{"id":135,"date":"2023-01-25T08:47:31","date_gmt":"2023-01-25T08:47:31","guid":{"rendered":"https:\/\/todaysainews.com\/index.php\/2023\/01\/25\/google-at-neurips-2022-google-ai-blog\/"},"modified":"2025-04-27T07:36:04","modified_gmt":"2025-04-27T07:36:04","slug":"google-at-neurips-2022-google-ai-blog","status":"publish","type":"post","link":"https:\/\/todaysainews.com\/index.php\/2023\/01\/25\/google-at-neurips-2022-google-ai-blog\/","title":{"rendered":"Google at NeurIPS 2022 \u2013 Google AI Blog"},"content":{"rendered":"

[ad_1]
\n<\/p>\n

\nPosted by Cat Armato, Program Manager, Google
\n<\/span><\/p>\n

<\/p>\n

\nThis week marks the beginning of the 36th annual Conference on Neural Information Processing Systems (NeurIPS 2022<\/a>), the biggest machine learning conference of the year. NeurIPS 2022 will be held as a hybrid event, in person in New Orleans, LA with some virtual attendance options, and includes invited talks, demonstrations and presentations of some of the latest in machine learning research. This year, NeurIPS is also offering a new track, called Spotlight Papers, which will provide opportunities to highlight papers presented in prestigious journals that would otherwise not have been eligible for submission.\n<\/p>\n

<\/p>\n

\nGoogle is proud to be a Diamond level sponsor of NeurIPS this year and will have a significant presence year with more than 175 accepted papers, additionally contributing to and learning from the broader academic research community through numerous talks, posters, workshops, and tutorials. You can learn more about our work being presented in the list below (Google affiliations highlighted in bold<\/b>).\n<\/p>\n

Organizing Committee<\/h2>\n

General Chairs includes: Sanmi Koyejo<\/b><\/i><\/p>\n

Program Chairs include: Alekh Agarwal<\/b><\/i><\/p>\n

Workshop Chairs include: Hanie Sedghi<\/b><\/i><\/p>\n

Tutorial Chairs include: Adji Bousso Dieng<\/b><\/i>, Jessica Schrouff<\/b><\/i><\/p>\n

Affinity Workshop Chair: Adji Bousso Dieng<\/b><\/i>, Jessica Schrouff<\/b><\/i><\/p>\n

Program Committee, Senior Area Chairs include: Corinna Cortes<\/b><\/i>, Claudio Gentile<\/b><\/i>, Mohammad Ghavamzadeh<\/b><\/i>, Amir Globerson<\/b><\/i>, Elad Hazan<\/b><\/i>, Katherine Heller<\/b><\/i>, Satyen Kale<\/b><\/i>, Been Kim<\/b><\/i>, Sanjiv Kumar<\/b><\/i>, Hugo Larochelle<\/b><\/i>, Sergey Levine<\/b><\/i>, Yishay Mansour<\/b><\/i>, Mehryar Mohri<\/b><\/i>, Tara Sainath<\/b><\/i>, Dale Schuurmans<\/b><\/i>, Daniel Tarlow<\/b><\/i><\/p>\n

NeurIPS Foundation Board Secretary: Michael Mozer<\/b><\/i><\/p>\n

NeurIPS Foundation Board Members include: Corinna Cortes<\/b><\/i>, Isabelle Guyon<\/b><\/i>, Sanmi Koyejo<\/b><\/i>, <\/b><\/i>Hugo Larochelle<\/b><\/i><\/p>\n

NeurIPS Foundation Advisory Board include: Peter Bartlett<\/b><\/i>, Zoubin Ghahramani<\/b><\/i>, John C. Platt<\/b><\/i>, Fernando Pereira<\/b><\/i>, Dale Schuurmans<\/b><\/i>\n<\/p>\n

Keynote Speakers<\/h2>\n

The Data-Centric Era: How ML is Becoming an Experimental Science<\/a>
\n
Isabelle Guyon<\/b><\/i>\n<\/p>\n

The Forward-Forward Algorithm for Training Deep Neural Networks<\/a>
\n
Geoffrey Hinton<\/b><\/i>\n<\/p>\n

Outstanding Paper Award<\/h2>\n

\nPhotorealistic Text-to-Image Diffusion Models with Deep Language Understanding<\/a>
\n
Chitwan Saharia<\/b><\/i>, William Chan<\/b><\/i>, Saurabh Saxena<\/b><\/i>, Lala Li<\/b><\/i>, Jay Whang<\/b><\/i>, Emily Denton<\/b><\/i>, Seyed Kamyar Seyed Ghasemipour<\/b><\/i>, Burcu Karagol Ayan<\/b><\/i>, S. Sara Mahdavi<\/b><\/i>, Rapha Gontijo Lopes<\/b><\/i>, Tim Salimans<\/b><\/i>, Jonathan Ho<\/b><\/i>, David J Fleet<\/b><\/i>, Mohammad Norouzi<\/b><\/i>\n<\/p>\n

EXPO Day Workshops<\/h2>\n

\nGraph Neural Networks in Tensorflow: A Practical Guide<\/a>
\n
Workshop Organizers include: Bryan Perozzi<\/b><\/i>, Sami Abu-el-Haija<\/b><\/i>\n<\/p>\n

\nA Hands-On Introduction to Tensorflow and Jax<\/a>
\n
Workshop Organizers include: Josh Gordon<\/b><\/i>\n<\/p>\n

Affinity Workshops <\/h2>\n

\nLatinX in AI (LXAI)<\/a>
\n
Platinum Sponsor
\n
Networking & Social Chairs include: Andres Mu\u00f1oz Medina<\/b><\/i>
\n
Program Committee includes: Johan Obando Ceron<\/b><\/i>\n<\/p>\n

\nQueer in AI<\/a>
\n
Panelists include: Sara Beery<\/b><\/i>, Talia Ringer<\/b><\/i>\n<\/p>\n

\nWomen in Machine Learning (WiML)<\/a>
\n
Platinum Sponsor
\n
Workshop Organizers and Mentorship Chairs include: Beliz Gunel<\/b><\/i>
\n
Mentors include: Adam Roberts<\/b><\/i>, Eleni Triantafillou<\/b><\/i>, Zelda Mariet<\/b><\/i>, Clara Hu<\/b><\/i>, Rosanne Liu<\/b><\/i>, Alekh Agarwal<\/b><\/i>, Vinod Prabhakaran<\/b><\/i>, Rose Yu<\/b><\/i>, Katherine Heller<\/b><\/i>\n<\/p>\n

Workshops<\/h2>\n

\nNew in ML<\/a>
\n
Workshop Organizers include: Isabelle Guyon<\/b><\/i>\n<\/p>\n

\nAI for Accelerated Materials Design (AI4Mat)<\/a>
\n
Workshop Organizers include: Benjamin Sanchez-Lengeling<\/b><\/i>\n<\/p>\n

\nAll Things Attention: Bridging Different Perspectives on Attention<\/a>
\n
Invited Speakers and Panelists include: Vidhya Navalpakkam<\/b><\/i>\n<\/p>\n

\nEfficient Natural Language and Speech Processing (ENLSP-II): The Future of Pre-trained Models<\/a>
\n
Invited Speakers include: Tara Sainath<\/b><\/i>, Anna Huang<\/b><\/i>
\n
Invited Panelists include: Mohammad Norouzi<\/b><\/i>
\n
Program Committee includes: Wenhu Chen<\/b><\/i>\n<\/p>\n

\nFederated Learning: Recent Advances and New Challenges<\/a>
\n
Program Committee includes: Kallista Bonawitz<\/b><\/i>, Zachary Charles<\/b><\/i>, Wenshuo Guo<\/b><\/i>, Peter Kairouz<\/b><\/i>, Zhaozhuo Xu<\/b><\/i>, Zheng Xu<\/b><\/i>\n<\/p>\n

\nGaussian Processes, Spatiotemporal Modeling, and Decision-Making Systems<\/a>
\n
Workshop Organizers include: Zi Wang<\/b><\/i>
\n
Invited Speakers include: Jasper Snoek<\/b><\/i>, Carolina Osorio<\/b><\/i>
\n
Advisory Board includes: Zoubin Ghahramani<\/b><\/i>\n<\/p>\n

\nHas it Trained Yet? A Workshop for Algorithmic Efficiency in Practical Neural Network Training<\/a>
\n
Workshop Organizers include: Zachary Nado<\/b><\/i>, George Dahl<\/b><\/i>, Naman Agarwal<\/b><\/i>, Aakanksha Chowdhery<\/b><\/i>
\n
Invited Speakers include: Aakanksha Chowdhery<\/b><\/i>, Priya Goyal<\/b><\/i>\n<\/p>\n

\nHuman in the Loop Learning (HiLL)<\/a>
\n
Workshop Organizers include: Fisher Yu, Vittorio Ferrari<\/b><\/i>
\n
Invited Speakers include: Dorsa Singh<\/b><\/i>, Igor Mordatch<\/b><\/i>, Ding Zhao<\/b><\/i>\n<\/p>\n

\nINTERPOLATE \u2014 First Workshop on Interpolation Regularizers and Beyond<\/a>
\n
Workshop Organizers include: Yann Dauphin<\/b><\/i>
\n
Invited Speakers include: Chelsea Finn<\/b><\/i>
\n
Panelists include: Chelsea Finn<\/b><\/i>, Dustin Tran<\/b><\/i>
\n
Program Committee includes: Wang Chen<\/b><\/i>, Kimin Lee<\/b><\/i>\n<\/p>\n

\nLaReL: Language and Reinforcement Learning<\/a>
\n
Invited Speakers include: Dorsa Singh<\/b><\/i>, Igor Mordatch<\/b><\/i>\n<\/p>\n

\nMedical Imaging Meets NeurIPS<\/a>
\n
Program Committee includes: Chenyu You<\/b><\/i>\n<\/p>\n

