Publications
2025
Gemini Team, Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities, Technical report, Blog
Mubashara Akhtar, Chenxi Pang, Andreea Marzoca, Yasemin Altun, Julian Eisenschlos, TANQ: An open domain dataset of table answered questions, Transactions of the Association for Computational Linguistics
Negar Foroutan, Angelika Romanou, Matin Ansaripour, Julian Eisenschlos, Karl Aberer, Rémi Lebret WikiMixQA: A Multimodal Benchmark for Question Answering over Tables and Charts, Findings of ACL 2025
Hernán Maina, Guido Ivetta, Mateo Lione Stuto, Julian Eisenschlos, Jorge Sánchez, Luciana Benotti, ROSA: Addressing text understanding challenges in photographs via ROtated SAmpling, Under review
2024
Si-An Chen, Lesly Miculicich, Julian Eisenschlos, Zifeng Wang, Zilong Wang, Yanfei Chen, Yasuhisa Fujii, Hsuan-Tien Lin, Chen-Yu Lee, Tomas Pfister, TableRag: Million-token table understanding with language models, NeurIPS 2024
Julian Eisenschlos, Hernán Maina, Guido Ivetta, Luciana Benotti, Selectively Answering Visual Questions, Findings of ACL 2024
Syrine Krichene, Francesco Piccinno, Fangyu Liu, Julian Eisenschlos, Faithful Chart Summarization with ChaTS-Pi, Proceedings of ACL 2024
Gemini Team, Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context, Technical report, Blog
Zilong Wang, Hao Zhang, Li, Liang Chu, Julian Eisenschlos, Vincent Perot, Zifeng Wang, Lesly Miculicich, Yasuhisa Fujii, Jingbo Shang, Lee, Yu Che, Chain-of-table: Evolving tables in the reasoning chain for table understanding, Proceedings of ICLR 2024, Blog
Julian Eisenschlos, Xingchen Wan, Hootan Nakhost, Sercan Omer Arik, Ruoxi Sun, Hanjun Dai, Universal Self-Adaptive Prompting, US Patent App. 18377368
Thomas Müller, Jonathan Herzig, Averi Nowak, Julian Eisenschlos, Francesco Piccinno, Syrine Krichene Systems and methods for training language models to reason over tables, US Patent App. 11868381B2
Julian Eisenschlos, Francesco Piccinno, Yasemin Altun, Syrine Krichene, Kenton Chiu Tsun Lee, Fangyu Liu, Mandar Joshi, Chenxi Pang, Wenhu Chen, One-Shot Visual Language Reasoning Over Graphical Depictions of Data, US Patent App. 18319249
Lucas Beyer, Andreas Steiner, André Susano Pinto, Alexander Kolesnikov, Xiao Wang, Daniel Salz, Maxim Neumann, Ibrahim Alabdulmohsin, Michael Tschannen, Emanuele Bugliarello, Thomas Unterthiner, Daniel Keysers, Skanda Koppula, Fangyu Liu, Adam Grycner, Alexey Gritsenko, Neil Houlsby, Manoj Kumar, Keran Rong, Julian Eisenschlos, Rishabh Kabra, Matthias Bauer, Matko Bošnjak, Xi Chen, Matthias Minderer, Paul Voigtlaender, Ioana Bica, Ivana Balazevic, Joan Puigcerver, Pinelopi Papalampidi, Olivier Henaff, Xi Xiong, Radu Soricut, Jeremiah Harmsen, Xiaohua Zhai, PaliGemma: A versatile 3B VLM for transfer, Technical report
2023
Gemini Team, Gemini: a family of highly capable multimodal models, Technical report, Blog
Jeremy Cole, Michael Zhang, Daniel Gillick, Julian Eisenschlos, Bhuwan Dhingra, Jacob Eisenstein, Selectively answering ambiguous questions, Proceedings of EMNLP 2023
Xingchen Wan, Ruoxi Sun, Hootan Nakhost, Hanjun Dai, Julian Eisenschlos, Sercan Arik, Tomas Pfister, Universal self-adaptive prompting, Proceedings of EMNLP 2023
Fangyu Liu*, Julian Eisenschlos*, Francesco Piccinno, Syrine Krichene, Chenxi Pang, Kenton Lee, Mandar Joshi, Wenhu Chen, Nigel Collier, Yasemin Altun, Deplot: One-shot visual language reasoning by plot-to-table translation, Findings of ACL 2023, Blog Code
Fangyu Liu, Francesco Piccinno, Syrine Krichene, Chenxi Pang, Kenton Lee, Mandar Joshi, Yasemin Altun, Nigel Collier, Julian Eisenschlos, Matcha: Enhancing visual language pretraining with math reasoning and chart derendering, Proceedings of ACL 2023, Blog Code
