OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models (2023 · 222 citations)
Strong autoregressive vision-language models like DeepMind's Flamingo accept mixed sequences of images and text, which allows in-context learning from a few demonstrations.
Are aligned neural networks adversarially aligned? (2023 · 157 citations)
This NeurIPS 2023 paper asks whether alignment-tuned language models, trained with RLHF or instruction tuning to be helpful and harmless, stay safe against a worst-case adversary who deliberately optimizes inputs rather than relying on hand-written jailbreaks.

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language ModelsarXiv:2308.01390Anas Awadalla, Irena Gao, Josh Gardner, et al.2023 · 222 citations
Are aligned neural networks adversarially aligned?Conference on Neural Information Processing Systems (NeurIPS)Nicholas Carlini, Milad Nasr, Christopher A. Choquette-Choo, et al.2023 · 157 citations
NitroGen: An Open Foundation Model for Generalist Gaming Agents ↗arXiv (Cornell University) · no summary yetLoïc Magne et al.2026 · 5 citations

Co-authors here

12 of 16 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 263 times (of the 149,439 papers whose bibliographies we read); 89 citing papers with a page here →.

Updated 2 November 2026