# NeurIPS Published articles for NeurIPS. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## AWS Trainium Frontier competition: Co-design models and kernels on purpose-built AI chips DevFeed: [AWS Trainium Frontier competition: Co-design models and kernels on purpose-built AI chips]() Original publisher: [Read original article]() Author: Louise Ping; John Gray; Emily Webber; Josh Longenecker Published: 2026-08-10T20:23:04Z Content type: article Language: en Sources: [Amazon Science homepage]() Topics: [AI Chat]() Tags: [aws-trainium](), [chip-design](), [hardware](), [kernels](), [language-models](), [machine-learning](), [model-architecture](), [neurips](), [performance](), [training]() ### AI overview AWS Trainium Frontier is a competition for training language models from scratch on Trainium while co-designing architectures, optimizers, training loops, and optional custom kernels under fixed compute and time budgets. ### Source excerpt A competition with a finalist ceremony during NeurIPS 2026, challenging researchers to train language models from scratch on Trainium, exploring what optimal architectures look like when the hardware changes. ## Introducing GIST: The next stage in smart sampling DevFeed: [Introducing GIST: The next stage in smart sampling]() Original publisher: [Read original article]() Published: 2026-01-23T17:46:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Algorithms](), [Algorithms & Theory](), [datasets](), [data](), [Machine Learning & Artificial Intelligence](), [Algorithm](), [Google](), [NeurIPS]() Tags: [algorithms](), [algorithms-theory](), [classification](), [computer-vision](), [data](), [data-mining-modeling](), [datasets](), [diversity](), [embedding](), [google](), [language-models](), [large-language-models-llms](), [machine-intelligence](), [machine-learning](), [neurips](), [points](), [research](), [systems](), [training](), [vision]() ### AI overview Google Research introduces GIST, an algorithm for selecting a high-quality subset of data for model training. It balances diversity, which reduces redundancy, with utility, which favors relevant and informative data, and provides a mathematical guarantee about solution quality. ### Source excerpt Algorithms & Theory ## Highlights of Booking.com's publication in 2025 DevFeed: [Highlights of Booking.com's publication in 2025]() Original publisher: [Read original article]() Author: Yang Yang Published: 2026-01-20T09:20:13Z Content type: article Language: en Sources: [Booking.com Data Science]() Topics: [Machine learning](), [Artificial Intelligence](), [Natural language processing](), [Language models](), [Fine-tuning](), [recommendation systems](), [Optimization](), [Compression](), [Inference]() Tags: [2025](), [ai](), [booking](), [compression](), [data-science](), [fine-tuning](), [inference](), [language-models](), [latency](), [neurips](), [nlp](), [optimization](), [publication]() ### AI overview Booking.com highlights its 2025 machine learning publications, including papers accepted at major conferences and research on applying Medusa speculative decoding and knowledge distillation to travel-related language model tasks. ### Source excerpt At Booking.com, our mission is to make experiencing the world easier for everyone. We are committed to investing in cutting-edge technology that removes the barriers to travel, enabling seamless connections between millions of travelers and unforgettable experiences, diverse transportation options, and exceptional accommodations. The intersection of academic rigor and industry application is where true transformation happens. In 2025, our ML community bridged this gap more effectively than ever, contributing vital new insights to the global scientific community. With 8 out of 13 papers accepted at premier conferences -- including NeurIPS, SIGIR, KDD, and ACL -- our colleagues have demonstrated world-class expertise in AI, NLP, recommendation systems, uplift modeling, etc. These aren't just theoretical wins; they are the engines of innovation that allow us to push technological boundaries, ensuring our platform remains the most sophisticated and intuitive guide in the ever-evolving travel industry. Below, we