π§΅ [3/3] Special thanks to all coauthors: Adam Davies, Ashkan Khakzar, Anjun Hu, Arshia Hemmat, Jianhao Yuan, Tom Lamb, Jiyang Guan, Philip Torr. Work done at @oxfordtvg.bsky.social
09.12.2024 21:04 β π 1 π 0 π¬ 0 π 0@frapintoml.bsky.social
AI security and safety: privacy, robustness, synthetic data, agents. Email: fpinto1@uchicago.edu
π§΅ [3/3] Special thanks to all coauthors: Adam Davies, Ashkan Khakzar, Anjun Hu, Arshia Hemmat, Jianhao Yuan, Tom Lamb, Jiyang Guan, Philip Torr. Work done at @oxfordtvg.bsky.social
09.12.2024 21:04 β π 1 π 0 π¬ 0 π 0π§΅ [2/3]
- π₯ Is DP In-Context Learning really making any progress? At the @solarneurips workshop we present a very preliminary draft that questions its progress in several settings.
Paper: openreview.net/pdf?id=5K7o8...
π§΅ [1/3] Heading to #Vancouver π¨π¦ tomorrow to present our latest work in @OxfordTVG #UniversityOfOxford at #NeurIPS2024 π§ :
- π₯ Improving on #StylizedImageNet, use #IllusionBench: can you see the cat πββ¬ Hidden in Plain Sight in the picture πΌοΈ?
Paper: arxiv.org/abs/2411.06287