Hit enter to search or ESC to close

Category: Best Paper

Paper Digest: 100 Must-Read Natural Language Processing Papers of the Past 10 Years (2016-2025)

Natural language processing has been rebuilt from the ground up in the past decade. Subword units made neural machine translation practical. ELMo, and then BERT, made pretrained language models the default starting point for almost every task. BART, Sentence-BERT, and Dense Passage Retrieval extended pretraining to generation, embeddings, and search. Prefix-Tuning, Self-Instruct, and TruthfulQA marked the shift to large language models (LLMs) and generative AI. The newest work, such as test-time scaling in s1, is about getting those models to reason. Keeping up is hard: ACL and EMNLP alone now publish thousands of papers a year. This reading list is a starting point: 100 of the most influential NLP and deep learning papers from 2016 to 2025, the work the research community has cited and built on most.

How the papers were selected

The papers were selected by citation count from the three flagship NLP and computational linguistics conferences: ACL, EMNLP, and NAACL. For each year from 2016 to 2025, we took the ten most-cited papers across that year's conferences. Selecting by year keeps recent work from being crowded out by older papers that have simply had more time to collect citations. NAACL is not held every year, and there was no edition in 2017, 2020, or 2023, so those years draw from ACL and EMNLP only.

The list is ordered newest year first. Read from the bottom up, it doubles as a short history of how the field moved:

  • neural machine translation, sequence labeling, and large reading-comprehension datasets
  • pretrained language models
  • prompting and parameter-efficient tuning
  • instruction tuning and evaluating large language models
  • today's reasoning and agentic models

A note on scope: this list reflects our selection criteria, not a definitive list of the best NLP papers. There may well be better or more important papers elsewhere. Some landmark NLP work appeared outside these three conferences. The Transformer and GPT-3 were published at NeurIPS, T5 in JMLR, and many influential LLM technical reports exist only on arXiv. Citation counts also favor popular topics and lag behind the newest work. Treat the list as a well-grounded map of the field rather than the final word. For the full year-by-year lists, see the Most Influential ACL, EMNLP, and NAACL papers pages. Lists for other venues are on the Best Paper Digest page.

Keeping up beyond this list

If you work across fields, the companion lists follow the same method: 100 must-read computer vision papers of the past 10 years (CVPR, ICCV, ECCV) and 100 must-read machine learning papers of the past 10 years (NeurIPS, ICML, ICLR).

A citation-based list looks backward. It tells you what mattered, not what is emerging this month. Every paper on Paper Digest links to related papers, patents, grants, and experts, so you can explore the research around any of the work below. You can also run a literature review on a specific topic. If you would like new NLP and LLM papers matched to your interests each morning, you can sign up and set up a daily digest.

Paper Digest: 100 Must-Read Machine Learning Papers of the Past 10 Years (2016-2025)

Machine learning has changed faster in the past decade than in any period before it. The Transformer replaced recurrence with attention. GPT-3 showed what scale alone could do. Diffusion models became the standard way to generate images. InstructGPT, LoRA, and DPO made it practical to adapt and align large language models. PyTorch and AdamW became default tools in nearly every lab. Keeping up is hard: NeurIPS alone now accepts thousands of papers a year. This reading list is a starting point: 100 machine learning papers from 2016 to 2025 that the research community has built on most.

How the papers were selected

The papers were selected by citation count from the three flagship machine learning conferences: NeurIPS, ICML, and ICLR. For each year from 2016 to 2025, we took the ten most-cited papers across that year's conferences. Selecting by year keeps recent work from being crowded out by older papers that have simply had more time to collect citations. Our ICLR data begins in 2018, so the 2016 and 2017 picks come from NeurIPS and ICML. These venues cover the whole field, so the list includes plenty of vision, language, and speech papers alongside core machine learning.

The list is ordered newest year first. Read from the bottom up, it doubles as a short history of how the field moved:

  • GANs, deep reinforcement learning, and graph neural networks
  • transformers and large-scale pretraining
  • self-supervised learning and diffusion models
  • today's work on aligning large language models and teaching them to reason

A note on scope: this list reflects our selection criteria, not a definitive ranking of the best machine learning research. There may well be better or more important papers elsewhere. Some landmark work appeared outside these three conferences: BERT at NAACL, AlphaFold in Nature, and many influential LLM technical reports, such as LLaMA, only on arXiv. Citation counts also favor popular topics and lag behind the newest work. Treat the list as a well-grounded map of the field rather than the final word. For the full year-by-year lists, see the Most Influential NeurIPS, ICML, and ICLR papers pages. Lists for other venues are on the Best Paper Digest page.

