1 code implementation • 25 Jan 2024 • Letian Fu, Long Lian, Renhao Wang, Baifeng Shi, Xudong Wang, Adam Yala, Trevor Darrell, Alexei A. Efros, Ken Goldberg
In this work, we re-examine inter-patch dependencies in the decoding mechanism of masked autoencoders (MAE).
no code implementations • 29 Sep 2023 • Long Lian, Baifeng Shi, Adam Yala, Trevor Darrell, Boyi Li
We show that LLMs are able to understand complex spatiotemporal dynamics from text alone and generate layouts that align closely with both the prompts and the object motion patterns typically observed in the real world.
1 code implementation • 16 Jun 2023 • Victor Quach, Adam Fisch, Tal Schuster, Adam Yala, Jae Ho Sohn, Tommi S. Jaakkola, Regina Barzilay
Translating this process to conformal prediction, we calibrate a stopping rule for sampling different outputs from the LM that get added to a growing set of candidates until we are confident that the output set is sufficient.
1 code implementation • 23 May 2023 • Long Lian, Boyi Li, Adam Yala, Trevor Darrell
Our method significantly outperforms the base diffusion model and several strong baselines in accurately generating images according to prompts that require various capabilities, doubling the generation accuracy across four tasks on average.
no code implementations • 31 Mar 2023 • Homa Esfahanizadeh, Adam Yala, Rafael G. L. D'Oliveira, Andrea J. D. Jaba, Victor Quach, Ken R. Duffy, Tommi S. Jaakkola, Vinod Vaikuntanathan, Manya Ghobadi, Regina Barzilay, Muriel Médard
Allowing organizations to share their data for training of machine learning (ML) models without unintended information leakage is an open problem in practice.
1 code implementation • 1 Mar 2022 • Janice Yang, Ludvig Karstens, Casey Ross, Adam Yala
This study is a technical supplement to "AI gone astray: How subtle shifts in patient data send popular algorithms reeling, undermining patient safety."
no code implementations • 28 Jan 2022 • Adam Yala, Victor Quach, Homa Esfahanizadeh, Rafael G. L. D'Oliveira, Ken R. Duffy, Muriel Médard, Tommi S. Jaakkola, Regina Barzilay
We quantify privacy as the number of attacker guesses required to re-identify a single image (guesswork).
1 code implementation • 4 Jun 2021 • Adam Yala, Homa Esfahanizadeh, Rafael G. L. D' Oliveira, Ken R. Duffy, Manya Ghobadi, Tommi S. Jaakkola, Vinod Vaikuntanathan, Regina Barzilay, Muriel Medard
We propose to approximate this family of encoding functions through random deep neural networks.
1 code implementation • EMNLP 2016 • Karthik Narasimhan, Adam Yala, Regina Barzilay
Most successful information extraction systems operate with access to a large collection of documents.