{"total":126,"rows":[{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073,"area":"moe"},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747,"area":"moe"},{"id":"2110.14048","title":"Conflict-Averse Gradient Descent for Multi-task Learning","created":"2021-10-26","cited_by_count":459,"area":null},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253,"area":null},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237,"area":"moe"},{"id":"2209.01667","title":"A Review of Sparse Expert Models in Deep Learning","created":"2022-09-04","cited_by_count":148,"area":"moe"},{"id":"2401.16468","title":"InstructIR: High-Quality Image Restoration Following Human Instructions","created":"2024-01-29","cited_by_count":140,"area":null},{"id":"2106.03760","title":"DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning","created":"2021-06-07","cited_by_count":115,"area":"moe"},{"id":"2104.03466","title":"Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT","created":"2021-04-08","cited_by_count":104,"area":null},{"id":"2103.01197","title":"Coordination Among Neural Modules Through a Shared Global Workspace","created":"2021-03-01","cited_by_count":85,"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":"2202.03091","title":"Auto-Lambda: Disentangling Dynamic Task Relationships","created":"2022-02-07","cited_by_count":73,"area":null},{"id":"2407.11633","title":"Scaling Diffusion Transformers to 16 Billion Parameters","created":"2024-07-16","cited_by_count":66,"area":"diffusion"},{"id":"2110.11526","title":"Wide Neural Networks Forget Less Catastrophically","created":"2021-10-21","cited_by_count":64,"area":null},{"id":"2106.03027","title":"Model Zoo: A Growing \"Brain\" That Learns Continually","created":"2021-06-06","cited_by_count":54,"area":null},{"id":"2302.11289","title":"Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning","created":"2023-02-22","cited_by_count":51,"area":null},{"id":"2405.00467","title":"Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing","created":"2024-05-01","cited_by_count":46,"area":null},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40,"area":null},{"id":"2107.02367","title":"Discrete-Valued Neural Communication","created":"2021-07-06","cited_by_count":39,"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":"2305.18409","title":"Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms","created":"2023-05-28","cited_by_count":34,"area":null},{"id":"2201.12522","title":"Continual Learning with Recursive Gradient Optimization","created":"2022-01-29","cited_by_count":32,"area":null},{"id":"2412.19726","title":"Position: Theory of Mind Benchmarks are Broken for Large Language Models","created":"2024-12-27","cited_by_count":31,"area":null},{"id":"2411.03284","title":"SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agents","created":"2024-11-05","cited_by_count":30,"area":"agents"},{"id":"2205.09797","title":"Improving Multi-Task Generalization via Regularizing Spurious Correlation","created":"2022-05-19","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":"2201.00042","title":"Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments","created":"2021-12-31","cited_by_count":25,"area":null},{"id":"2110.06399","title":"Dynamic Inference with Neural Interpreters","created":"2021-10-12","cited_by_count":24,"area":null},{"id":"2205.02399","title":"Spot-adaptive Knowledge Distillation","created":"2022-05-05","cited_by_count":22,"area":"distill"},{"id":"2203.14949","title":"Controllable Dynamic Multi-Task Architectures","created":"2022-03-28","cited_by_count":21,"area":null},{"id":"2207.04136","title":"CompoSuite: A Compositional Reinforcement Learning Benchmark","created":"2022-07-08","cited_by_count":21,"area":null},{"id":"2403.09323","title":"E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection","created":"2024-03-14","cited_by_count":21,"area":null},{"id":"2103.00336","title":"Transformers with Competitive Ensembles of Independent Mechanisms","created":"2021-02-27","cited_by_count":19,"area":null},{"id":"2304.14329","title":"Learning to Extrapolate: A Transductive Approach","created":"2023-04-27","cited_by_count":19,"area":null},{"id":"2108.09112","title":"Continual Learning for Image-Based Camera Localization","created":"2021-08-20","cited_by_count":18,"area":null},{"id":"2308.02066","title":"Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives","created":"2023-08-03","cited_by_count":18,"area":null},{"id":"2403.02600","title":"TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts","created":"2024-03-05","cited_by_count":18,"area":"moe"},{"id":"2108.11346","title":"Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral","created":"2021-08-25","cited_by_count":17,"area":null},{"id":"2110.08246","title":"Tricks for Training Sparse Translation Models","created":"2021-10-15","cited_by_count":17,"area":null},{"id":"2204.05133","title":"On the link between conscious function and general intelligence in humans and machines","created":"2022-03-24","cited_by_count":16,"area":null},{"id":"2212.08066","title":"Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learners","created":"2022-12-15","cited_by_count":15,"area":"moe"},{"id":"2210.12624","title":"Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach","created":"2022-10-23","cited_by_count":14,"area":null},{"id":"2211.13491","title":"Spatial Mixture-of-Experts","created":"2022-11-24","cited_by_count":14,"area":"moe"},{"id":"2508.01908","title":"Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models","created":"2025-08-03","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":"2205.10937","title":"muNet: Evolving Pretrained Deep Neural Networks into Scalable Auto-tuning Multitask Systems","created":"2022-05-22","cited_by_count":12,"area":null},{"id":"2205.12701","title":"Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts","created":"2022-05-25","cited_by_count":12,"area":"moe"},{"id":"2405.11530","title":"Learning More Generalized Experts by Merging Experts in Mixture-of-Experts","created":"2024-05-19","cited_by_count":12,"area":"moe"},{"id":"2502.20395","title":"R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts","created":"2025-02-27","cited_by_count":12,"area":"lr"},{"id":"2208.00843","title":"Relay Hindsight