Keeping up beyond this list

If you work across fields, the companion lists follow the same method: 100 must-read computer vision papers of the past 10 years (CVPR, ICCV, ECCV) and 100 must-read natural language processing papers of the past 10 years (ACL, EMNLP, NAACL).

A citation-based list looks backward. It tells you what mattered, not what is emerging this month. Every paper on Paper Digest links to related papers, patents, grants, and experts, so you can explore the research around any of the work below. You can also run a literature review on a specific topic. If you would like new machine learning papers matched to your interests each morning, you can sign up and set up a daily digest.

Paper Digest: 100 Must-Read Computer Vision Papers of the Past 10 Years (2016-2025)

Computer vision has changed more in the past decade than in the thirty years before it. ResNet made very deep neural networks trainable and set a new bar for image recognition. Mask R-CNN and DETR reshaped object detection and image segmentation. Swin Transformer brought transformers into mainstream vision. Latent diffusion models, the basis of Stable Diffusion, made high-quality image generation practical. Segment Anything and LLaVA-style models pushed the field toward general-purpose vision foundation models and multimodal AI. Keeping up is hard: CVPR alone now accepts thousands of papers a year. This reading list is a starting point: 100 of the most influential computer vision and deep learning papers from 2016 to 2025, the work the research community has cited and built on most.

How the papers were selected

The papers were selected by citation count from the three flagship computer vision conferences: CVPR, ICCV, and ECCV. For each year from 2016 to 2025, we took the ten most-cited papers across that year's conferences. Selecting by year keeps recent work from being crowded out by older papers that have simply had more time to collect citations. Each year's pool is CVPR plus either ICCV (held in odd years) or ECCV (held in even years). Our ECCV data begins in 2018, so the 2016 picks come from CVPR only.

The list is ordered newest year first. Read from the bottom up, it doubles as a short history of how the field moved:

  • convolutional neural networks (CNNs), object detection, and segmentation
  • GANs and self-supervised learning
  • vision transformers
  • neural rendering with NeRF and Gaussian splatting, and diffusion models
  • today's multimodal reasoning models

A note on scope: this list reflects our selection criteria, not a definitive list of the best computer vision papers. There may well be better or more important papers elsewhere. Several landmark vision papers appeared at machine learning venues rather than vision conferences, including the Vision Transformer (ViT) at ICLR and CLIP at ICML. Others were published in journals such as TPAMI and IJCV, or exist only on arXiv. Citation counts also favor popular topics and lag behind the newest work. Treat the list as a well-grounded map of the field rather than the final word. For the full year-by-year lists, see the Most Influential CVPR, ICCV, and ECCV papers pages. Lists for other venues are on the Best Paper Digest page.

Keeping up beyond this list

If you work across fields, the companion lists follow the same method: 100 must-read natural language processing papers of the past 10 years (ACL, EMNLP, NAACL) and 100 must-read machine learning papers of the past 10 years (NeurIPS, ICML, ICLR).

A citation-based list looks backward. It tells you what mattered, not what is emerging this month. Every paper on Paper Digest links to related papers, patents, grants, and experts, so you can explore the research around any of the work below. You can also run a literature review on a specific topic. If you would like new computer vision and multimodal AI papers matched to your interests each morning, you can sign up and set up a daily digest.

Most Influential ArXiv (Computation and Language) Papers (2026-04 Version)

The field of Computation and Language in arXiv covers natural language processing. Roughly it includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area. Paper Digest Team analyzes all papers published in this field in the past years, and presents up to 30 most influential papers for each year. This ranking list is automatically constructed based upon citations from both research papers and granted patents, and will be frequently updated to reflect the most recent changes. To find the latest version of this list or the most influential papers from other conferences/journals, please visit Best Paper Digest page. Note: the most influential papers may or may not include the papers that won the best paper awards. (Version: 2026-04).

