1. Best-of-N Jailbreaking. John Hughes, Sara Price, Aengus Lynch, Rylan Schaeffer, Fazl Barez, Arushi Somani, Sanmi Koyejo, Henry Sleight, Erik Jones, Ethan Perez, Mrinank Sharma. NeurIPS, 2025.
  2. Quantifying Elicitation of Latent Capabilities in Language Models. Elizabeth Donoway, Hailey Joren, Arushi Somani, Henry Sleight, Julian Michael, Michael R. DeWeese, John Schulman, Ethan Perez, Fabien Roger, Jan Leike. NeurIPS, 2025.
  3. Unsupervised Elicitation of Language Models. Jiaxin Wen, Zachary Ankner, Arushi Somani, Peter Hase, Samuel Marks, Jacob Goldman-Wetzler, Linda Petrini, Henry Sleight, Collin Burns, He He, Shi Feng, Ethan Perez, Jan Leike. arXiv, 2025.
  4. Reasoning Models Don’t Always Say What They Think. Yanda Chen, Joe Benton, Ansh Radhakrishnan, Jonathan Uesato, Carson Denison, John Schulman, Arushi Somani, Peter Hase, Misha Wagner, Fabien Roger, Vlad Mikulik, Samuel R. Bowman, Jan Leike, Jared Kaplan, Ethan Perez. arXiv, 2025.
  5. Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions. Saffron Huang, Esin Durmus, Miles McCain, Kunal Handa, Alex Tamkin, Jerry Hong, Michael Stern, Arushi Somani, Xiuruo Zhang, Deep Ganguli. arXiv, 2025.
  6. Fuyu-8B: A Multimodal Architecture for AI Agents. Rohan Bavishi, Erich Elsen, Curtis Hawthorne, Maxwell Nye, Augustus Odena, Arushi Somani, Sağnak Taşırlar. Adept blog, 2023.
  7. Releasing Persimmon-8B. Erich Elsen, Augustus Odena, Maxwell Nye, Sağnak Taşırlar, Tri Dao, Curtis Hawthorne, Deepak Moparthi, Arushi Somani. Adept blog, 2023.
  8. The Adventure of the Errant Hardware. Erich Elsen, Curtis Hawthorne, Arushi Somani. Adept blog, 2023.

Patents

  1. Multimodal Agent for Efficient Image-Text Interface Automation. Erich Elsen, Curtis Hawthorne, Augustus Odena, Maxwell Nye, Arushi Somani, Kyle Vigen, Rohan Bavishi, Sağnak Taşırlar, Warut Vijitbenjaronk, Ulas Kirazci, Joe Gershenson, Shaya Zarkesh. US Patent 12,387,036.
  2. Magnitude Invariant Multimodal Agent for Efficient Image-Text Interface Automation. Curtis Hawthorne, Erich Elsen, Augustus Odena, Maxwell Nye, Arushi Somani, Kyle Vigen, Rohan Bavishi, Sağnak Taşırlar, Warut Vijitbenjaronk, Ulas Kirazci, Joe Gershenson, Shaya Zarkesh. US Patent 12,619,815.
  3. Training Data for Training Artificial Intelligence Agents to Automate Multimodal Software Usage. Sağnak Taşırlar, David Abrahams, Lina Lukyantseva, …, Arushi Somani, and 18 others. US Patent 12,585,862.
  4. Artificial Intelligence Agents to Automate Multimodal Interface Task Workflows. Rohan Bavishi, Lina Lukyantseva, Shaya Zarkesh, …, Arushi Somani, and 17 others. US Patent 12,566,913.