision POMDPs","created":"2021-12-17","cited_by_count":8,"area":null},{"id":"2210.14830","title":"Personalized Federated Learning via Heterogeneous Modular Networks","created":"2022-10-26","cited_by_count":8,"area":null},{"id":"2502.17788","title":"On-device edge learning for IoT data streams: a survey","created":"2025-02-25","cited_by_count":8,"area":null},{"id":"2106.02626","title":"Dynamics of specialization in neural modules under resource constraints","created":"2021-06-04","cited_by_count":6,"area":null},{"id":"2106.14993","title":"Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment","created":"2021-06-28","cited_by_count":6,"area":null},{"id":"2209.06116","title":"Patching Weak Convolutional Neural Network Models through Modularization and Composition","created":"2022-09-11","cited_by_count":6,"area":null},{"id":"2206.01627","title":"Pruning for Feature-Preserving Circuits in CNNs","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2407.17356","title":"Gradient-based inference of abstract task representations for generalization in neural networks","created":"2024-07-24","cited_by_count":4,"area":null},{"id":"2211.17142","title":"Learning Label Modular Prompts for Text Classification in the Wild","created":"2022-11-30","cited_by_count":3,"area":null},{"id":"2310.01154","title":"Modularity in Deep Learning: A Survey","created":"2023-10-02","cited_by_count":3,"area":null},{"id":"2501.02837","title":"Forward Once for All: Structural Parameterized Adaptation for Efficient Cloud-coordinated On-device Recommendation","created":"2025-01-06","cited_by_count":3,"area":null},{"id":"2107.10963","title":"Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks","created":"2021-07-23","cited_by_count":2,"area":null},{"id":"2206.05810","title":"Analysis of Branch Specialization and its Application in Image Decomposition","created":"2022-06-12","cited_by_count":2,"area":null},{"id":"2303.04156","title":"Computing with Categories in Machine Learning","created":"2023-03-07","cited_by_count":2,"area":null},{"id":"2307.01446","title":"On Conditional and Compositional Language Model Differentiable Prompting","created":"2023-07-04","cited_by_count":2,"area":null},{"id":"2411.03840","title":"Flexible task abstractions emerge in linear networks with fast and bounded units","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2602.18960","title":"Modularity is the Bedrock of Natural and Artificial Intelligence","created":"2026-02-21","cited_by_count":2,"area":null},{"id":"2104.11410","title":"A modularity comparison of Long Short-Term Memory and Morphognosis neural networks","created":"2021-04-23","cited_by_count":1,"area":null},{"id":"2311.11083","title":"ECLM: Efficient Edge-Cloud Collaborative Learning with Continuous Environment Adaptation","created":"2023-11-18","cited_by_count":1,"area":null},{"id":"2512.15083","title":"Neural Modular Physics for Elastic Simulation","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2201.09534","title":"PaRT: Parallel Learning Towards Robust and Transparent AI","created":"2022-01-24","cited_by_count":0,"area":null},{"id":"2306.01316","title":"Independent Modular Networks","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2311.02123","title":"RigLSTM: Recurrent Independent Grid LSTM for Generalizable Sequence Learning","created":"2023-11-03","cited_by_count":0,"area":null},{"id":"2402.08345","title":"Conditional Information Gain Trellis","created":"2024-02-13","cited_by_count":0,"area":null},{"id":"2405.17466","title":"Distributed Continual Learning","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2504.18241","title":"Switch-Based Multi-Part Neural Network","created":"2025-04-25","cited_by_count":0,"area":null},{"id":"2508.00197","title":"Graph Lineages and Skeletal Graph Products","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2509.01874","title":"Preserving Bilinear Weight Spectra with a Signed and Shrunk Quadratic Activation Function","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2610.00541","title":"Random Recursive Models","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}