\nMemory in Artificial and Real Intelligence (MemARI)<\/a>
\n
Program Committee includes: Benjamin Eysenbach<\/b><\/i>, Otilia Stretcu<\/b><\/i>\n<\/p>\n

\nMeta-Learning<\/a>
\n
Workshop Organizers include: Eleni Triantafillou<\/b><\/i>
\n
Invited Speakers include: Lucas Byer<\/b><\/i>, Chelsea Finn<\/b><\/i>
\n
Program Committee includes: Ishita Dasgupta<\/b><\/i>, Praneet Dutta<\/b><\/i>, Benjamin Eysenbach<\/b><\/i>, Maximilian Igl<\/b><\/i>, Louis Kirsch<\/b><\/i>, Parsa Mahmoudieh<\/b><\/i>, Marc Pickett<\/b><\/i>, Eleni Triantafillou<\/b><\/i>\n<\/p>\n

\nNew Frontiers in Graph Learning (GLFrontiers)<\/a>
\n
Workshop Organizers include: Hanjun Dai<\/b><\/i>\n<\/p>\n

\nOffline Reinforcement Learning Workshop: Offline RL as a “Launchpad”<\/a>
\n
Workshop Organizers include: Rishabh Agarwal<\/b><\/i>, Aviral Kumar<\/b><\/i>, George Tucker<\/b><\/i>
\n
Invited Speakers include: Dorsa Sadigh<\/b><\/i>\n<\/p>\n

\nScore-Based Methods<\/a>
\n
Invited Speakers include: Mohammad Norouzi<\/b><\/i>
\n
Invited Panelists include: Jascha Sohl-Dickstein<\/b><\/i>\n<\/p>\n

\nSynthetic Data for Empowering ML Research<\/a>
\n
Invited Speakers include: Mehryar Mohri<\/b><\/i>
\n
Invited Panelists include: Katrina Ligett<\/b><\/i>
\n
Program Committee includes: Jinsung Yoon<\/b><\/i>\n<\/p>\n

\nTable Representation Learning<\/a>
\n
Workshop Organizers include: Pengcheng Yin<\/b><\/i>
\n
Invited Speakers include: Xinyun Chen<\/b><\/i>, Carsten Binnig<\/b><\/i>
\n
Panelists include: Julian Eisenschlos<\/b><\/i>
\n
Program Committee includes: Wenhu Chen<\/b><\/i>, Xinyun Chen<\/b><\/i>, Beliz Gunel<\/b><\/i>\n<\/p>\n

\nA Causal View on Dynamical Systems<\/a>
\n
Program Committee includes: Rose Yu<\/b><\/i>\n<\/p>\n

\nAlgorithmic Fairness Through the Lens of Causality and Privacy<\/a>
\n
Workshop Organizers include: Awa Dieng<\/b><\/i>
\n
Invited Speakers include: Nicolas Papernot<\/b><\/i>
\n
Roundtable Leads include: David Madras<\/b><\/i>, Negar Rostamzadeh<\/b><\/i>, Nyalleng Moroosi<\/b><\/i>
\n
Program Committee includes: Matt Kusner<\/b><\/i>\n<\/p>\n

\nBroadening Research Collaborations in ML<\/a>
\n
Workshop Organizers include: Rosanne Liu<\/b><\/i>, Pablo Samuel Castro<\/b><\/i>, Sunipa Dev<\/b><\/i>\n<\/p>\n

\nDecentralization and Trustworthy Machine Learning in Web3: Methodologies, Platforms, and Applications<\/a>
\n
Invited Speakers include: Peter Kairouz<\/b><\/i>\n<\/p>\n

\nDistribution Shifts (DistShift): Connecting Methods and Applications<\/a>
\n
Workshop Organizers include: Becca Roelofs<\/b><\/i>, Chelsea Finn<\/b><\/i>, Jacob Eisenstein<\/b><\/i>, Pang Wei Koh<\/b><\/i>
\n
Invited Speakers include: Sarah Beery<\/b><\/i>\n<\/p>\n

\nFoundation Models for Decision Making<\/a>
\n
Workshop Organizers include: Sherry Yang<\/b><\/i>, Yilun Du<\/b><\/i>, Igor Mordatch<\/b><\/i>, Shixiang Shane Gu<\/b><\/i>,Ofir Nachum<\/b><\/i>
\n
Invited Speakers include: Dorsa Sadigh<\/b><\/i>, Dale Schuurmans<\/b><\/i>, Machel Reid<\/b><\/i>
\n
Program Committee includes: Bo Dai<\/b><\/i>, Aleksandra Faust<\/b><\/i>, Hiroki Furuta<\/b><\/i>, Kati Goshvadi<\/b><\/i>, Izzeddin Gur<\/b><\/i>, Austin Huang<\/b><\/i>, Kimin Lee<\/b><\/i>, Kuang-Huei Lee<\/b><\/i>, Lisa Lee<\/b><\/i>, Yingjie Miao<\/b><\/i>, Jordi Orbay<\/b><\/i>, Ted Xiao<\/b><\/i>\n<\/p>\n

\nGaze Meets ML<\/a>
\n
Program Committee includes: Peter Mattson<\/b><\/i>, Mehdi Moradi<\/b><\/i>\n<\/p>\n

\nI Can\u2019t Believe It\u2019s Not Better: Understanding Deep Learning Through Empirical Falsification<\/a>
\n
Workshop Organizers include: Javier Antor\u00e1n<\/b><\/i>
\n
Panelists include: Kevin Murphy<\/b><\/i>\n<\/p>\n

\nInteractive Learning for Natural Language Processing<\/a>
\n
Invited Speakers include: Anca Dragan<\/b><\/i>
\n
Program Committees include: Julia Kreutzer<\/b><\/i>, Shunyu Yao<\/b><\/i>\n<\/p>\n

\nMachine Learning and the Physical Sciences<\/a>
\n
Workshop Organizers include: Adji Bousso Dieng<\/b><\/i>
\n
Invited Speakers include: Ekin Do\u011fu\u015f \u00c7ubuk<\/b><\/i>\n<\/p>\n

\nMachine Learning for Systems<\/a>
\n
Workshop Organizers include: Martin Maas<\/b><\/i>, Azade Nova<\/b><\/i>, Dan Zhang<\/b><\/i>
\n
Invited Speakers include: Jeff Dean<\/b><\/i>
\n
Program Committee includes: Milad Hashemi<\/b><\/i>, Kevin Swersky<\/b><\/i>\n<\/p>\n

\nMachine Learning in Structural Biology<\/a>
\n
Invited Speakers include: David Fleet<\/b><\/i>\n<\/p>\n

\nMATH-AI: Toward Human-Level Mathematical Reasoning<\/a>
\n
Workshop Organizers include: Swaroop Mishra<\/b><\/i>, Yuhuai Wu<\/b><\/i>
\n
Invited Speakers include: Talia Ringer<\/b><\/i>\n<\/p>\n

\nOPT 2022: Optimization for Machine Learning<\/a>
\n
Workshop Organizers include: Courtney Paquette<\/b><\/i>\n<\/p>\n

\nReinforcement Learning for Real Life (RL4RealLife)<\/a>
\n
Workshop Organizers include: Minmin Chen<\/b><\/i>
\n
Invited Panelists include: Pablo Samuel Castro<\/b><\/i>
\n
Program Committee includes: Victor Carbune<\/b><\/i>, Bo Chang<\/b><\/i>, Yinlam Chow<\/b><\/i>, Konstantina Christakopoulou<\/b><\/i>, Bo Dai<\/b><\/i>, Hanjun Dai<\/b><\/i>, Aleksandra Faust<\/b><\/i>, Joshua Greaves\u200e<\/b><\/i>, Chih-wei Hsu, Rahul Kidambi<\/b><\/i>, Srivatsan Krishnan<\/b><\/i>, Iou-Jen Liu<\/b><\/i>, Cong Lu<\/b><\/i>, Jincheng Mei<\/b><\/i>, Chao Qin<\/b><\/i>\n<\/p>\n

\nSelf-Supervised Learning – Theory and Practice<\/a>
\n
Invited Speakers include: Mathilde Caron<\/b><\/i>\n<\/p>\n

\nSymmetry and Geometry in Neural Representations (NeurReps)<\/a>
\n
Invited Speakers include: Noah Shutty<\/b><\/i>
\n
Program Committee includes: Ondrej Biza<\/b><\/i>, Noah Shutty<\/b><\/i>\n<\/p>\n

\nTemporal Graph Learning Workshop<\/a>
\n
Invited Speakers include: Mehran Kazemi<\/b><\/i>\n<\/p>\n

\nTransfer Learning for Natural Language Processing<\/a>
\n
Workshop Organizers include: Deepak Ramachandran<\/b><\/i>, Sebastian Ruder<\/b><\/i>
\n
Invited Speakers include: Jonas Pfeiffer<\/b><\/i>
\n
Invited Debaters include: Ellie Pavlick<\/b><\/i>
\n
Program Committee includes: Patrick Fernandes<\/b><\/i>, Jonas Pfeiffer<\/b><\/i>, Jiao Sun,<\/b><\/i> Tu Vu<\/b><\/i>, Xinyi Wang<\/b><\/i>, Xin Xu<\/b><\/i>\n<\/p>\n

\nCultures of AI and AI for Culture<\/a>
\n
Workshop Organizers include: Rida Qadri<\/b><\/i>, Fernando Diaz<\/b><\/i>\n<\/p>\n

\nDeep Reinforcement Learning Workshop<\/a>
\n
Workshop Organizers include: Karol Hausman<\/b><\/i>, Ted Xiao<\/b><\/i>, Zeyu Zheng<\/b><\/i>
\n
Invited Speakers include: Igor Mordatch<\/b><\/i>
\n
Advisory Board includes: Chelsea Finn<\/b><\/i>\n<\/p>\n

