Social
Machine learning

A quick guide to Amazon's papers at NeurIPS 2024

While large language models and other foundation models are well represented, traditional Amazon interests such as bandit problems and new topics such as AI for automated reasoning also get their due.

By Staff writer
December 10, 2024
3 min read
Share

The 2024 Conference on Neural Information Processing Systems (NeurIPS) — the premier conference in the field of AI — begins today, and the Amazon papers accepted there display the breadth of the company’s AI research.

Large language models (LLMs) and other foundation models have dominated the field for the past few years, and Amazon’s papers reflect that trend, covering topics such as retrieval-augmented generation, the use of LLMs for code generation, commonsense reasoning, and multimodal models. Training methodology also emerges as an area of focus, with papers on memory-efficient training, reinforcement learning with human feedback, classification with rejection, and convergence rates in transformer models.

But Amazon’s papers also demonstrate an abiding interest in topics such as bandit problems — long a staple of Amazon’s NeurIPS submissions — and speech processing, as well as newer concerns such as the applications of machine learning to scientific computing and automated reasoning. And one paper, “B’MOJO: Hybrid state space realizations of foundation models with eidetic and fading memory”, proposes a new paradigm of machine learning, rooted in the concept of transductive learning.

Automated reasoning

Neural model checking
Mirco Giacobbe, Daniel Kroening, Abhinandan Pal, Michael Tautschnig

Bandit problems

Adaptive experimentation when you can’t experiment
Yao Zhao, Kwang-Sung Jun, Tanner Fiez, Lalit Jain

Online posterior sampling with a diffusion prior
Branislav Kveton, Boris Oreshkin, Youngsuk Park, Aniket Deshmukh, Rui Song

Code generation

Training LLMs to better self-debug and explain code
Nan Jiang, Xiaopeng LI, Shiqi Wang, Qiang Zhou, Baishakhi Ray, Varun Kumar, Xiaofei Ma, Anoop Deoras

The LEDEX framework
The data collection and model-training framework proposed in "Training LLMs to better self-debug and explain code".

Commonsense reasoning

Can language models learn to skip steps?
Tengxiao Liu, Qipeng Guo, Xiangkun Hu, Jiayang Cheng, Yue Zhang, Xipeng Qiu, Zheng Zhang

Computational fluid dynamics

WindsorML: High-fidelity computational fluid dynamics dataset for automotive aerodynamics
Neil Ashton, Jordan B. Angel, Aditya S. Ghate, Gaetan K. W. Kenway, Man Long Wong, Cetin Kiris, Astrid Walle, Danielle Maddix Robinson, Gary Page

LLM evaluation

SetLexSem Challenge: Using set operations to evaluate the lexical and semantic robustness of language models
Bardiya Akhbari, Manish Gawali, Nicholas Dronen

SetLexSem Challenge figure
To evaluate LLMs' robustness to semantic variation in set members, Amazon researchers and their colleagues created “deceptive” sets by sampling pairs of hypernyms (e.g., “mammal” and “vehicle”) and, from them, extracting hyponyms under three different conditions: (1) with the hyponyms as sampled; (2) with half of the set members swapped; and (3) with random sampling. LLMs exhibit a unique failure mode under the second condition (swapped), and the mean and variance in accuracy of the first condition (not swapped) are better than in the random baseline. This figure can be found in "SetLexSem Challenge: Using set operations to evaluate the lexical and semantic robustness of language models".

Memory management

Online weighted paging with unknown weights
Orin Levy, Aviv Rosenberg, Noam Touitou

Model architecture

B’MOJO: Hybrid state space realizations of foundation models with eidetic and fading memory
Luca Zancato, Arjun Seshadri, Yonatan Dukler, Aditya Golatkar, Yantao Shen, Ben Bowman, Matthew Trager, Alessandro Achille, Stefano Soatto

Privacy

Pre-training differentially private models with limited public data
Zhiqi Bu, Xinwei Zhang, Sheng Zha, Mingyi Hong

Reconstruction attacks on machine unlearning: Simple models are vulnerable
Martin Bertran Lopez, Shuai Tang, Michael Kearns, Jamie Morgenstern, Aaron Roth, Zhiwei Steven Wu

Retrieval-augmented generation (RAG)

RAGChecker: A fine-grained framework for diagnosing retrieval-augmented generation
Dongyu Ru, Lin Qiu, Xiangkun Hu, Tianhang Zhang, Peng Shi, Shuaichen Chang, Cheng Jiayang, Cunxiang Wang, Shichao Sun, Huanyu Li, Zizhao Zhang, Binjie Wang, Jiarong Jiang, Tong He, Zhiguo Wang, Pengfei Liu, Yue Zhang, Zheng Zhang

