AI Lab
Collaborating with people to create new value
Our focus is on realizing a sustainable society by developing cutting-edge AI technologies that not only create new value but also contribute to the transformation of society and business.
Our research focuses on the next frontier: developing self-improving machine learning systems that leverage AI to optimize and enhance AI itself. Our core thesis is that by enabling AI systems to autonomously refine their own architecture, learning algorithms, and data utilization, we can achieve orders of magnitude improvement over current methodologies.
An AI system is built upon three fundamental layers: the infraestructure layer, encompassing both hardware and software infrastructure; the modeling layer, which defines model architectures and training methodologies; and the data layer, where data selection and supervision strategies come into play. Traditionally, each of these layers relies heavily on human intervention, demanding specialized expertise and manual tuning. Yet, self-improving ML systems will be able to optimize these elements with unparalleled precision and efficiency, surpassing the capabilities of human experts.
By pioneering self-improving ML, we aim to make AI not just a powerful tool for automatically solving today’s challenges but a dynamic entity that can evolve independently to tackle the complex problems of tomorrow. This evolution goes beyond technological advancement; we believe it can drive meaningful change. Our research is contributing to more sustainable use of resources, reduce energy consumption, and ultimately enable AI to address environmental and societal challenges more effectively. Through this work, we aspire to harness AI’s potential to make the world not only smarter but also more sustainable for future generations.
Researchers in the AI Lab
Self-improving ML,
multi-modal foundation models,
large scale AI system design
Machine Learning (ML),
distributed systems,
databases
Self-improving ML,
continual learning
foundation models
NLP (information retreival,
semantic web),open education,graph AI,
AI ethics,AutoML
Self-improving ML,
foundational models,
neuroscience
Self-improving ML,
computer vision,
natural language processing
Natural Language Processing,
(NLP),Machine Learning (ML),
and communication networks
Self-improving ML
natural language processing
computer vision
Machine Learning (ML),
computer vision,AI ethics,
Natural Language Processing (NLP),AI and creativity
Natural Language Processing (NLP),Computer Vision,
multimodal learning
Machine Learning (ML),
Computer Vision,
generative models
Machine Learning (ML),
customer segmentation, AutoML,bias in AI,
feature selection
Machine Learning (ML),
optimization,
mobile networks
Self-improving ML,
neuroscience,
AI for science
The Self-Improving Machine Learning group
Director of Research
Discover more about AI, one of our 5 key technologies
Publications
2025
-
In-distribution adversarial attacks on object recognition models using gradient-free search.- Spandan Madan, Tomotake Sasaki,
Hanspeter Pfister, Tzu-Mao Li, Xavier Boix
-
Configural processing as an optimized strategy for robust object recognition in neural networks (Communications Biology)- Hojin
Jang, Pawan Sinha, Xavier Boix
2024
- In-distribution adversarial attacks on object recognition models using gradient-free search.- Spandan Madan, Tomotake Sasaki, Hanspeter Pfister, Tzu-Mao Li, Xavier Boix
- Lei Liu, So Hasegawa, Shailaja Keyur Sampat, Maria Xenochristou, Wei-Peng Chen, Takashi Kato, Taisei Kakibuchi, Tatsuya Asai, "AutoDW: Automatic Data Wrangling Leveraging Large Language Models", ASE '24: Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering 2024
- Anay Majee, Maria Xenochristou, Wei-Peng Chen, "TabGLM: Tabular Graph Language Model for Learning Transferable Representations through Multi-Modal Consistency Minimization", Proceedings of the AAAI Conference on Artificial Intelligence, 2025
- Multi-domain improves classification in out-of-distribution and data-limited scenarios for medical image analysis, journal: Scientific Reports- Ece Ozkan, Xavier Boix
- D3: Data Diversity Design for Systematic Generalization in Visual Question Answering / journal: TMLR - Amir Rahimi, Vanessa D'Amario, Moyuru Yamada, Kentaro Takemoto, Tomotake Sasaki, Xavier Boix
- Transformer Module Networks for Systematic Generalization in Visual Question Answering / journal TPAMI - Moyuru Yamada, Vanessa D'Amario, Kentaro Takemoto, Xavier Boix*, Tomotake Sasaki* (*equal authorship)
2023
- Robustness to Transformations Across Categories: Is Robustness Driven by Invariant Neural Representations? - Hojin Jang*, Syed Suleman Abbas Zaidi*, Xavier Boix*, Neeraj Prasad*, Sharon Gilad-Gutnick, Shlomit Ben-Ami, Pawan Sinha (*equal authorship)
- Juhan Bae, Michael R Zhang, Michael Ruan, Eric Wang, So Hasegawa, Jimmy Ba, Roger Grosse, “Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve”, International Conference on Learning Representations (ICLR) 2023
- So Hasegawa, Masayuki Hiromoto, Akira Nakagawa, Yuhei Umeda, “Improving Predicate Representation in Scene Graph Generation by Self-Supervised Learning”, Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023
