Lethe
PulseAugur coverage of Lethe — every cluster mentioning Lethe across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New benchmark Lethe evaluates edge unlearning in graph neural networks
Researchers have introduced Lethe, a new benchmark designed to evaluate edge unlearning methods for graph neural networks. Current evaluations for edge unlearning are limited, often using datasets where node features ov…
-
KVeil method wins ECCV 2026 challenge for unlearnable videos
Researchers have developed a novel method called KVeil to protect facial videos from unauthorized customization, securing first place in the ECCV 2026 LifeGenIP Challenge. The technique employs Reference Capacity Collap…
-
New method LETHE defends against unauthorized image-to-video generation
Researchers have developed a new method called LETHE to defend against unauthorized image-to-video generation. This technique aims to corrupt fabricated videos by disrupting how image-to-video diffusion models interpret…
-
New research paper details LETHE, a GAN-inspired sonic oblivion system
A new research paper introduces LETHE, a self-referential system designed for sonic oblivion and implemented in SuperCollider. This architecture draws inspiration from Generative Adversarial Networks (GANs) but operates…
-
New benchmark 'Lethe' tests federated unlearning for medical imaging
Researchers have introduced Lethe, a new benchmark designed to evaluate federated unlearning methods specifically for medical imaging applications. Existing unlearning techniques, primarily tested on natural images, may…
-
New research explores efficient and robust machine unlearning techniques
Researchers are developing new methods for machine unlearning, which aims to remove specific data's influence from trained models without full retraining. Several papers propose novel techniques to achieve more efficien…