{"total":37,"rows":[{"id":"2211.05102","title":"Efficiently Scaling Transformer Inference","created":"2022-11-09","cited_by_count":539,"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":"2309.04662","title":"MADLAD-400: A Multilingual And Document-Level Large Audited Dataset","created":"2023-09-09","cited_by_count":181,"area":null},{"id":"2310.07707","title":"MatFormer: Nested Transformer for Elastic Inference","created":"2023-10-11","cited_by_count":85,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"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":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52,"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":"2404.08763","title":"CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models","created":"2024-04-12","cited_by_count":41,"area":null},{"id":"2401.10440","title":"Breaking the Curse of Multilinguality with Cross-lingual Expert Language Models","created":"2024-01-19","cited_by_count":38,"area":null},{"id":"2212.09811","title":"Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model","created":"2022-12-19","cited_by_count":36,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2202.13914","title":"Combining Modular Skills in Multitask Learning","created":"2022-02-28","cited_by_count":28,"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":"2305.14224","title":"mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2312.05662","title":"Understanding the Effect of Model Compression on Social Bias in Large Language Models","created":"2023-12-09","cited_by_count":19,"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":"2203.03312","title":"SkillNet-NLU: A Sparsely Activated Model for General-Purpose Natural Language Understanding","created":"2022-03-07","cited_by_count":10,"area":null},{"id":"2312.02520","title":"Towards More Unified In-context Visual Understanding","created":"2023-12-05","cited_by_count":10,"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":"2207.10341","title":"UFO: Unified Feature Optimization","created":"2022-07-21","cited_by_count":7,"area":null},{"id":"2403.08281","title":"Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models","created":"2024-03-13","cited_by_count":7,"area":null},{"id":"2406.07007","title":"Crayon: Customized On-Device LLM via Instant Adapter Blending and Edge-Server Hybrid Inference","created":"2024-06-11","cited_by_count":7,"area":null},{"id":"2305.18952","title":"Exploring the Practicality of Generative Retrieval on Dynamic Corpora","created":"2023-05-27","cited_by_count":6,"area":null},{"id":"2503.02354","title":"CoServe: Efficient Collaboration-of-Experts (CoE) Model Inference with Limited Memory","created":"2025-03-04","cited_by_count":5,"area":null},{"id":"2401.12756","title":"What the Weight?! A Unified Framework for Zero-Shot Knowledge Composition","created":"2024-01-23","cited_by_count":4,"area":null},{"id":"2402.01911","title":"From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers","created":"2024-02-02","cited_by_count":4,"area":null},{"id":"2508.19667","title":"Survey of Specialized Large Language Model","created":"2025-08-27","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":"2307.04052","title":"Learning to Group Auxiliary Datasets for Molecule","created":"2023-07-08","cited_by_count":3,"area":null},{"id":"2403.13112","title":"Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2504.05318","title":"Efficient Multi-Task Learning via Generalist Recommender","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2506.11999","title":"Generative Representational Learning of Foundation Models for Recommendation","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2210.11628","title":"Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?","created":"2022-10-20","cited_by_count":1,"area":null},{"id":"2402.17934","title":"Inducing Generalization across Languages and Tasks using Featurized Low-Rank Mixtures","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2608.02129","title":"PromptPath: Prompt-Adaptive Computational Pathways for In-Context Learning","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.24372","title":"Bridging Adversarial and Collaborative Learning for AI-Generated Image Quality Assessment","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}