Speech processing

CA-SSLR: Condition-aware self-supervised learning representation for generalized speech processing
Yen-Ju Lu, Jing Liu, Thomas Thebaud, Laureano Moro-Velazquez, Ariya Rastrow, Najim Dehak, Jesus Villalba

CA-SSLR scheme
The CA-SSLR scheme and its time-channel attention conditioner, as proposed in "CA-SSLR: Condition-aware self-supervised learning representation for generalized speech processing". Only the conditioner and linear projections for the decoders are trainable; all other parameters are frozen during adaptation. CA-SSLR improves SSL features by integrating intermediate LID/SV conditions, keeping pretrained parameters frozen (left). The trainable time-channel attention conditioner integrates language and speaker prediction (right).

Training methods

CoMERA: Computing- and memory-efficient training via rank-adaptive tensor optimization
Zi Yang, Ziyue Liu, Samridhi Choudhary, Xinfeng Xie, Cao Gao, Siegfried Kunzmann, Zheng Zhang

Optimal design for human preference elicitation
Subhojyoti Mukherjee, Anusha Lalitha, Kousha Kalantari, Aniket Deshmukh, Ge Liu, Yifei Ma, Branislav Kveton

Rejection via learning density ratios
Alexander Soen, Hisham Husain, Philip Schulz, Vu Nguyen

Unraveling the gradient descent dynamics of transformers
Bingqing Song, Boran Han, Shuai Zhang, Jie Ding, Mingyi Hong

Video

One token to seg them all: Language instructed reasoning segmentation in videos
Zechen Bai, Tong He, Haiyang Mei, Pichao Wang, Ziteng Gao, Joya Chen, Lei Liu, Pichao Wang, Zheng Zhang, Mike Zheng Shou

One token to seg them all: Language instructed reasoning segmentation in videos
The video object segmentation framework proposed in "One token to seg them all: Language instructed reasoning segmentation in videos".

Video token merging for long-form video understanding
Seon Ho Lee, Jue Wang, Zhikang Zhang, David Fan, Xinyu (Arthur) Li

Vision-language models

Unified lexical representation for interpretable visual-language alignment
Yifan Li, Yikai Wang, Yanwei Fu, Dongyu Ru, Zheng Zhang, Tong He

