Tal Schuster

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA

Conformal Risk Control

Conformal Language Modeling

Block Transformer: Global-to-Local Language Modeling for Fast Inference

Is margin all you need? An extensive empirical study of deep active learning on tabular data