{"total":55,"rows":[{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253,"area":null},{"id":"2208.03306","title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models","created":"2022-08-05","cited_by_count":191,"area":null},{"id":"2210.17451","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","created":"2022-10-31","cited_by_count":137,"area":null},{"id":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2304.04947","title":"Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference","created":"2023-04-11","cited_by_count":69,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2303.14177","title":"Scaling Expert Language Models with Unsupervised Domain Discovery","created":"2023-03-24","cited_by_count":60,"area":null},{"id":"2303.10845","title":"PanGu-{\\Sigma}: Towards Trillion Parameter Language Model with Sparse Heterogeneous Computing","created":"2023-03-20","cited_by_count":56,"area":null},{"id":"2112.12731","title":"ERNIE 3.0 Titan: Exploring Larger-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-12-23","cited_by_count":46,"area":null},{"id":"2305.09955","title":"Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models","created":"2023-05-17","cited_by_count":46,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2404.08763","title":"CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models","created":"2024-04-12","cited_by_count":41,"area":null},{"id":"2306.05406","title":"Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models Memories","created":"2023-06-08","cited_by_count":34,"area":null},{"id":"2405.16156","title":"Mixture of In-Context Prompters for Tabular PFNs","created":"2024-05-25","cited_by_count":33,"area":null},{"id":"2209.15466","title":"Sparsity-Constrained Optimal Transport","created":"2022-09-30","cited_by_count":32,"area":null},{"id":"2110.03888","title":"M6-10T: A Sharing-Delinking Paradigm for Efficient Multi-Trillion Parameter Pretraining","created":"2021-10-08","cited_by_count":31,"area":null},{"id":"2306.00008","title":"Brainformers: Trading Simplicity for Efficiency","created":"2023-05-29","cited_by_count":31,"area":null},{"id":"2312.06786","title":"Mixture-of-Linear-Experts for Long-term Time Series Forecasting","created":"2023-12-11","cited_by_count":29,"area":null},{"id":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2309.16354","title":"Transformer-VQ: Linear-Time Transformers via Vector Quantization","created":"2023-09-28","cited_by_count":26,"area":null},{"id":"2302.02596","title":"Ten Lessons We Have Learned in the New \"Sparseland\": A Short Handbook for Sparse Neural Network Researchers","created":"2023-02-06","cited_by_count":25,"area":null},{"id":"2202.07101","title":"A Survey on Dynamic Neural Networks for Natural Language Processing","created":"2022-02-15","cited_by_count":24,"area":null},{"id":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2311.15436","title":"Learning to Skip for Language Modeling","created":"2023-11-26","cited_by_count":19,"area":null},{"id":"2309.14763","title":"ConPET: Continual Parameter-Efficient Tuning for Large Language Models","created":"2023-09-26","cited_by_count":17,"area":null},{"id":"2312.17276","title":"PanGu-$\\pi$: Enhancing Language Model Architectures via Nonlinearity Compensation","created":"2023-12-27","cited_by_count":17,"area":null},{"id":"2301.13310","title":"Alternating Updates for Efficient Transformers","created":"2023-01-30","cited_by_count":13,"area":null},{"id":"2305.02665","title":"Learning Language-Specific Layers for Multilingual Machine Translation","created":"2023-05-04","cited_by_count":13,"area":null},{"id":"2402.08341","title":"Eliciting Personality Traits in Large Language Models","created":"2024-02-13","cited_by_count":12,"area":null},{"id":"2601.10639","title":"STEM: Scaling Transformers with Embedding Modules","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2303.11934","title":"Sparse Distributed Memory is a Continual Learner","created":"2023-03-20","cited_by_count":11,"area":null},{"id":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2408.11869","title":"ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA","created":"2024-08-19","cited_by_count":8,"area":null},{"id":"2205.12410","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","created":"2022-05-24","cited_by_count":7,"area":null},{"id":"2306.14525","title":"ParameterNet: Parameters Are All You Need","created":"2023-06-26","cited_by_count":7,"area":null},{"id":"2406.05360","title":"Flexible and Adaptable Summarization via Expertise Separation","created":"2024-06-08","cited_by_count":7,"area":null},{"id":"2402.05955","title":"A Hyper-Transformer model for Controllable Pareto Front Learning with Split Feasibility Constraints","created":"2024-02-04","cited_by_count":3,"area":null},{"id":"2403.08477","title":"Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts","created":"2024-03-13","cited_by_count":3,"area":null},{"id":"2509.25380","title":"Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.04331","title":"DoRAN: Stabilizing Weight-Decomposed Low-Rank Adaptation via Noise Injection and Auxiliary Networks","created":"2025-10-05","cited_by_count":2,"area":null},{"id":"2603.02227","title":"Routing Absorption in Sparse Attention: Why Random Gates Are Hard to Beat","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2603.10079","title":"Large Spikes in Stochastic Gradient Descent: A Large-Deviations View","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2604.21724","title":"Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2606.07500","title":"Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2608.10416","title":"Riemann GeoResolver: A Non-Euclidean Attention Framework from Euclidean Resolver to Hyperbolic-Spherical Geometry","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2302.00003","title":"The Power of External Memory in Increasing Predictive Model Capacity","created":"2023-01-31","cited_by_count":0,"area":null},{"id":"2310.10480","title":"G-SPEED: General SParse Efficient Editing MoDel","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2504.12471","title":"You Don't Need All Attentions: Distributed Dynamic Fine-Tuning for Foundation Models","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2506.12453","title":"Topology-Assisted Spatio-Temporal Pattern Disentangling for Scalable MARL in Large-scale Autonomous Traffic Control","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2508.20991","title":"ExpertSim: Fast Particle Detector Simulation Using Mixture-of-Generative-Experts","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2601.17616","title":"Split-on-Share: Mixture of Sparse Experts for Task-Agnostic Continual Learning","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2603.08589","title":"CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2605.06501","title":"Cubit: Token Mixer with Kernel Ridge Regression","created":"2026-05-07","cited_by_count":0,"area":null}],"next_cursor":null}