highlight some of the key achievements and insights from these groundbreaking works. Speed Without Sacrifice: Fine-Tuning Language Models with Medusa and Knowledge Distillation in Travel Applications By Daniel Zagyva, Emmanouil Stergiadis, Laurens Van Der Maas, Aleksandra Dokic, Eran Fainman, Ilya Gusev, Moran Beladev Best paper award of 2025 ACL Industry Track https://aclanthology.org/2025.acl-industry.48/ In high-stakes industrial NLP applications, balancing generation quality with speed and efficiency presents significant challenges. We address them by investigating two complementary optimization approaches: Medusa for speculative decoding and knowledge distillation (KD) for model compression. We demonstrate the practical application of these techniques in real-world travel domain tasks, including trip planning, smart filters, and generating accommodation descriptions. We introduce modifications to the Medusa implementation, starting with base pre-trained models ## From Waveforms to Wisdom: The New Benchmark for Auditory Intelligence DevFeed: [From Waveforms to Wisdom: The New Benchmark for Auditory Intelligence]() Original publisher: [Read original article]() Published: 2025-12-03T22:47:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Benchmark](), [Machine Intelligence](), [datasets](), [multimodal](), [hugging face](), [Open Source](), [Google](), [NeurIPS]() Tags: [2025](), [ai](), [benchmark](), [classification](), [data](), [datasets](), [embedding](), [google](), [hugging-face](), [machine-intelligence](), [multimodal](), [neurips](), [open-source](), [retrieval](), [sound-accoustics](), [speech-processing]() ### AI overview Google Research introduces the Massive Sound Embedding Benchmark (MSEB), an open-source benchmark for evaluating machine sound intelligence across eight capabilities, including transcription, classification, retrieval, reasoning, segmentation, clustering, reranking, and reconstruction. It also includes the Simple Voice Questions dataset, with 177,352 spoken queries across 26 locales and 17 languages, available on Hugging Face. ### Source excerpt Machine Intelligence ## Introducing Nested Learning: A new ML paradigm for continual learning DevFeed: [Introducing Nested Learning: A new ML paradigm for continual learning]() Original publisher: [Read original article]() Published: 2025-11-07T17:37:22Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Machine Learning & Artificial Intelligence](), [Optimization](), [Network architectures](), [Neural Network](), [LLMs](), [Google](), [Algorithms & Theory]() Tags: [algorithms-theory](), [architectures](), [generative-ai](), [google](), [large-language-models-llms](), [machine-intelligence](), [machine-learning](), [neurips](), [optimization](), [research]() ### AI overview Google Research introduces Nested Learning, a machine learning approach for continual learning that represents a model as interconnected, nested optimization problems. The approach aims to reduce catastrophic forgetting by jointly treating model architecture and training rules as multiple optimization levels with distinct information flows and update rates. ### Source excerpt Algorithms & Theory ## Announcing NeurIPS 2025 E2LM Competition: Early Training Evaluation of Language Models DevFeed: [Announcing NeurIPS 2025 E2LM Competition: Early Training Evaluation of Language Models]() Original publisher: [Read original article]() Author: Mouadh Yagoubi; Yasser Dahou; Billel Mokeddem; Younes B; Phúc Lê Khắc; Basma Boussaha; Ralami; Jingwei Zuo; Mughaira Published: 2025-07-04T12:25:00Z Content type: news Language: en Sources: [Hugging Face - Blog]() Topics: [LLM evaluation / benchmarking](), [LLMs](), [hugging face](), [.NET Conf]() Tags: [2025](), [architectures](), [benchmarks](), [blog](), [competition](), [evaluation](), [google](), [hugging-face](), [language-models](), [models](), [neurips](), [ranking](), [technology](), [tokens](), [training](), [validation](), [verification]() ### AI overview The article announces the NeurIPS 2025 E2LM Competition, which seeks new benchmarks for evaluating early-stage training of Large Language Models on scientific knowledge. Participants will submit