linear probing
- Are Greedy Task Orderings Better Than Random in Continual Linear Regression?
- Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations
- Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning
- On Fairness of Unified Multimodal Large Language Model for Image Generation
- REVE: A Foundation Model for EEG - Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects
- Understanding Parametric and Contextual Knowledge Reconciliation within Large Language Models
- UniViT: Unifying Image and Video Understanding in One Vision Encoder
- Vision Transformers with Self-Distilled Registers