\nEmpowering Communities: A Participatory Approach to AI for Mental Health<\/a>
\n
Program Committee includes: Diana Mincu<\/b><\/i>, Subhrajit Roy<\/b><\/i>, Martin Seneviratne<\/b><\/i>\n<\/p>\n

\nHCAI@NeurIPS 2022, Human Centered AI<\/a>
\n
Keynote Speaker includes: Fernanda Viegas<\/b><\/i>\n<\/p>\n

\nLearning Meaningful Representations of Life<\/a>
\n
Workshop Organizers include: Adji Bousso Dieng<\/b><\/i>\n<\/p>\n

\nMachine Learning for Creativity and Design<\/a>
\n
Workshop Organizers include: Yingtao Tian<\/b><\/i>\n<\/p>\n

\nMachine Learning Safety<\/a>
\n
Workshop Organizers include: Nicholas Carlini<\/b><\/i>
\n
Invited Speakers include: Dorsa Sadigh<\/b><\/i>\n<\/p>\n

\nNeuro Causal and Symbolic AI (nCSI)<\/a>
\n
Workshop Organizers include: Thomas Kipf<\/b><\/i>\n<\/p>\n

\nRobot Learning Workshop: Trustworthy Robotics<\/a>
\n
Workshop Organizers include: Alex Bewley<\/b><\/i>, Jonathan Tompson<\/b><\/i>
\n
Invited Speakers include: Karol Hausman<\/b><\/i>, Brian Ichter<\/b><\/i>, Been Kim<\/b><\/i>, Leila Takayama<\/b><\/i>, Andy Zeng<\/b><\/i>
\n
Program Committee includes: Vincent Vanhoucke<\/b><\/i>\n<\/p>\n

\nThe Symbiosis of Deep Learning and Differential Equations II<\/a>
\n
Workshop Organizers include: Winnie Xu<\/b><\/i>
\n
Invited Speakers include: Rose Yu<\/b><\/i>\n<\/p>\n

\nTackling Climate Change with Machine Learning<\/a>
\n
Workshop Organizers include: Emma Strubell<\/b><\/i>\n<\/p>\n

\nTrustworthy and Socially Responsible Machine Learning<\/a>
\n
Invited Speakers include: Been Kim, Dorsa Sadigh<\/b><\/i>, Milind Tambe<\/b><\/i>\n<\/p>\n

\nVision Transformers: Theory and Applications<\/a>
\n
Invited Speakers include: Cordelia Schmid<\/b><\/i>, Ming Hsuan Yang<\/b><\/i>\n<\/p>\n

Tutorials<\/h2>\n

\nAdvances in Bayesian Optimization<\/a>
\n
Tutorial Organizers include: Virginia Aglietti<\/b><\/i>\n<\/p>\n

\nCreative Culture and Machine Learning<\/a>
\n
Tutorial Organizers include: Negar Rostamzadeh<\/b><\/i>\n<\/p>\n

\nFair and Socially Responsible ML for Recommendations: Challenges and Perspectives<\/a>
\n
Invited Panelists include: Fernando Diaz<\/b><\/i>\n<\/p>\n

\nLifelong Learning Machines<\/a>
\n
Invited Panelists include: Christopher Summerfield<\/b><\/i>\n<\/p>\n

\nThe Role of Meta-learning for Few-Shot Learning<\/a>
\n
Tutorial Organizers include: Eleni Triantafillou<\/b><\/i>
\n
Invited Panelists include: Neil<\/b><\/i> Houlsby<\/b><\/i>, Priyanka Agrawal<\/b><\/i>\n<\/p>\n

Competitions<\/h2>\n

\nNeurIPS 2022 Competition Track: Overview & Results<\/a>
\n
Invited Speakers include: Isabelle Guyon<\/b><\/i>\n<\/p>\n

\nCausal Insights for Learning Paths in Education<\/a>
\n
Competition Organizers include: Zichao (Jack) Wang<\/b><\/i>\n<\/p>\n

\nIGLU: Interactive Grounded Language Understanding in a Collaborative Environment<\/a>
\n
Competition Organizers include: Negar Arabzadeh<\/b><\/i>\n<\/p>\n

\nCross-Domain MetaDL: Any-Way Any-Shot Learning Competition with Novel Datasets from Practical Domains<\/a>
\n
Competition Organizers include: Isabelle Guyon<\/b><\/i>\n<\/p>\n

\nReconnaissance Blind Chess: An Unsolved Challenge for Multi-Agent Decision Making Under Uncertainty<\/a>
\n
Competition Organizers include: Bo Li<\/b><\/i>\n<\/p>\n

\nVisDA 2022 Challenge: Sim2Real Domain Adaptation for Industrial Recycling<\/a>
\n
Competition Organizers include: Dina Bashkirova<\/b><\/i>\n<\/p>\n

Spotlight Papers<\/h2>\n

\nCoPur: Certifiably Robust Collaborative Inference via Feature Purification<\/a>
\n
Jing Liu, Chulin Xie, Oluwasanmi O Koyejo<\/b><\/i>, Bo Li\n<\/p>\n

\nMachine Learning on Graphs: A Model and Comprehensive Taxonomy<\/a>
\n
Ines Chami*<\/sup><\/span><\/a>, Sami Abu-El-Haija, Bryan Perozzi<\/b><\/i>, Christopher R\u00e9, Kevin Murphy<\/b><\/i>\n<\/p>\n

\nSparse Winning Tickets are Data-Efficient Image Recognizers<\/a>
\n
Mukund Varma T, Xuxi Chen, Zhenyu Zhang, Tianlong Chen, Subhashini Venugopalan<\/b><\/i>, Zhangyang Wang\n<\/p>\n

\nFederated Learning from Pre-trained Models: A Contrastive Learning Approach<\/a>
\n
Yue Tan, Guodong Long, Jie Ma, Lu Liu<\/b><\/i>, Tianyi Zhou, Jing Jiang\n<\/p>\n

\nImproving Multi-task Generalization via Regularizing Spurious Correlation<\/a>
\n
Ziniu Hu*<\/sup><\/span><\/a>, Zhe Zhao<\/b><\/i>, Xinyang Yi<\/b><\/i>, Tiansheng Yao, Lichan Hong<\/b><\/i>, Yizhou Sun, Ed H. Chi<\/b><\/i>\n<\/p>\n

\nThe Nature of Temporal Difference Errors in Multi-step Distributional Reinforcement Learning<\/a>
\n
Yunhao Tang, Mark Rowland, R\u00e9mi Munos, Bernardo \u00c1vila Pires, Will Dabney, Marc G. Bellemare<\/b><\/i>\n<\/p>\n

\nResidual Multiplicative Filter Networks for Multiscale Reconstruction<\/a>
\n
Shayan Shekarforoush, David B. Lindell, David J. Fleet<\/b><\/i>, <\/b><\/i>Marcus A Brubaker\n<\/p>\n

\nDifferentially Private Learning with Margin Guarantees<\/a>
\n
Raef Bassily<\/b><\/i>, Mehryar Mohri<\/b><\/i>, Ananda Theertha Suresh<\/b><\/i>\n<\/p>\n

\nOptimal Query Complexities for Dynamic Trace Estimation<\/a>
\n
David P. Woodruff*<\/sup><\/span><\/a>, Fred Zhang*<\/sup><\/span><\/a>, Qiuyi Zhang<\/b><\/i>\n<\/p>\n

Papers<\/h2>\n

\nFrom Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent<\/a>
\n
Ayush Sekhari, Satyen Kale<\/b><\/i>, Jason D. Lee, Chris De Sa, Karthik Sridharan\n<\/p>\n

\nOn the Global Convergence Rates of Decentralized Softmax Gradient Play in Markov Potential Games<\/a>
\n
Runyu Zhang, Jincheng Mei<\/b><\/i>, Bo Dai<\/b><\/i>, Dale Schuurmans<\/b><\/i>, <\/b><\/i>Na Li\n<\/p>\n

\nMatryoshka Representation Learning<\/a>
\n
Aditya Kusupati<\/b><\/i>, Gantavya Bhatt, Aniket Rege, Matthew Wallingford, Aditya Sinha<\/b><\/i>, <\/b><\/i>Vivek Ramanujan, William Howard-Snyder, Kaifeng Chen<\/b><\/i>, Sham Kakade, Prateek Jain<\/b><\/i>, Ali Farhadi\n<\/p>\n

\nEfficient Risk-Averse Reinforcement Learning<\/a>
\n
Ido Greenberg, Yinlam Chow,<\/b><\/i> Mohammad Ghavamzadeh<\/b><\/i>, Shie Mannor\n<\/p>\n

\nOperator Splitting Value Iteration<\/a>
\n
Amin Rakhsha, Andrew Wang, Mohammad Ghavamzadeh<\/b><\/i>, Amir-massoud Farahmand\n<\/p>\n

\nCluster Randomized Designs for One-Sided Bipartite Experiments<\/a>
\n
Jennifer Brennan*<\/sup><\/span><\/a>, Vahab Mirrokni<\/b><\/i>, Jean Pouget-Abadie<\/b><\/i>\n<\/p>\n

\nA Unified Sequence Interface for Vision Tasks<\/a>
\n
Ting Chen<\/b><\/i>, Saurabh Saxena<\/b><\/i>, Lala Li<\/b><\/i>, Tsung-Yi Lin*<\/sup><\/span><\/a>, David J. Fleet<\/b><\/i>, Geoffrey Hinton<\/b><\/i>\n<\/p>\n

\nCryptographic Hardness of Learning Halfspaces with Massart Noise<\/a>
\n
Ilias Diakonikolas, Daniel M. Kane, Pasin Manurangsi<\/b><\/i>, Lisheng Ren\n<\/p>\n