Jeremy Cole, Palak Jain, Julian Eisenschlos, Michael Zhang, Eunsol Choi, Bhuwan Dhingra, DiffQG: Generating questions to summarize factual changes, Proceedings of EACL 2023
Julian Eisenschlos, Jeremy Cole, Fangyu Liu, William Cohen, WinoDict: Probing language models for in-context word acquisition, Proceedings of EACL 2023, code, Best Paper Award
2022
Ewa Andrejczuk, Julian Eisenschlos*, Francesco Piccinno, Syrine Krichene, Yasemin Altun, Table-to-text generation and pre-training with TABT5, Findings of EMNLP 2022
Aashna Jena, Vivek Gupta, Manish Shrivastava, Julian Eisenschlos, Leveraging data recasting to enhance tabular reasoning, Findings of EMNLP 2022
Iulia Maria Comşa, Julian Eisenschlos, Srini Narayanan, Miqa: A benchmark for inference on metaphorical questions, Proceedings of AACL 2022, Code
Kenton Lee, Mandar Joshi, Turc, Raluca Iuli, Hexiang Hu, Fangyu Liu, Julian Eisenschlos, Urvashi Khandelwal, Peter Shaw, Chang, Wei Min, Kristina Toutanova, Pix2struct: Screenshot parsing as pretraining for visual language understanding, Proceedings of ICLR 2022, Code
Fangyu Liu, Julian Eisenschlos, Jeremy Cole, Nigel Collier, Do ever larger octopi still amplify reporting biases? Evidence from judgments of typical colour, Proceedings of AACL 2022
Bhuwan Dhingra, Jeremy Cole, Julian Eisenschlos, Daniel Gillick, Jacob Eisenstein, William Cohen, Time-aware language models as temporal knowledge bases, Transactions of the Association for Computational Linguistics
2021
Julian Eisenschlos, Maharshi Gor, Thomas Mueller, William Cohen, MATE: Multi-view attention for table transformer efficiency, Proceedings of EMNLP 2021 Code
Syrine Krichene, Thomas Müller, Julian Eisenschlos, DoT: An efficient Double Transformer for NLP tasks with tables, Findings of ACL 2021 Code
Julian Eisenschlos, Bhuwan Dhingra, Jannis Bulian, Benjamin Börschinger, Jordan Boyd-Graber, Fool Me Twice: Entailment from Wikipedia Gamification, Proceedings of NAACL 2021 Code
Jonathan Herzig, Thomas Müller, Syrine Krichene, Julian Eisenschlos, Open Domain Question Answering over Tables via Dense Retrieval, Proceedings of NAACL 2021 Code
Thomas Müller, Julian Eisenschlos, Syrine Krichene, TAPAS at SemEval-2021 Task 9: Reasoning over tables with intermediate pre-training, Proceedings of 15th International Workshop on Semantic Evaluation 2021 Code
Tao Lei, Julian Eisenschlos, Modifying text according to a specified attribute, US Patent App. 11610061B2 Application number 16699825
2020
Julian Eisenschlos, Syrine Krichene, Thomas Müller, Understanding tables with intermediate pre-training, Findings of EMNLP 2020 Code Blog
Jonathan Herzig, Averi Nowak, Thomas Müller, Francesco Piccinno, Julian Eisenschlos, TaPas: Weakly Supervised Table Parsing via Pre-training, Proceedings of ACL 2020 Code Blog
Sebastian Prillo*, Julian Eisenschlos* SoftSort: A Continuous Relaxation for the argsort Operator, Proceedings of ICML 2020 Code
2019
Julian Eisenschlos*, Sebastian Ruder*, Piotr Czapla*, Marcin Kadras*, Sylvain Gugger and Jeremy Howard MultiFiT: Efficient Multi-lingual Language Model Fine-tuning, Proceedings of EMNLP 2019 Code
Venky Iyer, Clayton Andrews, Omid Rouhani-Kalleh, Julian Eisenschlos Evaluating likely accuracy of metadata received from social networking system users based on user characteristics US Patent App. 10/061,797 US Patent App. 14/742,639, 2016
Julian Eisenschlos, Venky Iyer Predicting the Quality of New Contributors to a Crowdsourcing System NeurIPS: Crowdsourcing and Machine Learning Workshop 2014
Julian Eisenschlos, Mariano Suárez-Álvarez 3-Calabi-Yau Algebras from Steiner Systems Master Thesis 2013
[*] Equal contribution.