Most Influential ArXiv (Materials Science) Papers (2026-04 Version)

The field of Materials Science in arXiv covers Techniques, synthesis, characterization, structure; Structural phase transitions, mechanical properties, phonons; Defects, adsorbates, interfaces. Paper Digest Team analyzes all papers published in this field in the past years, and presents up to 30 most influential papers for each year. This ranking list is automatically constructed based upon citations from both research papers and granted patents, and will be frequently updated to reflect the most recent changes. To find the latest version of this list or the most influential papers from other conferences/journals, please visit Best Paper Digest page. Note: the most influential papers may or may not include the papers that won the best paper awards. (Version: 2026-04).

Most Influential ArXiv (Human-Computer Interaction) Papers (2026-04 Version)

The field of Human-Computer Interaction in arXiv covers human factors, user interfaces, and collaborative computing. Roughly it includes material in ACM Subject Classes H.1.2 and all of H.5, except for H.5.1, which is more likely to have Multimedia as the primary subject area. Paper Digest Team analyzes all papers published in this field in the past years, and presents up to 30 most influential papers for each year. This ranking list is automatically constructed based upon citations from both research papers and granted patents, and will be frequently updated to reflect the most recent changes. To find the latest version of this list or the most influential papers from other conferences/journals, please visit Best Paper Digest page. Note: the most influential papers may or may not include the papers that won the best paper awards. (Version: 2026-04).

Most Influential ArXiv (Software Engineering) Papers (2026-04 Version)

The field of Software Engineering in arXiv covers design tools, software metrics, testing and debugging, programming environments, etc. Roughly it includes material in all of ACM Subject Classes D.2, except that D.2.4 (program verification) should probably have Logics in Computer Science as the primary subject area. Paper Digest Team analyzes all papers published in this field in the past years, and presents up to 30 most influential papers for each year. This ranking list is automatically constructed based upon citations from both research papers and granted patents, and will be frequently updated to reflect the most recent changes. To find the latest version of this list or the most influential papers from other conferences/journals, please visit Best Paper Digest page. Note: the most influential papers may or may not include the papers that won the best paper awards. (Version: 2026-04).

Most Influential ArXiv (Statistics Methodology) Papers (2026-04 Version)

The field of Statistics Methodology in arXiv covers Design, Surveys, Model Selection, Multiple Testing, Multivariate Methods, Signal and Image Processing, Time Series, Smoothing, Spatial Statistics, Survival Analysis, Nonparametric and Semiparametric Methods. Paper Digest Team analyzes all papers published in this field in the past years, and presents up to 30 most influential papers for each year. This ranking list is automatically constructed based upon citations from both research papers and granted patents, and will be frequently updated to reflect the most recent changes. To find the latest version of this list or the most influential papers from other conferences/journals, please visit Best Paper Digest page. Note: the most influential papers may or may not include the papers that won the best paper awards. (Version: 2026-04).

Most Influential ArXiv (General Relativity and Quantum Cosmology) Papers (2026-04 Version)

The field of General Relativity and Quantum Cosmology in arXiv covers General Relativity and Quantum Cosmology Areas of gravitational physics, including experiments and observations related to the detection and interpretation of gravitational waves, experimental tests of gravitational theories, computational general relativity, relativistic astrophysics, solutions to Einstein's equations and their properties, alternative theories of gravity, classical and quantum cosmology, and quantum gravity. Paper Digest Team analyzes all papers published in this field in the past years, and presents up to 30 most influential papers for each year. This ranking list is automatically constructed based upon citations from both research papers and granted patents, and will be frequently updated to reflect the most recent changes. To find the latest version of this list or the most influential papers from other conferences/journals, please visit Best Paper Digest page. Note: the most influential papers may or may not include the papers that won the best paper awards. (Version: 2026-04).

Most Influential ArXiv (Quantum Physics) Papers (2026-04 Version)

The field of Quantum Physics in arXiv covers Quantum Physics. Paper Digest Team analyzes all papers published in this field in the past years, and presents up to 30 most influential papers for each year. This ranking list is automatically constructed based upon citations from both research papers and granted patents, and will be frequently updated to reflect the most recent changes. To find the latest version of this list or the most influential papers from other conferences/journals, please visit Best Paper Digest page. Note: the most influential papers may or may not include the papers that won the best paper awards. (Version: 2026-04).