\nBetter Best of Both Worlds Bounds for Bandits with Switching Costs<\/a>
\n
Idan Amir, Guy Azov, Tomer Koren<\/b><\/i>, Roi Livni\n<\/p>\n

\nFast Neural Kernel Embeddings for General Activations<\/a>
\n
Insu Han, Amir Zandieh, Jaehoon Lee<\/b><\/i>, Roman Novak<\/b><\/i>, Lechao Xiao<\/b><\/i>, Amin Karbasi<\/b><\/i>\n<\/p>\n

\nHierarchical Agglomerative Graph Clustering in Poly-Logarithmic Depth<\/a>
\n
Laxman Dhulipala<\/b><\/i>, David Eisenstat<\/b><\/i>, Jakub \u0141\u0105cki<\/b><\/i>, Vahab Mirronki<\/b><\/i>, Jessica Shi\n<\/p>\n

\nImproving Zero-Shot Generalization in Offline Reinforcement Learning Using Generalized Similarity Functions<\/a>
\n
Bogdan Mazoure*<\/sup><\/span><\/a>, Ilya Kostrikov, Ofir Nachum<\/b><\/i>, Jonathan Tompson<\/b><\/i>\n<\/p>\n

\nIndicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples<\/a>
\n
Maura Pintor, Luca Demetrio, Angelo Sotgiu, Ambra Demontis, Nicholas Carlini<\/b><\/i>, Battista Biggio, Fabio Roli\n<\/p>\n

\nLearning Energy Networks with Generalized Fenchel-Young Losses<\/a>
\n
Mathieu Blondel<\/b><\/i>, Felipe Llinares-L\u00f3pez<\/b><\/i>, Robert Dadashi<\/b><\/i>, L\u00e9onard Hussenot<\/b><\/i>, Matthieu Geist<\/b><\/i>\n<\/p>\n

\nLearning Robust Dynamics Through Variational Sparse Gating<\/a>
\n
Arnav Kumar Jain, Shiva Kanth Sujit, Shruti Joshi, Vincent Michalski, Danijar Hafner<\/b><\/i>, Samira Ebrahimi Kahou\n<\/p>\n

\nLearning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures<\/a>
\n
Arnav Kumar Jain, Shiva Kanth Sujit, Shruti Joshi, Vincent Michalski, Danijar Hafner<\/b><\/i>, Samira Ebrahimi Kahou\n<\/p>\n

\nSo3krates: Equivariant Attention for Interactions on Arbitrary Length-Scales in Molecular Systems<\/a>
\n
J. Thorben Frank, Oliver T. Unke, Klaus-Robert M\u00fcller<\/b><\/i>\n<\/p>\n

\nSpectral Bias in Practice: The Role of Function Frequency in Generalization<\/a>
\n
Sara Fridovich-Keil*<\/sup><\/span><\/a>, Raphael Gontijo-Lopes<\/b><\/i>, Rebecca Roelofs<\/b><\/i>\n<\/p>\n

\nDelving into Out-of-Distribution Detection with Vision-Language Representations<\/a>
\n
Yifei Ming, Ziyang Cai, Jiuxiang Gu, Yiyou Sun, Wei Li<\/b><\/i>, Yixuan Li\n<\/p>\n

\nPath Independent Equilibrium Models Can Better Exploit Test-Time Computation<\/a>
\n
Cem Anil, Ashwini Pokle, Kaiqu Liang, Johannes Treutlein, Yuhuai Wu<\/b><\/i>, Shaojie Bai, J. Zico Kolter, Roger Grosse\n<\/p>\n

\nOn Optimal Learning Under Targeted Data Poisoning<\/a>
\n
Steve Hanneke, Amin Karbasi<\/b><\/i>, Mohammad Mahmoody, Idan Mehalel, Shay Moran<\/b><\/i>\n<\/p>\n

\nLearning With Little Mixing<\/a>
\n
Ingvar Ziemann, Stephen Tu<\/b><\/i>\n<\/p>\n

\nBlock-Recurrent Transformers<\/a>
\n
DeLesley Hutchins<\/b><\/i>, Imanol Schlag*<\/sup><\/span><\/a>, Yuhuai Wu<\/b><\/i>, Ethan Dyer<\/b><\/i>, Behnam Neyshabur<\/b><\/i>\n<\/p>\n

\nTabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasets<\/a>
\n
Chengrun Yang<\/b><\/i>, Gabriel Bender<\/b><\/i>, Hanxiao Liu<\/b><\/i>, Pieter-Jan Kindermans<\/b><\/i>, Madeleine Udell, Yifeng Lu<\/b><\/i>, Quoc Le<\/b><\/i>, Da Huang<\/b><\/i>\n<\/p>\n

\nRegret Bounds for Multilabel Classification in Sparse Label Regimes<\/a>
\n
Robert Busa-Fekete<\/b><\/i>, Heejin Choi<\/b><\/i>, Krzysztof Dembczynski, Claudio Gentile<\/b><\/i>, Henry William Reeve, Balazs Szorenyi\n<\/p>\n

\nRobust Reinforcement Learning Using Offline Data<\/a>
\n
Kishan Panaganti, Zaiyan Xu, Dileep Kalathil, Mohammad Ghavamzadeh<\/b><\/i>\n<\/p>\n

\nContrastive Learning as Goal-Conditioned Reinforcement Learning<\/a>
\n
Benjamin Eysenbach<\/b><\/i>, Tianjun Zhang, Sergey Levine<\/b><\/i>, Ruslan Salakhutdinov\n<\/p>\n

\nBeyond Rewards: A Hierarchical Perspective on Offline Multiagent Behavioral Analysis<\/a>
\n
Shayegan Omidshafiei<\/b><\/i>, Andrei Kapishnikov<\/b><\/i>, Yannick Assogba<\/b><\/i>, Lucas Dixon<\/b><\/i>, Been Kim<\/b><\/i>\n<\/p>\n

\nRevisiting Neural Scaling Laws in Language and Vision<\/a>
\n
Ibrahim Alabdulmohsin<\/b><\/i>, Behnam Neyshabur<\/b><\/i>, Xiaohua Zhai<\/b><\/i>\n<\/p>\n

\nPolynomial Neural Fields for Subband Decomposition and Manipulation<\/a>
\n
Guandao Yang*<\/sup><\/span><\/a>, Sagie Benaim, Varun Jampani<\/b><\/i>, Kyle Genova<\/b><\/i>, Jonathan T. Barron<\/b><\/i>, Thomas Funkhouser<\/b><\/i>, Bharath Hariharan, Serge Belongie\n<\/p>\n

\nFirst Is Better Than Last for Language Data Influence<\/a>
\n
Chih-Kuan Yeh<\/b><\/i>, Ankur Taly<\/b><\/i>, Mukund Sundararajan<\/b><\/i>, Frederick Liu<\/b><\/i>, Pradeep Ravikumar\n<\/p>\n

\nThe Privacy Onion Effect: Memorization Is Relative<\/a>
\n
Nicholas Carlini<\/b><\/i>, Matthew Jagielski<\/b><\/i>, Chiyuan Zhang<\/b><\/i>, Nicolas Papernot<\/b><\/i>, Andreas Terzis<\/b><\/i>, Florian Tramer<\/b><\/i>\n<\/p>\n

\nDeep Hierarchical Planning from Pixels<\/a> (see\u00a0blog post<\/a>)
\n
Danijar Hafner<\/b><\/i>, Kuang-Huei Lee<\/b><\/i>, Ian Fischer<\/b><\/i>, Pieter Abbeel\n<\/p>\n

\nDiscovered Policy Optimisation<\/a>
\n
Chris Lu, Jakub Grudzien Kuba, Alistair Letcher, Luke Metz<\/b><\/i>, Christian Schroeder de Witt, Jakob Foerster\n<\/p>\n

\nSemi-supervised Active Linear Regression<\/a>
\n
Fnu Devvrit, Nived Rajaraman, Pranjal Awasthi<\/b><\/i>\n<\/p>\n

\nPruning\u2019s Effect on Generalization Through the Lens of Training and Regularization<\/a>
\n
Tian Jin, Daniel M. Roy, Michael Carbin, Jonathan Frankle, Gintare Karolina Dziugaite<\/b><\/i>\n<\/p>\n

\nExploring Length Generalization in Large Language Models<\/a>
\n
Cem Anil*<\/sup><\/span><\/a>, Yuhuai Wu<\/b><\/i>, Anders Andreassen<\/b><\/i>, Aitor Lewkowycz<\/b><\/i>, Vedant Misra<\/b><\/i>, Vinay Ramasesh<\/b><\/i>, Ambrose Slone<\/b><\/i>, Guy Gur-Ari<\/b><\/i>, Ethan Dyer<\/b><\/i>, Behnam Neyshabur<\/b><\/i>\n<\/p>\n

\nFast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm Under Parallelization<\/a>
\n
Benjamin Dubois-Taine, Francis Bach, Quentin Berthet<\/b><\/i>, Adrien Taylor\n<\/p>\n

\nGlobal Normalization for Streaming Speech Recognition in a Modular Framework<\/a>
\n
Ehsan Variani<\/b><\/i>, Ke Wu<\/b><\/i>, Michael Riley<\/b><\/i>, David Rybach<\/b><\/i>, Matt Shannon<\/b><\/i>, Cyril Allauzen<\/b><\/i>\n<\/p>\n

\nLearning Predictions for Algorithms with Predictions<\/a>
\n
Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar, Sergei Vassilvitskii<\/b><\/i>\n<\/p>\n

\nMultimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts<\/a> (see\u00a0blog post<\/a>)
\n
Basil Mustafa<\/b><\/i>, Carlos Riquelme<\/b><\/i>, Joan Puigcerver<\/b><\/i>, Rodolphe Jenatton<\/b><\/i>, Neil Houlsby<\/b><\/i>\n<\/p>\n

