{"total":937,"rows":[{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703,"area":null},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512,"area":null},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254,"area":null},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216,"area":null},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103,"area":null},{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906,"area":null},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764,"area":null},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763,"area":null},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727,"area":null},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714,"area":null},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650,"area":null},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649,"area":null},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609,"area":null},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511,"area":null},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492,"area":null},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484,"area":null},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471,"area":null},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415,"area":null},{"id":"2101.11718","title":"BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation","created":"2021-01-27","cited_by_count":412,"area":null},{"id":"2110.02861","title":"8-bit Optimizers via Block-wise Quantization","created":"2021-10-06","cited_by_count":403,"area":null},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366,"area":null},{"id":"2103.00453","title":"Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP","created":"2021-02-28","cited_by_count":337,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2109.05014","title":"An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA","created":"2021-09-10","cited_by_count":301,"area":null},{"id":"2103.01913","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","created":"2021-03-02","cited_by_count":287,"area":null},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287,"area":null},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282,"area":null},{"id":"2112.10668","title":"Few-shot Learning with Multilingual Language Models","created":"2021-12-20","cited_by_count":278,"area":null},{"id":"2309.14316","title":"Physics of Language Models: Part 3.1, Knowledge Storage and Extraction","created":"2023-09-25","cited_by_count":270,"area":null},{"id":"2402.01613","title":"Nomic Embed: Training a Reproducible Long Context Text Embedder","created":"2024-02-02","cited_by_count":265,"area":null},{"id":"2107.02137","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-07-05","cited_by_count":260,"area":null},{"id":"2305.08283","title":"From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models","created":"2023-05-15","cited_by_count":260,"area":null},{"id":"2203.15827","title":"LinkBERT: Pretraining Language Models with Document Links","created":"2022-03-29","cited_by_count":211,"area":null},{"id":"2303.10158","title":"Data-centric Artificial Intelligence: A Survey","created":"2023-03-17","cited_by_count":203,"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":"2311.16863","title":"Power Hungry Processing: Watts Driving the Cost of AI Deployment?","created":"2023-11-28","cited_by_count":191,"area":null},{"id":"2305.13169","title":"A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity","created":"2023-05-22","cited_by_count":182,"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":"2103.11790","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","created":"2021-03-08","cited_by_count":178,"area":null},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178,"area":null},{"id":"2104.06644","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","created":"2021-04-14","cited_by_count":177,"area":null},{"id":"2309.09400","title":"CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages","created":"2023-09-17","cited_by_count":174,"area":null},{"id":"2210.08964","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","created":"2022-09-20","cited_by_count":172,"area":null},{"id":"2210.09338","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","created":"2022-10-17","cited_by_count":156,"area":null},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"area":null},{"id":"2306.12929","title":"Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing","created":"2023-06-22","cited_by_count":151,"area":null},{"id":"2308.12284","title":"D4: Improving LLM Pretraining via Document De-Duplication and Diversification","created":"2023-08-23","cited_by_count":150,"area":null},{"id":"2201.06642","title":"Towards a Cleaner Document-Oriented Multilingual Crawled Corpus","created":"2022-01-17","cited_by_count":143,"area":null},{"id":"2104.04670","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","created":"2021-04-10","cited_by_count":128,"area":null},{"id":"2102.08473","title":"COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining","created":"2021-02-16","cited_by_count":126,"area":null},{"id":"2101.00204","title":"BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla","created":"2021-01-01","cited_by_count":125,"area":null},{"id":"2112.01522","title":"Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks","created":"2021-12-02","cited_by_count":125,"area":null},{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124,"area":null},{"id":"2311.05112","title":"A Survey of Large Language Models in Medicine: Progress, Application, and Challenge","created":"2023-11-09","cited_by_count":124,"area":null},{"id":"2108.01624","title":"Large-Scale