Thomas Hofmann

10

Papers

78

Total Citations

Papers (10)

Simplifying Transformer Blocks

LoRACLR: Contrastive Adaptation for Customization of Diffusion Models

The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?

On the Expressiveness and Length Generalization of Selective State Space Models on Regular Languages

The Directionality of Optimization Trajectories in Neural Networks

The Importance of Being Lazy: Scaling Limits of Continual Learning

UIP2P: Unsupervised Instruction-based Image Editing via Edit Reversibility Constraint

Recurrent Distance Filtering for Graph Representation Learning

Navigating Scaling Laws: Compute Optimality in Adaptive Model Training

A Language Model’s Guide Through Latent Space