\nIncrementality Bidding via Reinforcement Learning Under Mixed and Delayed Rewards<\/a>
\n
Ashwinkumar Badanidiyuru<\/b><\/i>, Zhe Feng<\/b><\/i>, Tianxi Li, Haifeng Xu*<\/sup><\/span><\/a>\n<\/p>\n

\nSolving Quantitative Reasoning Problems with Language Models<\/a> (see\u00a0blog post<\/a>)
\n
Aitor Lewkowycz<\/b><\/i>, Anders Andreassen<\/b><\/i>, David Dohan<\/b><\/i>, Ethan Dyer<\/b><\/i>, Henryk Michalewski<\/b><\/i>, Vinay Ramasesh<\/b><\/i>, Ambrose Slone<\/b><\/i>, Cem Anil<\/b><\/i>, Imanol Schlag<\/b><\/i>, Theo Gutman-Solo<\/b><\/i>, Yuhuai Wu<\/b><\/i>, Behnam Neyshabur<\/b><\/i>, Guy Gur-Ari<\/b><\/i>, Vedant Misra<\/b><\/i>\n<\/p>\n

\nAnonymized Histograms in Intermediate Privacy Models<\/a>
\n
Badih Ghazi<\/b><\/i>, Pritish Kamath<\/b><\/i>, Ravi Kumar<\/b><\/i>, Pasin Manurangsi<\/b><\/i>\n<\/p>\n

\nEfficient and Stable Fully Dynamic Facility Location<\/a>
\n
Sayan Bhattacharya, Nikos<\/b><\/i> Parotsidis<\/b><\/i>, Silvio<\/b><\/i> Lattanzi<\/b><\/i>\n<\/p>\n

\nAre All Losses Created Equal: A Neural Collapse Perspective<\/a>
\n
Jinxin Zhou, Chong You<\/b><\/i>, <\/b><\/i>Xiao Li, Kangning Liu, Sheng Liu, Qing Qu, Zhihui Zhu\n<\/p>\n

\nUniversal Rates for Interactive Learning<\/a>
\n
Steve Hanneke, Amin Karbasi<\/b><\/i>, Shay Moran<\/b><\/i>, Grigoris Velegkas\n<\/p>\n

\nNearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions<\/a>
\n
Jiafan He, Dongruo Zhou, Tong Zhang<\/b><\/i>, Quanquan Gu\n<\/p>\n

\nMulticlass Learnability Beyond the PAC Framework: Universal Rates and Partial Concept Classes<\/a>
\n
Alkis Kalavasis, Grigoris Velegkas, Amin Karbasi<\/b><\/i>\n<\/p>\n

\nTemporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning<\/a>
\n
Cenk Baykal<\/b><\/i>, Nishanth Dikkala<\/b><\/i>, Rina Panigrahy<\/b><\/i>, Cyrus Rashtchian<\/b><\/i>, Xin Wang<\/b><\/i>\n<\/p>\n

Pre-trained Language Models for Interactive Decision-Making<\/a>
\n
Shuang Li, Xavier Puig, Chris Paxton, Yilun Du, Clinton Wang, Linxi Fan, Tao Chen, De-An Huang, Ekin Aky\u00fcrek, Anima Anandkumar, Jacob Andreas, Igor Mordatch<\/b><\/i>, Antonio Torralba, Yuke Zhu\n<\/p>\n

Polynomial Neural Fields for Subband Decomposition and Manipulation<\/a>
\n
Guandao Yang*<\/sup><\/span><\/a>, Sagie Benaim, Varun Jampani<\/b><\/i>, Kyle Genova<\/b><\/i>, Jonathan T. Barron<\/b><\/i>, Thomas Funkhouser<\/b><\/i>, Bharath Hariharan, Serge Belongie\n<\/p>\n

Submodular Maximization in Clean Linear Time<\/a>
\n
Wenxin Li, Moran Feldman, Ehsan Kazemi<\/b><\/i>, Amin Karbasi<\/b><\/i>\n<\/p>\n

Reinforcement Learning with Logarithmic Regret and Policy Switches<\/a>
\n
Grigoris Velegkas, Zhuoran Yang, Amin Karbasi<\/b><\/i>\n<\/p>\n

Algorithms with Prediction Portfolios<\/a>
\n
Michael Dinitz, Sungjin Im, Thomas Lavastida, Benjamin Moseley, Sergei Vassilvitskii<\/b><\/i>\n<\/p>\n

Understanding and Improving Robustness of Vision Transformers Through Patch-Based Negative Augmentation<\/a>
\n
Yao Qin<\/b><\/i>, Chiyuan Zhang<\/b><\/i>, Ting Chen<\/b><\/i>, Balaji Lakshminarayanan<\/b><\/i>, Alex Beutel<\/b><\/i>, Xuezhi Wang<\/b><\/i>\n<\/p>\n

Best of Both Worlds Model Selection<\/a>
\n
Aldo Pacchiano, Christoph Dann<\/b><\/i>, Claudio Gentile<\/b><\/i>\n<\/p>\n

Fair Wrapping for Black-Box Predictions<\/a>
\n
Alexander Soen, Ibrahim Alabdulmohsin<\/b><\/i>, Sanmi Koyejo<\/b><\/i>, Yishay Mansour<\/b><\/i>, Nyalleng Moorosi<\/b><\/i>, Richard Nock<\/b><\/i>, Ke Sun, Lexing Xie\n<\/p>\n

A Reduction to Binary Approach for Debiasing Multiclass Datasets<\/a>
\n
Ibrahim Alabdulmohsin<\/b><\/i>, Jessica Schrouff<\/b><\/i>, Oluwasanmi Koyejo<\/b><\/i>\n<\/p>\n

Weighted Distillation with Unlabeled Examples<\/a>
\n
Fotis Iliopoulos<\/b><\/i>, Vasilis Kontonis<\/b><\/i>, Cenk Baykal<\/b><\/i>, Gaurav Menghani<\/b><\/i>, Khoa Trihn<\/b><\/i>,Erik Vee<\/b><\/i>\n<\/p>\n

A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases<\/a>
\n
James Harrison<\/b><\/i>, Luke Metz<\/b><\/i>, Jascha Sohl-Dickstein<\/b><\/i>\n<\/p>\n

Post-hoc Estimators for Learning to Defer to an Expert<\/a>
\n
Harikrishna Narasimhan<\/b><\/i>, Wittawat Jitkrittum<\/b><\/i>, Aditya Krishna Menon<\/b><\/i>, Ankit Singh Rawat<\/b><\/i>, Sanjiv Kumar<\/b><\/i>\n<\/p>\n

Model-Based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity<\/a>
\n
Alekh Agarwal<\/b><\/i>, Tong Zhang<\/b><\/i>\n<\/p>\n

On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL<\/a>
\n
Jinglin Chen, Aditya Modi, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal<\/b><\/i>\n<\/p>\n

Towards Learning Universal Hyperparameter Optimizers with Transformers<\/a> (see\u00a0blog post<\/a>)
\n
Yutian Chen, Xingyou Song<\/b><\/i>, Chansoo Lee<\/b><\/i>, Zi Wang<\/b><\/i>, Qiuyi Zhang<\/b><\/i>, David Dohan<\/b><\/i>, Kazuya Kawakami, Greg Kochanski<\/b><\/i>, Arnaud Doucet, Marc’aurelio Ranzato, Sagi Perel<\/b><\/i>, <\/b><\/i>Nando de Freitas\n<\/p>\n

Reproducibility in Optimization: Theoretical Framework and Limits<\/a>
\n
Kwangjun Ahn*<\/sup><\/span><\/a>, Prateek Jain<\/b><\/i>, Ziwei Ji<\/b><\/i>, Satyen Kale<\/b><\/i>, Praneeth Netrapalli<\/b><\/i>, Gil I. Shamir<\/b><\/i>\n<\/p>\n

Confident Adaptive Language Modeling<\/a>
\n
Tal Schuster<\/b><\/i>, Adam Fisch, Jai Gupta<\/b><\/i>, Mostafa Dehghani<\/b><\/i>, Dara Bahri<\/b><\/i>, Vinh Q. Tran<\/b><\/i>, Yi Tay<\/b><\/i>, Donald Metzler<\/b><\/i>\n<\/p>\n

Reinforcement Learning with Neural Radiance Fields<\/a>
\n
Danny Driess, Ingmar Schubert, Pete Florence<\/b><\/i>, Yunzhu Li, Marc Toussaint\n<\/p>\n

Invariant and Transportable Representations for Anti-Causal Domain Shifts<\/a>
\n
Yibo Jiang, Victor Veitch<\/b><\/i>\n<\/p>\n

Simple Mechanisms for Welfare Maximization in Rich Advertising Auctions<\/a>
\n
Gagan Aggarwal<\/b><\/i>, Kshipra Bhawalkar<\/b><\/i>, Aranyak Mehta<\/b><\/i>, <\/b><\/i>Divyarthi Mohan, Alexandros Psomas\n<\/p>\n

STaR: Bootstrapping Reasoning with Reasoning<\/a>
\n
Eric Zelikman, Yuhuai Wu<\/b><\/i>, Jesse Mu, Noah D. Goodman\n<\/p>\n

Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality<\/a>
\n
Teodor V. Marinov<\/b><\/i>, Mehryar Mohri<\/b><\/i>, Julian Zimmert<\/b><\/i>\n<\/p>\n

The Curse of Unrolling: Rate of Differentiating Through Optimization<\/a>
\n
Damien Scieur, Quentin Bertrand, Gauthier Gidel, Fabian Pedregosa<\/b><\/i>\n<\/p>\n

Visual Prompting via Image Inpainting<\/a>
\n
Amir Bar, Yossi Gandelsman, Trevor Darrell, Amir Globerson<\/b><\/i>, Alexei A Efros\n<\/p>\n