solutions based on the lm-evaluation-harness library, with submissions scored for signal quality, ranking consistency, and alignment with scientific knowledge. ### Source excerpt A Blog post by Technology Innovation Institute on Hugging Face ## NeurIPS 2023: Our Favorite Papers on LLMs, Statistical Learning, and More DevFeed: [NeurIPS 2023: Our Favorite Papers on LLMs, Statistical Learning, and More]() Original publisher: [Read original article]() Author: Emily Majewski Published: 2024-03-21T19:52:06Z Content type: article Language: en Sources: [Two Sigma Engineering]() Topics: [NeurIPS](), [machine learning research](), [LLMs](), [LLM evaluation / benchmarking](), [Machine learning]() Tags: [evaluation](), [llms](), [machine-learning-research](), [neurips](), [papers]() ### AI overview Two Sigma reviews selected papers and presentations from NeurIPS 2023, with particular attention to large language models and statistical learning. It discusses research arguing that some apparent emergent abilities in LLMs may result from nonlinear metrics, limited evaluation resolution, and insufficient sampling. ### Source excerpt The post NeurIPS 2023: Our Favorite Papers on LLMs, Statistical Learning, and More appeared first on Two Sigma. ## Cappy: Outperforming and boosting large multi-task language models with a small scorer DevFeed: [Cappy: Outperforming and boosting large multi-task language models with a small scorer]() Original publisher: [Read original article]() Author: Google AI (noreply@blogger.com) Published: 2024-03-14T19:38:00Z Content type: article Language: en Sources: [Google Research]() Topics: [Large Language Model](), [Natural language processing](), [data](), [Google]() Tags: [google](), [language](), [language-models](), [large-language-models](), [machine-learning](), [model](), [models](), [natural-language-processing](), [neurips](), [software](), [training-data]() ### AI overview This Google Research article introduces the motivation for Cappy, a small scorer intended to help adapt and improve large multi-task language models. It describes how instruction-following LLMs generalize across tasks, while noting that their size creates substantial computational, memory, storage, and adaptation challenges. ### Source excerpt Posted by Yun Zhu and Lijuan Liu, Software Engineers, Google Research Large language model (LLM) advancements have led to a new paradigm that unifies various natural language processing (NLP) tasks within an instruction-following framework. This paradigm is exemplified by recent multi-task LLMs, such as T0, FLAN, and OPT-IML. First, multi-task data is gathered with each task following a task-specific template, where each labeled example is converted into an instruction (e.g., "Put the concepts together to form a sentence: ski, mountain, skier") paired with a corresponding response (e.g., "Skier skis down the mountain"). These instruction-response pairs are used to train the LLM, resulting in a conditional generation model that takes an instruction as input and generates a response. Moreover, multi-task LLMs have exhibited remarkable task-wise generalization capabilities as they can address unseen tasks by understanding and solving brand-new instructions. The demonstration of the instruction-following pre-training of multi-task LLMs, e.g., FLAN. Pre-training tasks under this paradigm improves the performance for unseen tasks. Due to the complexity of understanding and solving various tasks solely using instructions, the size of multi-task LLMs typically spans from several billion parameters to hundreds of billions (e.g., FLAN-11B, T0-11B and OPT-IML-175B). As a result, operating such sizable models poses significant challenges because they demand considerable computational power and impose substantial requirements on the memory capacities of GPUs and TPUs, making their training and inference expensive and inefficient. Extensive storage is required to maintain a unique LLM copy for each downstream task. Moreover, the most powerful multi-task LLMs (e.g., FLAN-PaLM-540B) are closed-sourced, making them impossible to be adapted. However, in practical applications, harnessing a single multi-task LLM to manage all