Differentially Private BERT","created":"2021-08-03","cited_by_count":118,"area":null},{"id":"2202.08005","title":"Should You Mask 15% in Masked Language Modeling?","created":"2022-02-16","cited_by_count":118,"area":null},{"id":"2211.00083","title":"WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain","created":"2022-10-31","cited_by_count":117,"area":null},{"id":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2308.01907","title":"The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World","created":"2023-08-03","cited_by_count":116,"area":null},{"id":"2402.06925","title":"A Thorough Examination of Decoding Methods in the Era of LLMs","created":"2024-02-10","cited_by_count":114,"area":null},{"id":"2205.12674","title":"Training Language Models with Memory Augmentation","created":"2022-05-25","cited_by_count":113,"area":null},{"id":"2301.07733","title":"Learning-Rate-Free Learning by D-Adaptation","created":"2023-01-18","cited_by_count":113,"area":null},{"id":"2105.06990","title":"BERT Busters: Outlier Dimensions that Disrupt Transformers","created":"2021-05-14","cited_by_count":112,"area":null},{"id":"2212.07525","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","created":"2022-12-14","cited_by_count":110,"area":null},{"id":"2103.11943","title":"BERT: A Review of Applications in Natural Language Processing and Understanding","created":"2021-03-22","cited_by_count":109,"area":null},{"id":"2410.21228","title":"LoRA vs Full Fine-tuning: An Illusion of Equivalence","created":"2024-10-28","cited_by_count":109,"area":null},{"id":"2310.13771","title":"Copyright Violations and Large Language Models","created":"2023-10-20","cited_by_count":108,"area":null},{"id":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106,"area":null},{"id":"2409.16235","title":"EuroLLM: Multilingual Language Models for Europe","created":"2024-09-24","cited_by_count":106,"area":null},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105,"area":null},{"id":"2205.10287","title":"On the SDEs and Scaling Rules for Adaptive Gradient Algorithms","created":"2022-05-20","cited_by_count":104,"area":null},{"id":"2109.03646","title":"Sustainable Modular Debiasing of Language Models","created":"2021-09-08","cited_by_count":100,"area":null},{"id":"2104.07143","title":"An Interpretability Illusion for BERT","created":"2021-04-14","cited_by_count":97,"area":null},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96,"area":null},{"id":"2402.18540","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","created":"2024-02-28","cited_by_count":96,"area":null},{"id":"2201.09405","title":"Improving Chest X-Ray Report Generation by Leveraging Warm Starting","created":"2022-01-24","cited_by_count":95,"area":null},{"id":"2206.02369","title":"Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation","created":"2022-06-06","cited_by_count":94,"area":null},{"id":"2210.01351","title":"Less is More: Task-aware Layer-wise Distillation for Language Model Compression","created":"2022-10-04","cited_by_count":93,"area":null},{"id":"2106.16163","title":"The MultiBERTs: BERT Reproductions for Robustness Analysis","created":"2021-06-30","cited_by_count":92,"area":null},{"id":"2204.08110","title":"Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models","created":"2022-04-17","cited_by_count":92,"area":null},{"id":"2106.03706","title":"A Comprehensive Assessment of Dialog Evaluation Metrics","created":"2021-06-07","cited_by_count":90,"area":null},{"id":"2110.12010","title":"ClimateBert: A Pretrained Language Model for Climate-Related Text","created":"2021-10-22","cited_by_count":90,"area":null},{"id":"2406.02542","title":"Loki: Low-rank Keys for Efficient Sparse Attention","created":"2024-06-04","cited_by_count":89,"area":null},{"id":"2302.13939","title":"SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks","created":"2023-02-27","cited_by_count":88,"area":null},{"id":"2306.09968","title":"ClinicalGPT: Large Language Models Finetuned with Diverse Medical Data and Comprehensive Evaluation","created":"2023-06-16","cited_by_count":88,"area":null},{"id":"2110.05006","title":"Pre-trained Language Models in Biomedical Domain: A Systematic Survey","created":"2021-10-11","cited_by_count":87,"area":null},{"id":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87,"area":null},{"id":"2310.15337","title":"Moral Foundations of Large Language Models","created":"2023-10-23","cited_by_count":85,"area":null},{"id":"2107.00717","title":"SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios","created":"2021-07-01","cited_by_count":84,"area":null},{"id":"2204.02968","title":"Temporal Alignment Networks for Long-term Video","created":"2022-04-06","cited_by_count":84,"area":null},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84,"area":null},{"id":"2109.15290","title":"MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extraction","created":"2021-09-30","cited_by_count":83,"area":null},{"id":"2110.09456","title":"NormFormer: Improved Transformer Pretraining with Extra Normalization","created":"2021-10-18","cited_by_count":83,"area":null},{"id":"2205.09357","title":"Continual Pre-Training Mitigates Forgetting in Language and Vision","created":"2022-05-19","cited_by_count":83,"area":null},{"id":"2303.00980","title":"Learning to Grow Pretrained Models for Efficient Transformer Training","created":"2023-03-02","cited_by_count":83,"area":null},{"id":"2402.02834","title":"Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods","created":"2024-02-05","cited_by_count":82,"area":null},{"id":"2104.07705","title":"How to Train BERT with an Academic Budget","created":"2021-04-15","cited_by_count":80,"area":null}],"next_cursor":"100"}