Multi-Class H-Consistency Bounds<\/a>
\n
Pranjal Awasthi<\/b><\/i>, Anqi Mao, Mehryar Mohri<\/b><\/i>, Yutao Zhong\n<\/p>\n

Anonymous Bandits for Multi-User Systems<\/a>
\n
Hossein Esfandiari<\/b><\/i>, Vahab Mirrokni<\/b><\/i>, Jon Schneider<\/b><\/i>\n<\/p>\n

Understanding the Eluder Dimension<\/a>
\n
Gene Li, Pritish Kamath<\/b><\/i>, Dylan J. Foster, Nathan Srebro\n<\/p>\n

Why So Pessimistic? Estimating Uncertainties for Offline RL Through Ensembles, and Why Their Independence Matters<\/a>
\n
Seyed Kamyar Seyed Ghasemipour<\/b><\/i>, Shixiang Shane Gu<\/b><\/i>, Ofir Nachum<\/b><\/i>\n<\/p>\n

A Best-of-Both-Worlds Algorithm for Bandits with Delayed Feedback<\/a>
\n
Saeed Masoudian, Julian Zimmert<\/b><\/i>, Yevgeny Seldin\n<\/p>\n

A Theoretical View on Sparsely Activated Networks<\/a>
\n
Cenk Baykal<\/b><\/i>, Nishanth Dikkala<\/b><\/i>, Rina Panigrahy<\/b><\/i>, Cyrus Rashtchian<\/b><\/i>, Xin Wang<\/b><\/i>\n<\/p>\n

Chain of Thought Prompting Elicits Reasoning in Large Language Models<\/a> (see\u00a0blog post<\/a>)
\n
Jason Wei<\/b><\/i>, Xuezhi Wang<\/b><\/i>, Dale Schuurmans<\/b><\/i>, Maarten Bosma<\/b><\/i>, Brian Ichter<\/b><\/i>, Fei Xia<\/b><\/i>, Ed Chi<\/b><\/i>, Quoc Le<\/b><\/i>, Denny Zhou<\/b><\/i>\n<\/p>\n

Decoupled Context Processing for Context Augmented Language Modeling<\/a>
\n
Zonglin Li<\/b><\/i>, Ruiqi Guo<\/b><\/i>, Sanjiv Kumar<\/b><\/i>\n<\/p>\n

Exploring Through Random Curiosity with General Value Functions<\/a>
\n
Aditya Ramesh, Louis Kirsch, Sjoerd van Steenkiste<\/b><\/i>, J\u00fcrgen Schmidhuber\n<\/p>\n

Object Scene Representation Transformer<\/a>
\n
Mehdi S. M. Sajjadi<\/b><\/i>, Daniel Duckworth<\/b><\/i>, Aravindh Mahendran<\/b><\/i>, Sjoerd van Steenkiste<\/b><\/i>, Filip Paveti\u0107<\/b><\/i>, Mario Lu\u010di\u0107<\/b><\/i>, Leonidas J. Guibas<\/b><\/i>, Klaus Greff<\/b><\/i>, Thomas Kipf<\/b><\/i>\n<\/p>\n

Joint Model-Policy Optimization of a Lower Bound for Model-Based RL<\/a>
\n
Benjamin Eysenbach<\/b><\/i>, Alexander Khazatsky, Sergey Levine<\/b><\/i>, Ruslan Salakhutdinov\n<\/p>\n

A Fourier Approach to Mixture Learning<\/a>
\n
Mingda Qiao*<\/sup><\/span><\/a>, Guru Guruganesh<\/b><\/i>, Ankit Singh Rawat<\/b><\/i>, Avinava Dubey<\/b><\/i>, Manzil Zaheer\n<\/p>\n

Why Neural Networks Find Simple Solutions: The Many Regularizers of Geometric Complexity<\/a>
\n
Benoit Dherin<\/b><\/i>, Michael Munn<\/b><\/i>, <\/b><\/i>Mihaela Rosca, <\/b><\/i>David Barrett\n<\/p>\n

Do Current Multi-task Optimization Methods in Deep Learning Even Help?<\/a>
\n
Derrick Xin<\/b><\/i>, Behrooz Ghorbani<\/b><\/i>, Ankush Garg<\/b><\/i>, Orhan Firat<\/b><\/i>, Justin Gilmer<\/b><\/i>\n<\/p>\n

Associating Objects and Their Effects in Video Through Coordination Games<\/a>
\n
Erika Lu<\/b><\/i>, Forrester Cole<\/b><\/i>, <\/b><\/i>Weidi Xie, Tali Dekel<\/b><\/i>, William Freeman<\/b><\/i>, <\/b><\/i>Andrew Zisserman, Michael Rubinstein<\/b><\/i>\n<\/p>\n

Increasing Confidence in Adversarial Robustness Evaluations<\/a>
\n
Roland S. Zimmermann*<\/sup><\/span><\/a>, Wieland Brendel, Florian Tram\u00e8r<\/b><\/i>, Nicholas Carlini<\/b><\/i>\n<\/p>\n

The Role of Baselines in Policy Gradient Optimization<\/a>
\n
Jincheng Mei<\/b><\/i>, Wesley Chung, Valentin Thomas, Bo Dai<\/b><\/i>, Csaba Szepesvari<\/b><\/i>, Dale Schuurmans<\/b><\/i>\n<\/p>\n

Scaling Multimodal Pre-training via Cross-Modality Gradient Harmonization<\/a>
\n
Junru Wu, Yi Liang<\/b><\/i>, Feng Han<\/b><\/i>, Hassan Akbari<\/b><\/i>, Zhangyang Wang, Cong Yu*<\/sup><\/span><\/a>\n<\/p>\n

S3GC: Scalable Self-Supervised Graph Clustering<\/a>
\n
Fnu Devvrit*<\/sup><\/span><\/a>, Aditya Sinha<\/b><\/i>, Inderjit Dhillon<\/b><\/i>, Prateek Jain<\/b><\/i>\n<\/p>\n

Algorithms and Hardness for Learning Linear Thresholds from Label Proportions<\/a>
\n
Rishi Saket<\/b><\/i>\n<\/p>\n

ALMA: Hierarchical Learning for Composite Multi-Agent Tasks<\/a>
\n
Shariq Iqbal, Robby Costales, Fei Sha<\/b><\/i>\n<\/p>\n

DC-BENCH: Dataset Condensation Benchmark<\/a>
\n
Justin Cui, Ruochen Wang, Si Si<\/b><\/i>, Cho-Jui Hsieh\n<\/p>\n

Does GNN Pre-training Help Molecular Representation?<\/a>
\n
Ruoxi Sun<\/b><\/i>, Hanjun Dai<\/b><\/i>, Adams Yu<\/b><\/i>\n<\/p>\n

Drawing Out of Distribution with Neuro-Symbolic Generative Models<\/a>
\n
Yichao Liang, Joshua B. Tenenbaum, Tuan Anh Le<\/b><\/i>, N. Siddharth\n<\/p>\n

Mixture-of-Experts with Expert Choice Routing<\/a> <\/b><\/i>(see\u00a0blog post<\/a>)
\n
Yanqi Zhou<\/b><\/i>, Tao Lei<\/b><\/i>, Hanxiao Liu<\/b><\/i>, Nan Du<\/b><\/i>, Yanping Huang<\/b><\/i>, Vincent Zhao<\/b><\/i>, Andrew Dai<\/b><\/i>, Zhifeng Chen<\/b><\/i>, Quoc Le<\/b><\/i>, James Laudon<\/b><\/i>\n<\/p>\n

Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback<\/a>
\n
Tiancheng Jin, Tal Lancewicki, Haipeng Luo, Yishay Mansour<\/b><\/i>, Aviv Rosenberg\n<\/p>\n

Precise Learning Curves and Higher-Order Scalings for Dot-Product Kernel Regression<\/a>
\n
Lechao Xiao<\/b><\/i>, Jeffrey Pennington, Theodor Misiakiewicz, Hong Hu, Yue Lu<\/b><\/i>\n<\/p>\n

Rate-Optimal Online Convex Optimization in Adaptive Linear Control<\/a>
\n
Asaf Cassel, Alon<\/b><\/i> Cohen<\/b><\/i>, Tomer Koren<\/b><\/i>\n<\/p>\n

Why Neural Networks Find Simple Solutions: The Many Regularizers of Geometric Complexity<\/a>
\n
Benoit Dherin<\/b><\/i>, Michael Munn<\/b><\/i>, Mihaela Rosca, David G.T. Barrett\n<\/p>\n

Private Isotonic Regression<\/a>
\n
Badih Ghazi<\/b><\/i>, Pritish Kamath<\/b><\/i>, Ravi Kumar<\/b><\/i>, Pasin Manurangsi<\/b><\/i>\n<\/p>\n

Sketching Based Representations for Robust Image Classification with Provable Guarantees<\/a>
\n
Nishanth Dikkala<\/b><\/i>, Sankeerth Rao Karingula<\/b><\/i>, Raghu Meka, Jelani Nelson, Rina Panigrahy<\/b><\/i>, Xin Wang<\/b><\/i>\n<\/p>\n

The Role of Baselines in Policy Gradient Optimization<\/a>
\n
Jincheng Mei<\/b><\/i>, Wesley Chung, Valentin Thomas, Bo Dai<\/b><\/i>, Csaba Szepesvari, Dale Schuurmans<\/b><\/i>\n<\/p>\n

Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens<\/a>
\n
Elad Ben Avraham, Roei Herzig, Karttikeya Mangalam, Amir Bar, Anna Rohrbach, Leonid Karlinsky, Trevor Darrell, Amir Globerson<\/b><\/i>\n<\/p>\n

Near-Optimal Private and Scalable k-Clustering<\/a>
\n
Vincent Cohen-Addad<\/b><\/i>, Alessandro Epasto<\/b><\/i>, Vahab Mirrokni<\/b><\/i>, <\/b><\/i>Shyam Narayanan*<\/sup><\/span><\/a>, Peilin Zhong<\/b><\/i>\n<\/p>\n