conceivable tasks in a zero-shot manner remains difficult, ## Grading Complex Interactive Coding Programs with Reinforcement Learning DevFeed: [Grading Complex Interactive Coding Programs with Reinforcement Learning]() Original publisher: [Read original article]() Author: A Href; Allen Nie; Emma Brunskill; Chris Piech Published: 2022-03-28T07:00:00Z Content type: article Language: en Sources: [The Stanford AI Lab Blog]() Topics: [rlvr](), [Code Challenge](), [Artificial Intelligence](), [Programming](), [NeurIPS](), [browser]() Tags: [agents](), [algorithms](), [browser](), [coding](), [courses](), [games](), [machine-learning](), [neurips](), [programming](), [reinforcement-learning](), [speed]() ### AI overview This article presents the Play to Grade Challenge, which applies reinforcement-learning methods for game-playing AI agents to the automated grading of complex interactive coding assignments. It explains why games and interactive applications are difficult to evaluate automatically and describes the challenge introduced in a NeurIPS 2021 paper. ### Source excerpt [Summary] tl;dr: A tremendous amount of effort has been poured into training AI algorithms to competitively play games that computers have traditionally had trouble with, such as the retro games published by Atari, Go, DotA, and StarCraft II. The practical machine learning knowledge accumulated in developing these algorithms has paved the way for people to now routinely train game-playing AI agents for many games. Following this line of work, we focus on a specific category of games - those developed by students as part of a programming assignment. Can the same algorithms that master Atari games help us grade these game assignments? In our recent NeurIPS 2021 paper, we illustrate the challenges in treating interactive coding assignment grading as game playing and introduce the Play to Grade Challenge. Introduction Massive Online Coding Education has reached striking success over the past decade. Fast internet speed, improved UI design, code editors that are embedded in a browser window allow educational platforms such as Code.org to build a diverse set of courses tailored towards students of different coding experiences and interest levels (for example, Code.org offers "Star War-themed coding challenge," and "Elsa/Frozen themed for-loop writing"). As a non-profit organization, Code.org claims to have reached over 60 million learners across the world 1. Such organizations typically provide a variety of carefully constructed teaching materials such as videos and programming challenges. A challenge faced by these platforms is that of grading assignments. It is well known that grading is critical to student learning 2, in part because it motivates students to complete their assignments. Sometimes manual grading can be feasible in small settings, or automated grading used in simple settings such as when assignments are multiple choice or adopt a fill-in-the-blink modular coding structure. Unfortunately, many of the most exciting assignments, such as developing games or i ## BanditPAM: Almost Linear-Time k-medoids Clustering via Multi-Armed Bandits DevFeed: [BanditPAM: Almost Linear-Time k-medoids Clustering via Multi-Armed Bandits]() Original publisher: [Read original article]() Author: A Href; Mo Tiwari Published: 2021-12-17T08:00:00Z Content type: article Language: en Sources: [The Stanford AI Lab Blog]() Topics: [AI, ML & Data Engineering](), [C++]() Tags: [algorithms](), [c-plus-plus](), [code](), [complexity](), [neurips](), [speed]() ### AI overview BanditPAM is a publicly available k-medoids clustering implementation that reduces the stated runtime from O(n²) to O(n log n). It is pip-installable, written in C++, and designed to resemble the sklearn.cluster.KMeans interface. ### Source excerpt TL;DR Want something better than \(k\)-means? Our state-of-the-art \(k\)-medoids algorithm from NeurIPS, BanditPAM, is now publicly available! \(\texttt{pip install banditpam}\) and you're good to go! Like the \(k\)-means problem, the \(k\)-medoids problem is a clustering problem in which our objective is to partition a dataset into disjoint subsets. In \(k\)-medoids, however, we