- Ramya Malur Srinivasan, Hiroya Inakoshi, Kanji Uchino, “Leveraging Cognitive Science for Testing Large Language Models”, 2023 IEEE International Conference On Artificial Intelligence Testing (AITest), 2023
- Youzhi Luo, Michael McThrow, Wing Yee Au, Tao Komikado, Kanji Uchino, Koji Maruhashi, Shuiwang Ji, “Automated Data Augmentations for Graph Classification”, ICLR2023, 2023
2022
- Lei Liu, Wei-Peng Chen, Mehdi Bahrami, “Automatic Generation of Visualizations from Synthesizing Rules for Machine Learning Pipelines”, 37th IEEE/ACM International Conference on Automated Software Engineering (ASE ’22), October 10–14, 2022, Ann Arbor, Michigan, United States
- Mehdi Bahrami, Wei-Peng Chen, Lei Liu, and Mukul Prasad, “BERT-Sort: A Zero-shot MLM Semantic Encoder on Ordinal Features for AutoML”, First Conference on Automated Machine Learning (Main Track). AutoML 2022 (co-located ICML)
- Mehdi Assefi, Mehdi Bahrami, Sarthak Arora, Thiab R. Taha, Hamid R. Arabnia, Khaled M. Rasheed, and Wei-Peng Chen, “An Intelligent Data-Centric Web Crawler Service for API Corpus Construction at Scale”, 2022 IEEE International Conference on Web Services (ICWS’22), July 2022, Barcelona, Spain
- Ripon K Saha, Akira Ura, Sonal Mahajan, Chenguang Zhu, Linyi Li, Yang Hu, Hiroaki Yoshida, Sarfraz Khurshid, Mukul R Prasad, “SapientML: synthesizing machine learning pipelines by learning from human-writen solutions”, Proceedings of the 44th International Conference on Software Engineering (ICSE ’22), May 21 - 29, 2022, Pittsburgh Pennsylvania
- Sonal Mahajan, Mukul R Prasad, “Providing Real-time Assistance for Repairing Runtime Exceptions using Stack Overflow Posts,” 2022 IEEE Conference on Software Testing, Verification and Validation (ICST), Valencia, Spain, 2022
- Meng Liu, Youzhi Luo, Kanji Uchino Koji Maruhashi, Shuiwang Ji, “Generating 3D Molecules for Target Protein Binding”, ICML 2022 as a Long Presentation, 2022
2021
- Vardaan Pahuja, Yu Gu,Wenhu Chen,Mehdi Bahrami, Lei Liu,Wei-Peng Chen and Yu Su, A Systematic Investigation of KB-Text Embedding Alignment at Scale, ACL-IJCNLP 2021 main conference
- Chenguang Zhu, Ripon K. Saha, Mukul R. Prasad, Sarfraz KhurshidC. Zhu, “Restoring the Executability of Jupyter Notebooks by Automatic Upgrade of Deprecated APIs,” 2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE), Melbourne, Australia, 2021
- Rohan Bavishi, Shadaj Laddad, Hiroaki Yoshida, Mukul R. Prasad, Koushik Sen, “VizSmith: Automated Visualization Synthesis by Mining Data-Science Notebooks,” 2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE), Melbourne, Australia, 2021
- Yusuke Kimura, Takumi Akazaki, Shinji Kikuchi, Sonal Mahajan, Mukul R. Prasad, “Q&A MAESTRO: Q&A Post Recommendation for Fixing Java Runtime Exceptions,” 2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE), Melbourne, Australia, 2021
- Ramya Malur Srinivasan, Kanji Uchino, “The Role of Arts in Shaping AI Ethics”, In AAAI Workshop on reframing diversity in AI: Representation, inclusion, and power. CEUR Workshop Proceedings(CEUR-WS. org), 2021
- Ramya Malur Srinivasan, Kanji Uchino, ” Quantifying Confounding bias in generative art:A case Study”, AAAI Conference on AI, Ethics, and Society, 2021
- Ramya Malur Srinivasan, Kanji Uchino, “Biases in Generative Art--A Causal Look from the Lens of Art History”, ACM FAccT March 3--10, 2021
2020
- Mehdi Bahrami, Mehdi Assefi, Ian Thomas, Wei-Peng Chen, Shridhar Choudhary, Hamid Arabnia, “Deep SAS: A Deep Signature-based API Specification Learning Approach”, 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC).
- Lei Liu, Mehdi Bahrami, and Wei-Peng Chen, “Automatic Generation of IFTTT Mashup Infrastructures”, 35th IEEE/ACM International Conference on Automated Software Engineering (ASE), September 21-25, 2020.
- Mehdi Bahrami, Wei-Peng Chen, “Automated Web Service Specification Generation through a Transformation-based Learning”, International Conference on Web Services (ICWS 2020), September 18-20, 2020.
- Lei Liu, Mehdi Bahrami, Junhee Park, Wei-Peng Chen, “Web API Search: Discover Web API and its Endpoint with Natural Language Queries”, International Conference on Web Services (ICWS 2020), September 18-20, 2020.
- Sonal Mahajan, Negarsadat Abolhassani, Mukul R. Prasad, “Recommending stack overflow posts for fixing runtime exceptions using failure scenario matching”, Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering ESEC/FSE 2020, November 2020
- Hiroaki Yoshida, Rohan Bavishi, Keisuke Hotta, Yusuke Nemoto, Mukul R Prasad, Shinji Kikuch, “Phoenix: a tool for automated data-driven synthesis of repairs for static analysis violations”, Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering: Companion Proceedings (ICSE ’20), June 2020
- Xiang Gao, Ripon K Saha, Mukul R Prasad, Abhik Roychoudhury, “Fuzz testing based data augmentation to improve robustness of deep neural networks”, Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering: Companion Proceedings (ICSE ’20), June 2020
- Hitoshi Tamamura, Motoyoshi Yamanaka, Shun Chiyonobu, Goro Yamada, Sou Hasegawa, Yukitsugu Totake, Takashi Nanjo, “Facilitating the Identification of the Nannofossil Species in Cretaceous of Abu Dhabi Using Artificial Intelligence”, Abu Dhabi International Petroleum Exhibition and Conference, 2020