When Does Differentially Private Learning Not Suffer in High Dimensions?<\/a>
\n
Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin A Inan, Janardhan Kulkarni, YinTat Lee, Abhradeep Guha Thakurta<\/b><\/i>\n<\/p>\n

End-to-End Learning to Index and Search in Large Output Spaces<\/a>
\n
Nilesh Gupta, Patrick H. Chen, Hsiang-Fu, Yu, Cho-Jui Hsieh, Inderjit S. Dhillon<\/b><\/i>\n<\/p>\n

A Boosting Approach to Reinforcement Learning<\/a>
\n
Nataly Brukhim, Elad Hazan<\/b><\/i>, Karan Singh\n<\/p>\n

FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction<\/a>
\n
Samiul Alam, Luyang Liu<\/b><\/i>, Ming Yan, Mi Zhang\n<\/p>\n

Non-Convex Online Learning via Algorithmic Equivalence<\/a>
\n
Udaya Ghai<\/b><\/i>, Zhou Lu<\/b><\/i>, Elad Hazan<\/b><\/i>\n<\/p>\n

Is this the Right Neighborhood? Accurate and Query Efficient Model Agnostic Explanations<\/a>
\n
Amit Dhurandhar, Karthikeyan Natesan Ramamurthy, Karthikeyan Shanmugam<\/b><\/i>\n<\/p>\n

SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos<\/a>
\n
Gamaleldin F. Elsayed<\/b><\/i>, Aravindh Mahendran<\/b><\/i>, Sjoerd van Steenkiste<\/b><\/i>, Klaus Greff<\/b><\/i>, Michael C. Mozer<\/b><\/i>, Thomas Kipf<\/b><\/i>\n<\/p>\n

UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes<\/a>
\n
Alexander Kolesnikov<\/b><\/i>, Andr\u00e9 Susano Pinto<\/b><\/i>, Lucas Beyer<\/b><\/i>, Xiaohua Zhai<\/b><\/i>, Jeremiah Harmsen<\/b><\/i>, Neil Houlsby<\/b><\/i>\n<\/p>\n

Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions<\/a>
\n
Courtney Paquette<\/b><\/i>, <\/b><\/i>Elliot Paquette, Ben Adlam<\/b><\/i>, Jeffrey Pennington<\/b><\/i>\n<\/p>\n

Multi-game Decision Transformers<\/a> (see\u00a0blog post<\/a>)
\n
Kuang-Huei Lee<\/b><\/i>, Ofir Nachum<\/b><\/i>, Mengjiao Yang<\/b><\/i>, Lisa Lee<\/b><\/i>, Daniel Freeman<\/b><\/i>, Winnie Xu<\/b><\/i>, Sergio Guadarrama<\/b><\/i>, Ian Fischer<\/b><\/i>, Eric Jang<\/b><\/i>, Henryk Michalewski<\/b><\/i>, Igor Mordatch<\/b><\/i>\n<\/p>\n

Subsidiary Prototype Alignment for Universal Domain Adaptation<\/a>
\n
Jogendra Nath Kundu<\/b><\/i>, Suvaansh Bhambri<\/b><\/i>, Akshay Ravindra Kulkarni<\/b><\/i>, Hiran Sarkar<\/b><\/i>, Varun Jampani<\/b><\/i>, Venkatesh Babu Radhakrishnan<\/b><\/i>\n<\/p>\n

SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections<\/a>
\n
Mark Boss*<\/sup><\/span><\/a>, Andreas Engelhardt*<\/sup><\/span><\/a>, Abhishek Kar<\/b><\/i>, Yuanzhen Li<\/b><\/i>, Deqing Sun<\/b><\/i>, Jonathan T. Barron<\/b><\/i>, Hendrik P. A. Lensch, Varun Jampani<\/b><\/i>\n<\/p>\n

Chefs\u2019 Random Tables: Non-Trigonometric Random Features<\/a>
\n
Valerii Likhosherstov, Krzysztof Marcin Choromanski<\/b><\/i>, Avinava Dubey<\/b><\/i>, Frederick Liu<\/b><\/i>, Tamas Sarlos<\/b><\/i>, Adrian Weller\n<\/p>\n

Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks<\/a>
\n
Mansheej Paul, Brett W Larsen, Surya Ganguli, Jonathan Frankle, Gintare Karolina Dziugaite<\/b><\/i>\n<\/p>\n

DP-PCA: Statistically Optimal and Differentially Private PCA<\/a>
\n
Xiyang Liu, Weihao Kong<\/b><\/i>, Prateek Jain<\/b><\/i>, Sewoong Oh<\/b><\/i>\n<\/p>\n

Emergent Communication: Generalization and Overfitting in Lewis Games<\/a>
\n
Mathieu Rita, Corentin Tallec, Paul Michel, Jean-Bastien Grill, Olivier Pietquin<\/b><\/i>, Emmanuel Dupoux, Florian Strub\n<\/p>\n

Handcrafted Backdoors in Deep Neural Networks<\/a>
\n
Sanghyun Hong, Nicholas Carlini<\/b><\/i>, Alexey Kurakin<\/b><\/i>\n<\/p>\n

I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification<\/a>
\n
Muhammad Ferjad Naeem, Yongqin Xian, Luc Van Gool, Federico Tombari<\/b><\/i>\n<\/p>\n

Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams<\/a>
\n
Sergey Denisov, Brendan McMahan<\/b><\/i>, Keith Rush<\/b><\/i>, Adam Smith, Abhradeep Guha Thakurta<\/b><\/i>\n<\/p>\n

Optimal Scaling for Locally Balanced Proposals in Discrete Spaces<\/a>
\n
Haoran Sun*<\/sup><\/span><\/a>, Hanjun Dai<\/b><\/i>, Dale Schuurmans<\/b><\/i>\n<\/p>\n

Near-Optimal Correlation Clustering with Privacy<\/a>
\n
Vincent Cohen-Addad<\/b><\/i>, Chenglin Fan, Silvio Lattanzi<\/b><\/i>, Slobodan Mitrovi\u0107, Ashkan Norouzi-Fard<\/b><\/i>, Nikos Parotsidis<\/b><\/i>, <\/b><\/i>Jakub Tarnawski\n<\/p>\n

Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers<\/a>
\n
Albert Q. Jiang, Wenda Li, Szymon Tworkowski, Konrad Czechowski, Tomasz Odrzyg\u00f3\u017ad\u017a, Piotr Mi\u0142o\u015b, Yuhuai Wu<\/b><\/i>, Mateja Jamnik\n<\/p>\n

TPU-KNN: K Nearest Neighbor Search at Peak FLOP\/s<\/a>
\n
Felix Chern<\/b><\/i>, Blake Hechtman<\/b><\/i>, Andy Davis<\/b><\/i>, Ruiqi Guo<\/b><\/i>, David Majnemer<\/b><\/i>, Sanjiv Kumar<\/b><\/i>\n<\/p>\n

When Does Dough Become a Bagel? Analyzing the Remaining Mistakes on ImageNet<\/a>
\n
Vijay Vasudevan<\/b><\/i>, Benjamin Caine<\/b><\/i>, Raphael Gontijo-Lopes<\/b><\/i>, Sara Fridovich-Keil<\/b><\/i>, Rebecca Roelofs<\/b><\/i>\n<\/p>\n

DASCO: Dual-Generator Adversarial Support Constrained Offline Reinforcement Learning<\/a>
\n
Quan Vuong<\/b><\/i>, Aviral Kumar<\/b><\/i>, Sergey Levine<\/b><\/i>, Yevgen Chebotar<\/b><\/i>\n<\/p>\n

A Characterization of Semi-Supervised Adversarially Robust PAC Learnability<\/a>
\n
Idan Attias, Steve Hanneke, Yishay Mansour<\/b><\/i>\n<\/p>\n

Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified Backpropagation<\/a>
\n
Ziyu Jiang, Xuxi Chen, Xueqin Huang, Xianzhi Du<\/b><\/i>, Denny Zhou<\/b><\/i>, Zhangyang Wang\n<\/p>\n

Subquadratic Kronecker Regression with Applications to Tensor Decomposition<\/a>
\n
Matthew Fahrbach<\/b><\/i>, Gang Fu<\/b><\/i>, Mehrdad Ghadiri\n<\/p>\n

Zero-Shot Transfer Learning Within a Heterogeneous Graph via Knowledge Transfer Networks<\/a>
\n
Minji Yoon*<\/sup><\/span><\/a>, John Palowitch<\/b><\/i>, Dustin Zelle<\/b><\/i>, Ziniu Hu*<\/sup><\/span><\/a>, Ruslan Salakhutdinov, Bryan Perozzi<\/b><\/i>\n<\/p>\n

Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank<\/a>
\n
Alessandro Epasto<\/b><\/i>, Vahab Mirrokni<\/b><\/i>, Bryan Perozzi<\/b><\/i>, Anton Tsitsulin<\/b><\/i>, Peilin Zhong<\/b><\/i>\n<\/p>\n

Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress<\/a> (see\u00a0blog post<\/a>)
\n
Rishabh Agarwal<\/b><\/i>, Max Schwarzer<\/b><\/i>, Pablo Samuel Castro<\/b><\/i>, Aaron Courville, Marc G. Bellemare<\/b><\/i>\n<\/p>\n

Private and Communication-Efficient Algorithms for Entropy Estimation<\/a>
\n
Gecia Bravo-Hermsdorff, Robert Busa-Fekete<\/b><\/i>, Mohammad Ghavamzadeh<\/b><\/i>, Andres Munoz Medina<\/b><\/i>, Umar Syed<\/b><\/i>\n<\/p>\n