require that the cluster centers must be actual datapoints, which permits greater interpretability of the cluster centers. \(k\)-medoids also works better with arbitrary distance metrics, so your clustering can be more robust to outliers if you're using metrics like \(L_1\). Despite these advantages, most people don't use \(k\)-medoids because prior algorithms were too slow. In our NeurIPS paper, BanditPAM, we sped up the best known algorithm from \(O(n^2)\) to \(O(n\text{log}n)\). We've released our implementation, which is pip-installable. It's written in C++ for speed and supports parallelization and intelligent caching, at no extra complexity to end users. Its interface also matches the \(\texttt{sklearn.cluster.KMeans}\) interface, so minimal changes are necessary to existing code. Useful Links: 3-minute video summary PyPI Github Repository Full Paper \(k\)-means vs. \(k\)-medoids If you're an ML practitioner, you're probably familiar with the \(k\)-means problem. In fact, you may know some of the common algorithms for the \(k\)-means problem. You're much less likely, however, familiar with the \(k\)-medoids problem. The \(k\)-medoids problem is a clustering problem similar to \(k\)-means. Given a dataset, we want to partition our dataset into subsets where the points in each cluster are closer to a single cluster center than all other \(k-1\) cluster centers. Unlike in \(k\)-means, however, the \(k\)-medoids problem requires cluster centers to be actual datapoints. Figure 1: The \(k\)-medoids solution (left) forces the cluster centers to be actual datapoints. This solution is often di ## Stanford AI Lab Papers and Talks at NeurIPS 2021 DevFeed: [Stanford AI Lab Papers and Talks at NeurIPS 2021]() Original publisher: [Read original article]() Author: Compiled by Drew A. Hudson Published: 2021-12-06T08:00:00Z Content type: article Language: en Sources: [The Stanford AI Lab Blog]() Topics: [NeurIPS](), [Artificial Intelligence](), [Reverse Engineering](), [data](), [Reinforcement learning]() Tags: [ai](), [generative](), [imitation](), [learning](), [models](), [neural-networks](), [neurips](), [reinforcement-learning](), [reverse-engineering](), [transformers]() ### AI overview Stanford AI Lab presents its research at NeurIPS 2021, including work on generative models, recurrent and transformer-based architectures, state-space models, emergent communication, reinforcement learning, imitation learning, and neural coding. ### Source excerpt The thirty-fifth Conference on Neural Information Processing Systems (NeurIPS) 2021 is being hosted virtually from Dec 6th - 14th. We're excited to share all the work from SAIL that's being presented at the main conference, at the Datasets and Benchmarks track and the various workshops, and you'll find links to papers, videos and blogs below. Some of the members in our SAIL community also serve as co-organizers of several exciting workshops that will take place on Dec 13-14, so we hope you will check them out! Feel free to reach out to the contact authors and the workshop organizers directly to learn more about the work that's happening at Stanford! Main Conference Improving Compositionality of Neural Networks by Decoding Representations to Inputs Authors: Mike Wu, Noah Goodman, Stefano Ermon Contact: wumike@stanford.edu Links: Paper Keywords: generative models, compositionality, decoder Reverse engineering recurrent neural networks with Jacobian switching linear dynamical systems Authors: Jimmy T.H. Smith, Scott W. Linderman, David Sussillo Contact: jsmith14@stanford.edu Links: Paper | Website Keywords: recurrent neural networks, switching linear dynamical systems, interpretability, fixed points Compositional Transformers for Scene Generation Authors: Drew A. Hudson, C. Lawrence Zitnick Contact: dorarad@cs.stanford.edu Links: Paper | Github Keywords: GANs, transformers, compositionality, scene synthesis Combining Recurrent, Convolutional, and Continuous-time Models with Linear State Space Layers Authors: Albert Gu, Isys Johnson, Karan Goel, Khaled Saab, Tri Dao, Atri Rudra, Chris Ré Contact: albertgu@stanford.edu Links: Paper Keywords: recurrent neural networks, rnn, continuous models, state space, long