{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2310.04378","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","created":"2023-10-06","cited_by_count":846},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1606.07792","title":"Wide & Deep Learning for Recommender Systems","created":"2016-06-24","cited_by_count":747},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"id":"2401.02385","title":"TinyLlama: An Open-Source Small Language Model","created":"2024-01-04","cited_by_count":618},{"id":"1708.03888","title":"Large Batch Training of Convolutional Networks","created":"2017-08-13","cited_by_count":535},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"2309.03883","title":"DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models","created":"2023-09-07","cited_by_count":376},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"2101.06840","title":"ZeRO-Offload: Democratizing Billion-Scale Model Training","created":"2021-01-18","cited_by_count":341},{"id":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265},{"id":"2105.11259","title":"PTR: Prompt Tuning with Rules for Text Classification","created":"2021-05-24","cited_by_count":238},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"2307.05695","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","created":"2023-07-11","cited_by_count":204},{"id":"1710.09854","title":"Gradient Sparsification for Communication-Efficient Distributed Optimization","created":"2017-10-26","cited_by_count":201},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180},{"id":"2310.06786","title":"OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text","created":"2023-10-10","cited_by_count":155},{"id":"2302.12246","title":"Active Prompting with Chain-of-Thought for Large Language Models","created":"2023-02-23","cited_by_count":154},{"id":"2302.12822","title":"Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data","created":"2023-02-24","cited_by_count":119},{"id":"2312.12379","title":"Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning","created":"2023-12-19","cited_by_count":106},{"id":"2403.02181","title":"Not All Layers of LLMs Are Necessary During Inference","created":"2024-03-04","cited_by_count":96},{"id":"1401.2753","title":"Stochastic Optimization with Importance Sampling","created":"2014-01-13","cited_by_count":91},{"id":"2201.08531","title":"Black-box Prompt Learning for Pre-trained Language Models","created":"2022-01-21","cited_by_count":70},{"id":"2306.12420","title":"LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models","created":"2023-06-21","cited_by_count":60},{"id":"1706.04983","title":"FreezeOut: Accelerate Training by Progressively Freezing Layers","created":"2017-06-15","cited_by_count":54},{"id":"2102.01386","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","created":"2021-02-02","cited_by_count":48},{"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},{"id":"2311.02265","title":"Not all layers are equally as important: Every Layer Counts BERT","created":"2023-11-03","cited_by_count":21},{"id":"2309.01172","title":"FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs","created":"2023-09-03","cited_by_count":20},{"id":"2402.07011","title":"FedImpro: Measuring and Improving Client Update in Federated Learning","created":"2024-02-10","cited_by_count":15},{"id":"2311.03687","title":"Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models","created":"2023-11-07","cited_by_count":12},{"id":"2401.16720","title":"SmartFRZ: An Efficient Training Framework using Attention-Based Layer Freezing","created":"2024-01-30","cited_by_count":12}],"next_cursor":null}