no code implementations • 16 Nov 2023 • Xi Ye, Ruoxi Sun, Sercan Ö. Arik, Tomas Pfister
Our framework tunes LLMs to selfground the claims in their responses and provide accurate citations to retrieved documents.
no code implementations • 6 Nov 2023 • Ruoxi Sun, Sercan Ö. Arik, Rajarishi Sinha, Hootan Nakhost, Hanjun Dai, Pengcheng Yin, Tomas Pfister
Text-to-SQL aims to automate the process of generating SQL queries on a database from natural language text.
1 code implementation • 1 Nov 2023 • Chuizheng Meng, Yihe Dong, Sercan Ö. Arik, Yan Liu, Tomas Pfister
Estimation of temporal counterfactual outcomes from observed history is crucial for decision-making in many domains such as healthcare and e-commerce, particularly when randomized controlled trials (RCTs) suffer from high cost or impracticality.
no code implementations • 26 May 2023 • Ruoxi Sun, Sercan Ö. Arik, Alex Muzio, Lesly Miculicich, Satya Gundabathula, Pengcheng Yin, Hanjun Dai, Hootan Nakhost, Rajarishi Sinha, Zifeng Wang, Tomas Pfister
Text-to-SQL, the process of translating natural language into Structured Query Language (SQL), represents a transformative application of large language models (LLMs), potentially revolutionizing how humans interact with data.
1 code implementation • 7 Oct 2022 • Rui Wang, Yihe Dong, Sercan Ö. Arik, Rose Yu
Temporal distributional shifts, with underlying dynamics changing over time, frequently occur in real-world time series and pose a fundamental challenge for deep neural networks (DNNs).
1 code implementation • 16 Sep 2022 • Serdar Ozsoy, Shadi Hamdan, Sercan Ö. Arik, Deniz Yuret, Alper T. Erdogan
In this article, we argue that a straightforward application of information maximization among alternative latent representations of the same input naturally solves the collapse problem and achieves competitive empirical results.
Ranked #1 on Self-Supervised Learning on ImageNet-100
no code implementations • 13 Jun 2022 • Yunhao Ge, Sercan Ö. Arik, Jinsung Yoon, Ao Xu, Laurent Itti, Tomas Pfister
ISL splits the data into different environments, and learns a structure that is invariant to the target across different environments by imposing a consistency constraint.
no code implementations • 5 Jun 2022 • Aya Abdelsalam Ismail, Sercan Ö. Arik, Jinsung Yoon, Ankur Taly, Soheil Feizi, Tomas Pfister
In addition to constituting a standalone inherently-interpretable architecture, IME has the premise of being integrated with existing DNNs to offer interpretability to a subset of samples while maintaining the accuracy of the DNNs.