range dependencies, sequence modeling Emergent Communication of Generalizations Authors: Jesse Mu, Noah Goodman Contact: muj@stanford.edu Links: Paper | Video Keywords: emergent communication, multi-agent communication, language grounding, compositionality Deep Lear ## NIPS 2017 Summary DevFeed: [NIPS 2017 Summary]() Original publisher: [Read original article]() Published: 2017-12-11T00:00:00Z Content type: article Language: en Sources: [Alex Korbonits]() Topics: [NeurIPS](), [AI Research](), [Deep learning](), [Deep neural networks](), [Reinforcement learning]() Tags: [ai-research](), [deep-learning](), [fairness](), [machine-learning](), [model](), [model-interpretability](), [neurips](), [open-source](), [papers](), [reinforcement-learning](), [research]() ### AI overview A summary of key themes from NIPS 2017, including rapid progress in Bayesian deep learning, growing attention to model interpretability, bias, and fairness, the need for more theory in deep learning, advances in deep reinforcement learning, and ongoing questions about GANs. ### Source excerpt Key takeaways from NeurIPS 2017: Bayesian deep learning, model interpretability, fairness, and the state of AI research. ## Deep Probabilistic Modelling with Gaussian Processes #NIPS2017 DevFeed: [Deep Probabilistic Modelling with Gaussian Processes #NIPS2017]() Original publisher: [Read original article]() Published: 2017-12-04T12:00:00Z Content type: tutorial Language: en Sources: [Alex Korbonits]() Topics: [Tutorial](), [VAE](), [Machine learning](), [Deep learning](), [Neural Network](), [NeurIPS]() Tags: [analysis](), [bias](), [conference](), [data](), [deep-learning](), [gaussian](), [inference](), [modelling](), [neural-network](), [neurips](), [probabilistic](), [research](), [supervised-learning](), [theory](), [tutorial](), [unsupervised-learning](), [videos]() ### AI overview Lecture notes from a NeurIPS 2017 tutorial introduce deep probabilistic modelling with Gaussian processes, covering probabilistic neural networks, uncertainty, graphical models, and the computational challenge of inference. ### Source excerpt Lecture notes from Neil Lawrence's NIPS 2017 tutorial on deep probabilistic modelling with Gaussian processes -- from GPs to deep GPs and variational inference. ## Notes from NIPS 2017 on geometric deep learning, GAN theory, reinforcement learning, fairness, and Bayesian deep learning DevFeed: [Notes from NIPS 2017 on geometric deep learning, GAN theory, reinforcement learning, fairness, and Bayesian deep learning]() Original publisher: [Read original article]() Published: 2017-12-04T12:00:00Z Content type: opinion Language: en Sources: [Alex Korbonits]() Topics: [NeurIPS](), [Deep learning](), [Machine learning](), [Graphs](), [Reinforcement learning]() Tags: [3d](), [bias](), [deep-learning](), [fairness](), [graphs](), [ml](), [neurips](), [reinforcement-learning]() ### AI overview Personal notes from attending NIPS 2017 cover geometric deep learning on manifolds and graphs, Bayesian deep learning, fairness and bias, theory, deep reinforcement learning, and GANs. The article also reflects on how those research themes developed over the following years. ### Source excerpt Notes from NIPS 2017 -- covering geometric deep learning, GAN theory, reinforcement learning, fairness in ML, Bayesian deep learning, and more. ## A Primer on Optimal Transport #NIPS2017 DevFeed: [A Primer on Optimal Transport #NIPS2017]() Original publisher: [Read original article]() Published: 2017-12-04T08:00:00Z Content type: tutorial Language: en Sources: [Alex Korbonits]() Topics: [Tutorial](), [Machine learning](), [Algorithms](), [Deep learning](), [NeurIPS]() Tags: [2017](), [algorithm](), [applications](), [conference](), [deep-learning](), [ml](), [neurips](), [tutorial]() ### AI overview Lecture notes on optimal transport covering the Monge problem, Kantorovich relaxation, Wasserstein distance, Sinkhorn's algorithm, and applications in generative models and machine learning. ### Source excerpt Lecture notes from Marco Cuturi and Justin Solomon's NIPS 2017 tutorial on optimal transport -- Wasserstein distances, Sinkhorn's algorithm, and applications in generative models and ML.