Andrea Madotto

Email / Resume / Google Scholar

There can't be beauty and utility?

- Leonardo da Vinci

I am a Member of Technical Staff at Thinking Machines Lab. Previously, I was a Research Scientist at Meta's Fundamental AI Research (FAIR), where I focused on multimodal language models and LLM-based agents capable of navigating user interfaces to accomplish user goals. I received my PhD in Electronic & Computer Engineering at The Hong Kong University of Science and Technology (HKUST). I received the outstanding paper award from ACL2019, and the best paper award from the NeurIPS2019 ConvAI workshop. My work has been featured in MIT technology review and VentureBeat. I serve as program committee and reviewer for various machine learning and natural language processing conferences such as ACL, EMNLP, NeurIPS, ICML, ICLR, and AAAI, and journals such as the Journal of Natural Language Engineering and Computer Speech and Languages, and I co-presented the NeurIPS 2020 tutorial on Deeper Conversational AI.

News

Apr 2025 Perception Encoder: The best visual embeddings are not at the output of the network [Paper]
Apr 2025 PerceptionLM: Open-access data and models for detailed visual understanding [Paper]
Sep 29, 2023 The AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model is out [Paper]
Nov 7, 2022 The Survey of Hallucination in Natural Language Generation is out [Paper]
Jan 10, 2022 Started at FAIR as Research Scientist
Nov 10, 2021 The Few-Shot Bot is out [Paper] [Code] [Demo]
Sep 10, 2021 3 papers accepted at EMNLP2021
Apr 2, 2021 BiToD accepted at NeurIPS2021 Benchmark Track
Apr 2, 2021 2 papers accepted at NAACL2021
Feb 3, 2021 AAAI 2021: 2 paper main + 1 demo. Check our AdapterBot
Dec 3, 2020 We are presenting the NeurIPS Tutorial on Conversational AI.
Oct 1, 2020 4 papers accepted at EMNLP2020 (3 findings and 1 main)
Aug 9, 2020 My first blog post on few-shot learning with LMs is out!
Feb 1, 2020 GO-Explore for text-based games got accepted in IJCAI 2020