Experience Replay: Self-Guided Continual Reinforcement Learning for Sequential Object Manipulation Tasks with Sparse Rewards","created":"2022-08-01","cited_by_count":11,"area":null},{"id":"2303.06095","title":"HiNet: Novel Multi-Scenario & Multi-Task Learning with Hierarchical Information Extraction","created":"2023-03-10","cited_by_count":11,"area":"moe"},{"id":"2402.04005","title":"Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2506.14811","title":"Self-Composing Policies for Scalable Continual Reinforcement Learning","created":"2025-06-04","cited_by_count":11,"area":"deeprl"},{"id":"2110.05838","title":"Balancing Average and Worst-case Accuracy in Multitask Learning","created":"2021-10-12","cited_by_count":10,"area":null},{"id":"2311.01075","title":"Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2403.07965","title":"Conditional computation in neural networks: principles and research trends","created":"2024-03-12","cited_by_count":10,"area":"moe"},{"id":"2407.20734","title":"Efficient Pareto Manifold Learning with Low-Rank Structure","created":"2024-07-30","cited_by_count":9,"area":null},{"id":"2105.01844","title":"Joint Registration and Segmentation via Multi-Task Learning for Adaptive Radiotherapy of Prostate Cancer","created":"2021-05-05","cited_by_count":8,"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":"2312.03248","title":"Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning","created":"2023-12-06","cited_by_count":8,"area":null},{"id":"2308.11744","title":"Efficient Controllable Multi-Task Architectures","created":"2023-08-22","cited_by_count":7,"area":null},{"id":"2410.14633","title":"Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning","created":"2024-10-18","cited_by_count":7,"area":null},{"id":"2412.14355","title":"Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference","created":"2024-12-18","cited_by_count":7,"area":"deeprl"},{"id":"2301.13465","title":"GDOD: Effective Gradient Descent using Orthogonal Decomposition for Multi-Task Learning","created":"2023-01-31","cited_by_count":6,"area":null},{"id":"2308.10716","title":"Color Prompting for Data-Free Continual Unsupervised Domain Adaptive Person Re-Identification","created":"2023-08-21","cited_by_count":6,"area":null},{"id":"2207.01117","title":"Saliency-Regularized Deep Multi-Task Learning","created":"2022-07-03","cited_by_count":5,"area":null},{"id":"2409.05780","title":"Breaking Neural Network Scaling Laws with Modularity","created":"2024-09-09","cited_by_count":5,"area":null},{"id":"2510.00444","title":"TokMem: One-Token Procedural Memory for Large Language Models","created":"2025-10-01","cited_by_count":5,"area":null},{"id":"2510.15416","title":"Adaptive Minds: Empowering Agents with LoRA-as-Tools","created":"2025-10-17","cited_by_count":5,"area":"agents"},{"id":"2206.01627","title":"Pruning for Feature-Preserving Circuits in CNNs","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2309.16467","title":"Compositional Program Generation for Few-Shot Systematic Generalization","created":"2023-09-28","cited_by_count":4,"area":null},{"id":"2409.01793","title":"Task Weighting through Gradient Projection for Multitask Learning","created":"2024-09-03","cited_by_count":4,"area":null},{"id":"2303.04338","title":"Provable Pathways: Learning Multiple Tasks over Multiple Paths","created":"2023-03-08","cited_by_count":3,"area":null},{"id":"2305.19844","title":"Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs","created":"2023-05-31","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":"2510.03930","title":"LLM Chemistry Estimation for Multi-LLM Recommendation","created":"2025-10-04","cited_by_count":3,"area":null},{"id":"2512.19154","title":"Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments","created":"2025-12-22","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":"2202.01011","title":"Auto-Transfer: Learning to Route Transferrable Representations","created":"2022-02-02","cited_by_count":2,"area":null},{"id":"2203.14855","title":"Modular Adaptive Policy Selection for Multi-Task Imitation Learning through Task Division","created":"2022-03-28","cited_by_count":2,"area":"offlinerl"},{"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":"2305.00441","title":"Multi-Task Structural Learning using Local Task Similarity induced Neuron Creation and Removal","created":"2023-04-30","cited_by_count":2,"area":null},{"id":"2308.13957","title":"Differentiable Weight Masks for Domain Transfer","created":"2023-08-26","cited_by_count":2,"area":null},{"id":"2410.08003","title":"More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing","created":"2024-10-10","cited_by_count":2,"area":"moe"},{"id":"2510.01858","title":"Compositional meta-learning through probabilistic task inference","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2512.22337","title":"The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Models","created":"2025-12-26","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":"2606.08897","title":"A multi-agent system for spine MRI report generation from multi-sequence imaging","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2606.24756","title":"Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning","created":"2026-06-23","cited_by_count":2,"area":null},{"id":"2110.13365","title":"Multi-Faceted Hierarchical Multi-Task Learning for a Large Number of Tasks with Multi-dimensional Relations","created":"2021-10-26","cited_by_count":1,"area":null},{"id":"2111.10601","title":"Deep Safe Multi-Task Learning","created":"2021-11-20","cited_by_count":1,"area":null},{"id":"2209.10072","title":"On the Convergence Theory of Meta Reinforcement Learning with Personalized Policies","created":"2022-09-21","cited_by_count":1,"area":null},{"id":"2209.11892","title":"Highly Scalable Task Grouping for Deep Multi-Task Learning in Prediction of Epigenetic Events","created":"2022-09-24","cited_by_count":1,"area":null},{"id":"2306.09742","title":"Meta Generative Flow Networks with Personalization for Task-Specific Adaptation","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2309.08776","title":"Projected Task-Specific Layers for Multi-Task Reinforcement Learning","created":"2023-09-15","cited_by_count":1,"area":null}],"next_cursor":"100"}