Research areas
Tags
About the Author
Staff writer

Related content

Work with us

See more jobs See more jobs
Senior Applied Scientist, Applied AI
US, WA, Bellevue
We are seeking a passionate, talented, and inventive individual to join the Applied AI team and help build industry-leading technologies that customers will love. This team offers a unique opportunity to make a significant impact on the customer experience and contribute to the design, architecture, and implementation of a cutting-edge product. The mission of the Applied AI team is to enable organizations within Worldwide Amazon.com Stores to accelerate the adoption of AI technologies across various parts of our business. We are looking for a Senior Applied Scientist to join our Applied AI team to work on LLM-based solutions. On our team you will push the boundaries of ML and Generative AI techniques to scale the inputs for hundreds of billions of dollars of annual revenue for our eCommerce business. If you have a passion for AI technologies, a drive to innovate and a desire to make a meaningful impact, we invite you to become a valued member of our team. You will be responsible for developing and maintaining the systems and tools that enable us to accelerate knowledge operations and work in the intersection of Science and Engineering. You will push the boundaries of ML and Generative AI techniques to scale the inputs for hundreds of billions of dollars of annual revenue for our eCommerce business. If you have a passion for AI technologies, a drive to innovate and a desire to make a meaningful impact, we invite you to become a valued member of our team. We are seeking an experienced Scientist who combines superb technical, research, analytical and leadership capabilities with a demonstrated ability to get the right things done quickly and effectively. This person must be comfortable working with a team of top-notch developers and collaborating with our research teams. We’re looking for someone who innovates, and loves solving hard problems. You will be expected to have an established background in building highly scalable systems and system design, excellent project management skills, great communication skills, and a motivation to achieve results in a fast-paced environment. You should be somebody who enjoys working on complex problems, is customer-centric, and feels strongly about building good software as well as making that software achieve its operational goals.
Senior Applied Scientist , Buyer Risk Prevention (BRP)
IN, KA, Bengaluru
Do you want to lead the development of advanced machine learning systems that protect millions of customers and power a trusted global eCommerce experience? Are you passionate about modeling terabytes of data, solving highly ambiguous fraud and risk challenges, and driving step-change improvements through scientific innovation? If so, the Amazon Buyer Risk Prevention (BRP) Machine Learning team may be the right place for you. We are seeking a Senior Applied Scientist to define and drive the scientific direction of large-scale risk management systems that safeguard millions of transactions every day. In this role, you will lead the design and deployment of advanced machine learning solutions, influence cross-team technical strategy, and leverage emerging technologies—including Generative AI and LLMs—to build next-generation risk prevention platforms. Key job responsibilities Lead the end-to-end scientific strategy for large-scale fraud and risk modeling initiatives Define problem statements, success metrics, and long-term modeling roadmaps in partnership with business and engineering leaders Design, develop, and deploy highly scalable machine learning systems in real-time production environments Drive innovation using advanced ML, deep learning, and GenAI/LLM technologies to automate and transform risk evaluation Influence system architecture and partner with engineering teams to ensure robust, scalable implementations Establish best practices for experimentation, model validation, monitoring, and lifecycle management Mentor and raise the technical bar for junior scientists through reviews, technical guidance, and thought leadership Communicate complex scientific insights clearly to senior leadership and cross-functional stakeholders Identify emerging scientific trends and translate them into impactful production solutions
Applied Scientist, Artificial General Intelligence, AGI Data Services
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
Applied Scientist, Artificial General Intelligence, AGI Data Services
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
Applied Scientist, Artificial General Intelligence, AGI Data Services
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
Applied Scientist, Artificial General Intelligence, AGI Data Services
US, MA, Boston
The Artificial General Intelligence (AGI) team is seeking a dedicated, skilled, and innovative Applied Scientist with a robust background in machine learning, statistics, quality assurance, auditing methodologies, and automated evaluation systems to ensure the highest standards of data quality, to build industry-leading technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As part of the AGI team, an Applied Scientist will collaborate closely with core scientist team developing Amazon Nova models. They will lead the development of comprehensive quality strategies and auditing frameworks that safeguard the integrity of data collection workflows. This includes designing auditing strategies with detailed SOPs, quality metrics, and sampling methodologies that help Nova improve performances on benchmarks. The Applied Scientist will perform expert-level manual audits, conduct meta-audits to evaluate auditor performance, and provide targeted coaching to uplift overall quality capabilities. A critical aspect of this role involves developing and maintaining LLM-as-a-Judge systems, including designing judge architectures, creating evaluation rubrics, and building machine learning models for automated quality assessment. The Applied Scientist will also set up the configuration of data collection workflows and communicate quality feedback to stakeholders. An Applied Scientist will also have a direct impact on enhancing customer experiences through high-quality training and evaluation data that powers state-of-the-art LLM products and services. A day in the life An Applied Scientist with the AGI team will support quality solution design, conduct root cause analysis on data quality issues, research new auditing methodologies, and find innovative ways of optimizing data quality while setting examples for the team on quality assurance best practices and standards. Besides theoretical analysis and quality framework development, an Applied Scientist will also work closely with talented engineers, domain experts, and vendor teams to put quality strategies and automated judging systems into practice.
Senior Economist , Economic Decision Science
GB, London
We are looking for a Senior Economist to work on exciting and challenging business problems related to Amazon Retail’s worldwide product assortment. You will build innovative solutions based on econometrics, machine learning, and experimentation. You will be part of a interdisciplinary team of economists, product managers, engineers, and scientists, and your work will influence finance and business decisions affecting Amazon’s vast product assortment globally. If you have an entrepreneurial spirit, you know how to deliver results fast, and you have a deeply quantitative, highly innovative approach to solving problems, and long for the opportunity to build pioneering solutions to challenging problems, we want to talk to you. Key job responsibilities * Work on a challenging problem that has the potential to significantly impact Amazon’s business position * Develop econometric models and experiments to measure the customer and financial impact of Amazon’s product assortment * Collaborate with other scientists at Amazon to deliver measurable progress and change * Influence business leaders based on empirical findings
