EA-VAE paper in IEEE T-PAMI fixes systematic uncertainty failures in VAEs
enzoferrante · x · 2026-10-10
Josefina Catoni's team published in IEEE T-PAMI: DL models usually don't know when they don't know. The paper identifies systematic failures in uncertainty representation in variational autoencoders and shows a simple extension, EA-VAE, improves uncertainty representations across multiple domains.
More from Research
- Mathematician John Urschel solved a decades-old problem with GPT Astra, staying optimistic on AI research — soumitrashukla9 · 2026-10-10
- State space models bring recurrence back with linear cost and transformer-era tricks — anshulkundaje · 2026-10-10
- IROS 2026 Best Paper: humanoid robot learns tennis rallies from 5 hours of human motion data — qinzytech · 2026-10-10
- AC2 lets you train custom decision models, lifting toxicity-detection F1 from 0.482 to 0.677 — rhythmrg · 2026-10-10
- KordingLab renames Plan Your Science, keeps free AI science-planning tool for researchers — KordingLab · 2026-10-10
- QuestionFirst's AI mentor critiques research plans, not with praise but 'which result would change your mind?' — KordingLab · 2026-10-10