Search papers, labs, and topics across Lattice.
PeRCeiVe Lab, University of Catania, Italy {salvatore.calcagno, amelia.sorrenti}@phd.unict.it {matteo.pennisi, federica.proiettosalanitri, simone.palazzo}@unict.it {concetto.spampinato, giovanni.bellitto}@unict.it
3
0
7
Forget gradient descent: this new method routes transformer activations through a Hopfield-inspired memory in a single forward pass to achieve state-of-the-art online continual learning.
You can now audit black-box vision models for biases and failure modes using only their output probabilities, thanks to a clever LLM-powered semantic search.
Forget replaying old data – this continual learning method dreams up entirely new classes to train on, boosting forward transfer and outperforming standard rehearsal techniques.
