Co-occurring keywords
Papers
Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders
NIPS 2024
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
NIPS 2024
Multi-Modal Disordered Representation Learning Network for Description-Based Person Search
AAAI 2024
The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks
NIPS 2024
Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method
NIPS 2024