Dear MAIEI Community, The past few months have been a time of profound loss and reflection for all of us at the Montreal AI Ethics Institute (MAIEI). On September 30, we lost our dear friend and founder, Abhishek … [Read more...] about Open Letter: Moving Forward Together – MAIEI’s Next Chapter
Spotlight
Honouring Abhishek Gupta at the Montreal Startup Community Awards 2024
On November 28, 2024 at the sixth Montreal Startup Community Awards organized by MTL NewTech in collaboration with Startupfest, we paid tribute to Abhishek Gupta. His parents, Mr. Ashok Gupta and Mrs. Asha Gupta, along … [Read more...] about Honouring Abhishek Gupta at the Montreal Startup Community Awards 2024
In Memoriam: Abhishek Gupta (Dec 20, 1992 – Sep 30, 2024)
Honoring the Life and Legacy of a Leader in AI Ethics In accordance with his family's wishes, it is with profound sadness that we announce the passing of Abhishek Gupta, Founder and Principal Researcher of the … [Read more...] about In Memoriam: Abhishek Gupta (Dec 20, 1992 – Sep 30, 2024)
Representation Engineering: A Top-Down Approach to AI Transparency
🔬 Research Summary by Andy Zou, a Ph.D. student at CMU, advised by Zico Kolter and Matt Fredrikson. He also cofounded the Center for AI Safety (safe.ai). [Original paper by Andy Zou, Long Phan, Sarah Chen, James … [Read more...] about Representation Engineering: A Top-Down Approach to AI Transparency
Universal and Transferable Adversarial Attacks on Aligned Language Models
🔬 Research Summary by Andy Zou, a second-year PhD student at CMU, advised by Zico Kolter and Matt Fredrikson. He is also a cofounder of the Center for AI Safety (safe.ai). [Original paper by Andy Zou, Zifan … [Read more...] about Universal and Transferable Adversarial Attacks on Aligned Language Models