Research
Publications
-
- Date
- Title
- Generative Ghosts: Anticipating Benefits and Risks of AI Afterlives
- Authors
- Meredith Ringel Morris and Jed R. Brubaker
- Venue
- ACM CHI 2025
-
- Date
- Title
- Decoding-based Regression
- Authors
- Xingyou Song, Dara Bahri
- Venue
- arXiv
-
- Date
- Title
- MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
- Authors
- Sebastian Farquhar, Vikrant Varma, David Lindner, David Elson, Caleb Biddulph, Ian Goodfellow, Rohin Shah
- Venue
- arXiv
-
- Date
- Title
- Are vision-language models shape or texture biased and can we steer them?
- Authors
- Paul Gavrikov, Jovita Lukasik, Steffen Jung, Robert Geirhos, Muhammad Jehanzeb Mirza, Margret Keuper, Janis Keuper
- Venue
- ICLR 2025
-
- Date
- Title
- Exposing Limitations of Language Model Agents in Sequential-Task Compositions on the Web
- Authors
- Hiroki Furuta, Yutaka Matsuo, Aleksandra Faust, Izzeddin Gur
- Venue
- Transactions on Machine Learning Research (TMLR)
-
- Date
- Title
- Deliberation in Latent Space via Differentiable Cache Augmentation
- Authors
- Luyang Liu, Jonas Pfeiffer, Jiaxing Wu, Jun Xie, Arthur Szlam
- Venue
- arXiv
-
- Date
- Title
- Machine Unlearning Doesn’t Do What You Think: Lessons for Generative AI Policy, Research, and Practice
- Authors
- A. Feder Cooper, Christopher A. Choquette-Choo, Miranda Bogen, Matthew Jagielski, Katja Filippova, Ken Ziyu Liu, Alexandra Chouldechova, Jamie Hayes, Yangsibo Huang, Niloofar Mireshghallah, Ilia Shumailov, Eleni Triantafillou, Peter Kairouz, Nicole Mitchell, Percy Liang, Daniel E. Ho, Yejin Choi, Sanmi Koyejo, Fernando Delgado, James Grimmelmann, Vitaly Shmatikov, Christopher De Sa, Solon Barocas, Amy Cyphert, Mark Lemley, danah boyd, Jennifer Wortman Vaughan, Miles Brundage, David Bau, Seth Neel, Abigail Z. Jacobs, Andreas Terzis, Hanna Wallach, Nicolas Papernot, Katherine Lee
- Venue
- arXiv
-
- Date
- Title
- What type of inference is planning?
- Authors
- Miguel Lazaro-Gredilla, Li Yang Ku, Kevin Murphy, Dileep George
- Venue
- NeurIPS 2024
-
- Date
- Title
- Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty
- Authors
- Zi Wang, Meera Hahn, Wenjun Zeng, Nithish Kannen, Been Kim, Rich Galt, Kartikeya Badola
- Venue
- arXiv
-
- Date
- Title
- Mastering Board Games by External and Internal Planning with Language Models
- Authors
- John Schultz, Jakub Adamek, Matej Jusup, Marc Lanctot, Michael Kaisers, Sarah Perrin, Daniel Hennes, Jeremy Shar, Cannada Lewis, Anian Ruoss, Tom Zahavy, Petar Veličković, Laurel Prince, Satinder Singh, Eric Malmi, Nenad Tomašev
- Venue
- arXiv
-
- Date
- Title
- How Well Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?
- Authors
- Sohee Yang, Nora Kassner, Elena Gribovskaya, Sebastian Riedel, Mor Geva
- Venue
- arXiv
-
- Date
- Title
- Understanding LLM Embeddings for Regression
- Authors
- Eric Tang, Bangding Yang, Xingyou Song
- Venue
- arXiv
-
- Date
- Title
- AI can help humans find common ground in democratic deliberation
- Authors
- Michael Henry Tessler†, Michiel A Bakker†, Daniel Jarrett, Hannah Sheahan*, Martin Chadwick, Raphael Koster, Georgina Evans, Lucy Campbell-Gillingham, Teddy Collins*, David C Parkes*, Matthew Botvinick, Christopher Summerfield*
- Venue
- Science
-
- Date
- Title
- Prompting Considered Harmful
- Authors
- Meredith Ringel Morris
- Venue
- Communications of the ACM
-
- Date
- Title
- Predicting from Strings: Language Model Embeddings for Bayesian Optimization
- Authors
- Tung Nguyen, Qiuyi Zhang, Bangding Yang, Chansoo Lee, Jorg Bornschein, Yingjie Miao, Sagi Perel, Yutian Chen, Xingyou Song
- Venue
- arXiv
-
- Date
- Title
- Diffusion model predictive control
- Authors
- Stannis Zhou, Siva Swaminathan, Rajkumar Vasudeva Raju, Swaroop Guntupalli, Wolfgang Lehrach, Joseph Ortiz, Antoine Dedieu, Miguel Lazaro-Gredilla, Kevin Murphy
- Venue
- arXiv
-
- Date
- Title
- Geometric-Averaged Preference Optimization for Soft Preference Labels
- Authors
- Hiroki Furuta, Kuang-Huei Lee, Shixiang Shane Gu, Yutaka Matsuo, Aleksandra Faust, Heiga Zen, Izzeddin Gur
- Venue
- NeurIPS 2024
-
- Date
- Title
- Learned feature representations are biased by complexity, learning order, position, and more
- Authors
- Andrew Lampinen, Stephanie Chan, Katherine Hermann
- Venue
- Transactions on Machine Learning Research (TMLR)
-
- Date
- Title
- Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries
- Authors
- Kiran Vodrahalli, Santiago Ontanon, Nilesh Tripuraneni, Kelvin Xu, Sanil Jain, Rakesh Shivanna, Jeffrey Hui, Nishanth Dikkala, Mehran Kazemi, Bahar Fatemi, Rohan Anil, Ethan Dyer, Siamak Shakeri, Roopali Vij, Harsh Mehta, Vinay Ramasesh, Quoc Le, Ed Chi, Yifeng Lu, Orhan Firat, Angeliki Lazaridou, Jean-Baptiste Lespiau, Nithya Attaluri, Kate Olszewska
- Venue
- arXiv
-
- Date
- Title
- The Vizier Gaussian Process Bandit Algorithm
- Authors
- Xingyou Song, Qiuyi Zhang, Chansoo Lee, Emily Fertig, Tzu-Kuo Huang, Lior Belenki, Greg Kochanski, Setareh Ariafar, Srinivas Vasudevan, Sagi Perel, Daniel Golovin
- Venue
- arXiv