Oracle Inequalities for Model Selection in Offline Reinforcement Learning<\/a>
\n
Jonathan Lee, George Tucker<\/b><\/i>, Ofir Nachum<\/b><\/i>, Bo Dai<\/b><\/i>, Emma Brunskill\n<\/p>\n

Diagnosing Failures of Fairness Transfer Across Distribution Shift in Real-World Medical Settings<\/a>
\n
Jessica Schrouff*<\/sup><\/span><\/a>, Natalie Harris<\/b><\/i>, Oluwasanmi O Koyejo<\/b><\/i>, Ibrahim Alabdulmohsin<\/b><\/i>, Eva Schnider*<\/sup><\/span><\/a>, Krista Opsahl-Ong<\/b><\/i>, Alexander Brown<\/b><\/i>, Subhrajit Roy<\/b><\/i>, Diana Mincu<\/b><\/i>, Christina Chen<\/b><\/i>, Awa Dieng<\/b><\/i>, Yuan Liu<\/b><\/i>, Vivek Natarajan<\/b><\/i>, Alan Karthikesalingam<\/b><\/i>, Katherine A Heller<\/b><\/i>, Silvia Chiappa, Alexander D’Amour<\/b><\/i>\n<\/p>\n

LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery<\/a>
\n
Chun-Han Yao, Wei-Chih Hung, Yuanzhen Li<\/b><\/i>, Michael Rubinstein<\/b><\/i>, Ming-Hsuan Yang<\/b><\/i>, Varun Jampani<\/b><\/i>\n<\/p>\n

Patching Open-Vocabulary Models by Interpolating Weights<\/a>
\n
Gabriel Ilharco, Mitchell Wortsman, Samir Yitzhak Gadre, Shuran Song, Hannaneh Hajishirzi, Simon Kornblith<\/b><\/i>, Ali Farhadi, Ludwig Schmidt\n<\/p>\n

TUSK: Task-Agnostic Unsupervised Keypoints<\/a>
\n
Yuhe Jin, Weiwei Sun, Jan Hosang<\/b><\/i>, Eduard Trulls<\/b><\/i>, Kwang Moo Yi\n<\/p>\n

Active Learning of Classifiers with Label and Seed Queries<\/a>
\n
Marco Bressan, Nicol\u00f2 Cesa-Bianchi, Silvio Lattanzi<\/b><\/i>, Andrea Paudice, Maximilian Thiessen\n<\/p>\n

Autoformalization with Large Language Models<\/a>
\n
Yuhuai Wu<\/b><\/i>, Albert Q. Jiang, Wenda Li, Markus N. Rabe<\/b><\/i>, Charles Staats<\/b><\/i>, Mateja Jamnik, Christian Szegedy<\/b><\/i>\n<\/p>\n

Benign Underfitting of Stochastic Gradient Descent<\/a>
\n
Tomer Koren<\/b><\/i>, Roi Livni, Yishay Mansour<\/b><\/i>, Uri Sherman\n<\/p>\n

Chain of Thought Imitation with Procedure Cloning<\/a>
\n
Mengjiao Yang<\/b><\/i>, Dale Schuurmans<\/b><\/i>, Pieter Abbeel, Ofir Nachum<\/b><\/i>\n<\/p>\n

Efficient and Modular Implicit Differentiation<\/a>
\n
Mathieu Blondel<\/b><\/i>, Quentin Berthet<\/b><\/i>, Marco Cuturi<\/b><\/i>, Roy Frostig<\/b><\/i>, Stephan Hoyer<\/b><\/i>, Felipe Llinares-L\u00f3pez<\/b><\/i>, Fabian Pedregosa<\/b><\/i>, Jean-Philippe Vert<\/b><\/i>\n<\/p>\n

Insights into Pre-training via Simpler Synthetic Tasks<\/a>
\n
Yuhuai Wu<\/b><\/i>, <\/b><\/i>Felix Li, Percy Liang\n<\/p>\n

Self-Supervised Learning with an Information Maximization Criterion<\/a>
\n
Serdar Ozsoy, Shadi Hamdan, Sercan \u00d6. Arik<\/b><\/i>, Deniz Yuret, Alper T. Erdogan\n<\/p>\n

Trimmed Maximum Likelihood Estimation for Robust Generalized Linear Model<\/a>
\n
Weihao Kong<\/b><\/i>, Rajat Sen<\/b><\/i>, Pranjal Awasthi<\/b><\/i>, Abhimanyu Das<\/b><\/i>\n<\/p>\n

Using Embeddings for Causal Estimation of Peer Influence in Social Networks<\/a>
\n
Irina Cristali, Victor Veitch<\/b><\/i>\n<\/p>\n

VCT: A Video Compression Transformer<\/a>
\n
Fabian Mentzer<\/b><\/i>, George Toderici<\/b><\/i>, David Minnen<\/b><\/i>, Sung-Jin Hwang<\/b><\/i>, Sergi Caelles<\/b><\/i>, Mario Lucic<\/b><\/i>, Eirikur Agustsson<\/b><\/i>\n<\/p>\n

Video Diffusion Models<\/a>
\n
Jonathan Ho<\/b><\/i>, Tim Salimans<\/b><\/i>, Alexey Gritsenko<\/b><\/i>, William Chan<\/b><\/i>, Mohammad Norouzi<\/b><\/i>, David J. Fleet<\/b><\/i>\n<\/p>\n

Large Language Models are Zero-Shot Reasoners<\/a>
\n
Takeshi Kojima, Shixiang Shane Gu<\/b><\/i>, <\/b><\/i>Machel Reid, Yutaka Matsuo, Yusuke Iwasawa\n<\/p>\n

Improved Coresets for Euclidean k-Means<\/a>
\n
Vincent Cohen-Addad<\/b><\/i>, Kasper Green Larsen, David Saulpic, Chris Schwiegelshohn, Omar Ali Sheikh-Omar\n<\/p>\n

On the Adversarial Robustness of Mixture of Experts<\/a>
\n
Joan Puigcerver<\/b><\/i>, Rodolphe Jenatton<\/b><\/i>, Carlos Riquelme Ruiz<\/b><\/i>, Pranjal Awasthi<\/b><\/i>, Srinadh Bhojanapalli<\/b><\/i>\n<\/p>\n

Stars: Tera-Scale Graph Building for Clustering and Learning<\/a>
\n
CJ Carey<\/b><\/i>, Jonathan Halcrow<\/b><\/i>, Rajesh Jayaram<\/b><\/i>, Vahab Mirrokni<\/b><\/i>, Warren Schudy<\/b><\/i>, Peilin Zhong<\/b><\/i>\n<\/p>\n

VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement<\/a>
\n
Erik Wijmans, Irfan Essa<\/b><\/i>, Dhruv Batra\n<\/p>\n

TaSIL: Taylor Series Imitation Learning<\/a>
\n
Daniel Pfrommer, Thomas TCK Zhang, Stephen Tu<\/b><\/i>, Nikolai Matni\n<\/p>\n

RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks<\/a>
\n
Leo Kozachkov, Michaela M Ennis, Jean-Jacques Slotine<\/b><\/i>\n<\/p>\n

Integral Probability Metrics PAC-Bayes Bounds<\/a>
\n
Ron Amit, Baruch Epstein, Shay Moran<\/b><\/i>, Ron Meir\n<\/p>\n

D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video<\/a>
\n
Tianhao Wu, Fangcheng Zhong, Andrea Tagliasacchi<\/b><\/i>, Forrester Cole<\/b><\/i>, Cengiz Oztireli<\/b><\/i>\n<\/p>\n

Posted Pricing and Dynamic Prior-Independent Mechanisms with Value Maximizers<\/a>
\n
Yuan Deng<\/b><\/i>, Vahab Mirrokni<\/b><\/i>, <\/b><\/i>Hanrui Zhang\n<\/p>\n

Transformer Memory as a Differentiable Search Index<\/a>
\n
Yi Tay<\/b><\/i>, Vinh Q. Tran<\/b><\/i>, Mostafa Dehghani<\/b><\/i>, Jianmo Ni<\/b><\/i>, Dara Bahri<\/b><\/i>, Harsh Mehta<\/b><\/i>, Zhen Qin<\/b><\/i>, Kai Hui<\/b><\/i>, Zhe Zhao<\/b><\/i>, Jai Gupta<\/b><\/i>, Tal Schuster<\/b><\/i>, William W. Cohen<\/b><\/i>, Donald Metzler<\/b><\/i><\/p>\n

\n<\/p>\n


*<\/sup><\/a>Work done while at Google. \u00a0\u21a9<\/sup><\/a>
\n<\/span>\n<\/div>\n

[ad_2]
\n
Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

[ad_1] Posted by Cat Armato, Program Manager, Google This week marks the beginning of the 36th annual Conference<\/p>\n","protected":false},"author":2,"featured_media":136,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[],"class_list":["post-135","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-google-ai"],"_links":{"self":[{"href":"https:\/\/todaysainews.com\/index.php\/wp-json\/wp\/v2\/posts\/135","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/todaysainews.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/todaysainews.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/todaysainews.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/todaysainews.com\/index.php\/wp-json\/wp\/v2\/comments?post=135"}],"version-history":[{"count":1,"href":"https:\/\/todaysainews.com\/index.php\/wp-json\/wp\/v2\/posts\/135\/revisions"}],"predecessor-version":[{"id":2994,"href":"https:\/\/todaysainews.com\/index.php\/wp-json\/wp\/v2\/posts\/135\/revisions\/2994"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/todaysainews.com\/index.php\/wp-json\/wp\/v2\/media\/136"}],"wp:attachment":[{"href":"https:\/\/todaysainews.com\/index.php\/wp-json\/wp\/v2\/media?parent=135"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/todaysainews.com\/index.php\/wp-json\/wp\/v2\/categories?post=135"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/todaysainews.com\/index.php\/wp-json\/wp\/v2\/tags?post=135"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}