Senior Applied Scientist, International Machine Learning
IN, KA, Bengaluru
Do you want to join an innovative team of scientists who use machine learning and statistical techniques to create state-of-the-art solutions for providing better value to Amazon’s customers? Do you want to build and deploy advanced algorithmic systems that help optimize millions of transactions every day? Are you excited by the prospect of analyzing and modeling terabytes of data to solve real world problems? Do you like to own end-to-end business problems/metrics and directly impact the profitability of the company? Do you like to innovate and simplify? If yes, then you may be a great fit to join the Machine Learning and Data Sciences team for India Consumer Businesses. If you have an entrepreneurial spirit, know how to deliver, love to work with data, are deeply technical, highly innovative and long for the opportunity to build solutions to challenging problems that directly impact the company's bottom-line, we want to talk to you. Major responsibilities - Use machine learning and analytical techniques to create scalable solutions for business problems - Analyze and extract relevant information from large amounts of Amazon’s historical business data to help automate and optimize key processes - Design, development, evaluate and deploy innovative and highly scalable models for predictive learning - Research and implement novel machine learning and statistical approaches - Work closely with software engineering teams to drive real-time model implementations and new feature creations - Work closely with business owners and operations staff to optimize various business operations - Establish scalable, efficient, automated processes for large scale data analyses, model development, model validation and model implementation - Mentor other scientists and engineers in the use of ML techniques Key job responsibilities Use machine learning and analytical techniques to create scalable solutions for business problems Analyze and extract relevant information from large amounts of Amazon’s historical business data to help automate and optimize key processes Design, develop, evaluate and deploy, innovative and highly scalable ML models Work closely with software engineering teams to drive real-time model implementations Work closely with business partners to identify problems and propose machine learning solutions Establish scalable, efficient, automated processes for large scale data analyses, model development, model validation and model maintenance Work proactively with engineering teams and product managers to evangelize new algorithms and drive the implementation of large-scale complex ML models in production Leading projects and mentoring other scientists, engineers in the use of ML techniques About the team International Machine Learning Team is responsible for building novel ML solutions that attack India first (and other Emerging Markets across MENA and LatAm) problems and impact the bottom-line and top-line of India business. Learn more about our team from https://www.amazon.science/working-at-amazon/how-rajeev-rastogis-machine-learning-team-in-india-develops-innovations-for-customers-worldwide
2026 Applied Scientist Intern, Amazon University Talent Acquisition
EG, Cairo
Are you a MS or PhD student interested in a 2026 internship in the field of machine learning, deep learning, generative AI, large language models and speech technology, robotics, computer vision, optimization, operations research, quantum computing, automated reasoning, or formal methods? If so, we want to hear from you! We are looking for students interested in using a variety of domain expertise to invent, design and implement state-of-the-art solutions for never-before-solved problems. You can find more information about the Amazon Science community as well as our interview process via the links below; https://www.amazon.science/ https://amazon.jobs/content/en/career-programs/university/science https://amazon.jobs/content/en/how-we-hire/university-roles/applied-science Key job responsibilities As an Applied Science Intern, you will own the design and development of end-to-end systems. You’ll have the opportunity to write technical white papers, create roadmaps and drive production level projects that will support Amazon Science. You will work closely with Amazon scientists and other science interns to develop solutions and deploy them into production. You will have the opportunity to design new algorithms, models, or other technical solutions whilst experiencing Amazon’s customer focused culture. The ideal intern must have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems. A day in the life At Amazon, you will grow into the high impact person you know you’re ready to be. Every day will be filled with developing new skills and achieving personal growth. How often can you say that your work changes the world? At Amazon, you’ll say it often. Join us and define tomorrow. Some more benefits of an Amazon Science internship include; • All of our internships offer a competitive stipend/salary • Interns are paired with an experienced manager and mentor(s) • Interns receive invitations to different events such as intern program initiatives or site events • Interns can build their professional and personal network with other Amazon Scientists • Interns can potentially publish work at top tier conferences each year About the team Applicants will be reviewed on a rolling basis and are assigned to teams aligned with their research interests and experience prior to interviews. Start dates are available throughout the year and durations can vary in length from 3-6 months for full time internships. This role may available across multiple locations in the EMEA region (Austria, Estonia, France, Germany, Ireland, Israel, Italy, Jordan, Luxembourg, Netherlands, Poland, Romania, Spain, South Africa, UAE, and UK). Please note these are not remote internships.
Intern - Economics, Private Brands - Intelligence
US, CA, San Diego
We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to apply their macroeconomics and forecasting skillsets to solve real world problems. The intern will work in the area of forecasting, developing models to improve the success of new product launches in Private Brands. Our PhD Economist Internship Program offers hands-on experience in applied economics, supported by mentorship, structured feedback, and professional development. Interns work on real business and research problems, building skills that prepare them for full-time economist roles at Amazon and beyond. You will learn how to build data sets and perform applied econometric analysis collaborating with economists, scientists, and product managers. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement. These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis About the team The Amazon Private Brands Intelligence team applies Machine Learning, Statistics and Econometrics/economics to solve high-impact business problems, develop prototypes for Amazon-scale science solutions, and optimize key business functions of Amazon Private Brands and other Amazon orgs. We are an interdisciplinary team, using science and technology and leveraging the strengths of engineers and scientists to build solutions for some of the toughest business problems at Amazon, covering areas such as pricing, discovery, negotiation, forecasting, supply chain and product selection/development.
See more jobs
View from space of a connected network around planet Earth representing the Internet of Things.
Get more from Amazon Science
Subscribe to our newsletter

Amazon.com | Conditions of Use | Privacy | © 1996-2026 Amazon.com, Inc. or its affiliates

Social