{"list":"other","total":67,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1704.04368","title":"Get To The Point: Summarization with Pointer-Generator Networks","created":"2017-04-14","cited_by_count":1292},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"1708.00055","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","created":"2017-07-31","cited_by_count":1001},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"2005.00247","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","created":"2020-05-01","cited_by_count":788},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460},{"id":"1807.05118","title":"Tune: A Research Platform for Distributed Model Selection and Training","created":"2018-07-13","cited_by_count":395},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364},{"id":"2303.10512","title":"AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning","created":"2023-03-18","cited_by_count":357},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"2312.03732","title":"A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA","created":"2023-11-28","cited_by_count":243},{"id":"2101.11038","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","created":"2021-01-26","cited_by_count":192},{"id":"2110.07577","title":"UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning","created":"2021-10-14","cited_by_count":162},{"id":"2304.11127","title":"Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance","created":"2023-04-21","cited_by_count":147},{"id":"2005.00770","title":"Exploring and Predicting Transferability across NLP Tasks","created":"2020-05-02","cited_by_count":128},{"id":"2404.19245","title":"HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning","created":"2024-04-30","cited_by_count":123},{"id":"2303.02861","title":"Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning","created":"2023-03-06","cited_by_count":115},{"id":"2309.14859","title":"Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation","created":"2023-09-26","cited_by_count":109},{"id":"2006.04096","title":"Robust Learning Through Cross-Task Consistency","created":"2020-06-07","cited_by_count":105},{"id":"2311.11696","title":"Sparse Low-rank Adaptation of Pre-trained Language Models","created":"2023-11-20","cited_by_count":96},{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82},{"id":"2203.00759","title":"HyperPrompt: Prompt-based Task-Conditioning of Transformers","created":"2022-03-01","cited_by_count":67},{"id":"2305.03937","title":"Residual Prompt Tuning: Improving Prompt Tuning with Residual Reparameterization","created":"2023-05-06","cited_by_count":64},{"id":"2506.06105","title":"Text-to-LoRA: Instant Transformer Adaption","created":"2025-06-06","cited_by_count":58},{"id":"1801.06146","title":"Universal Language Model Fine-tuning for Text Classification","created":"2018-01-18","cited_by_count":52},{"id":"2211.11720","title":"Multitask Vision-Language Prompt Tuning","created":"2022-11-21","cited_by_count":51},{"id":"2312.08636","title":"MmAP : Multi-modal Alignment Prompt for Cross-domain Multi-task Learning","created":"2023-12-14","cited_by_count":41},{"id":"2311.11501","title":"MultiLoRA: Democratizing LoRA for Better Multi-Task Learning","created":"2023-11-20","cited_by_count":32},{"id":"2304.08612","title":"Bridging Discrete and Backpropagation: Straight-Through and Beyond","created":"2023-04-17","cited_by_count":31},{"id":"2206.08927","title":"DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning","created":"2022-06-17","cited_by_count":25},{"id":"2310.12100","title":"Non-Intrusive Adaptation: Input-Centric Parameter-efficient Fine-Tuning for Versatile Multimodal Modeling","created":"2023-10-18","cited_by_count":20},{"id":"2410.09437","title":"MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning","created":"2024-10-12","cited_by_count":17},{"id":"2501.06252","title":"Transformer-Squared: Self-adaptive LLMs","created":"2025-01-09","cited_by_count":16},{"id":"2204.02725","title":"Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning","created":"2022-04-06","cited_by_count":10},{"id":"2312.03248","title":"Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning","created":"2023-12-06","cited_by_count":8},{"id":"2407.01411","title":"HyperLoader: Integrating Hypernetwork-Based LoRA and Adapter Layers into Multi-Task Transformers for Sequence Labelling","created":"2024-07-01","cited_by_count":6},{"id":"2506.13674","title":"PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention","created":"2025-06-16","cited_by_count":4}],"next_cursor":null}