Duen Horng "Polo" Chau
@polochau.bsky.social
Professor, Georgia Tech • ML+VIS • Director, Polo Club of AI 🚀 poloclub.gatech.edu • Carnegie Mellon alum. Covert designer, cellist, pianist faculty.cc.gatech.edu/~dchau
Reposted by Duen Horng "Polo" Chau
It's on! In its 8th year, the original VISxAI workshop wants your contributions for explaining ML/AI/GenAI principles. Please consider to submit.
Deadline: July 30
webpage: visxai.io
#ML #AI #GenAI #Visualization
Deadline: July 30
webpage: visxai.io
#ML #AI #GenAI #Visualization
June 11, 2025 at 2:07 PM
It's on! In its 8th year, the original VISxAI workshop wants your contributions for explaining ML/AI/GenAI principles. Please consider to submit.
Deadline: July 30
webpage: visxai.io
#ML #AI #GenAI #Visualization
Deadline: July 30
webpage: visxai.io
#ML #AI #GenAI #Visualization
Reposted by Duen Horng "Polo" Chau
🚨 NeurIPS 2024 🚨How robust are AI-Generated Image Detectors?
🤔 Can they detect various magnitudes of image augmentations?
💡 Does performance fluctuate across scenes?
🚀 Find out with Semi-Truths: 1.5 million images for the targeted evaluation of AI-generated images. arxiv.org/abs/2411.07472
🤔 Can they detect various magnitudes of image augmentations?
💡 Does performance fluctuate across scenes?
🚀 Find out with Semi-Truths: 1.5 million images for the targeted evaluation of AI-generated images. arxiv.org/abs/2411.07472
December 5, 2024 at 1:02 AM
🚨 NeurIPS 2024 🚨How robust are AI-Generated Image Detectors?
🤔 Can they detect various magnitudes of image augmentations?
💡 Does performance fluctuate across scenes?
🚀 Find out with Semi-Truths: 1.5 million images for the targeted evaluation of AI-generated images. arxiv.org/abs/2411.07472
🤔 Can they detect various magnitudes of image augmentations?
💡 Does performance fluctuate across scenes?
🚀 Find out with Semi-Truths: 1.5 million images for the targeted evaluation of AI-generated images. arxiv.org/abs/2411.07472
Reposted by Duen Horng "Polo" Chau
Excited to share "Dense Associative Memory through the Lens of Random Features" accepted to #neurips2024🎉
DenseAMs need new weights for each stored pattern–hurting scalability. Kernel methods let us add memories without adding weights!
Distributed memory for DenseAMs, unlocked🔓
DenseAMs need new weights for each stored pattern–hurting scalability. Kernel methods let us add memories without adding weights!
Distributed memory for DenseAMs, unlocked🔓
December 3, 2024 at 4:33 PM
Excited to share "Dense Associative Memory through the Lens of Random Features" accepted to #neurips2024🎉
DenseAMs need new weights for each stored pattern–hurting scalability. Kernel methods let us add memories without adding weights!
Distributed memory for DenseAMs, unlocked🔓
DenseAMs need new weights for each stored pattern–hurting scalability. Kernel methods let us add memories without adding weights!
Distributed memory for DenseAMs, unlocked🔓