14 citations · 32 across the 21 of their papers we have counts for
9 papers · 1 filter
Simple LLM Baselines are Competitive for Model Diffing
Elias Kempf, Simon Schrodi, Bartosz Cywiński +3
Standard LLM evaluations only test capabilities or dispositions that evaluators designed them for, missing unexpected differences such as behavioral shifts between model revisions…
Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer
Simon Schrodi, Elias Kempf, Fazl Barez +1
Language models can transfer hidden biases during distillation. For example, a teacher that "likes owls" can make its student "like owls" too, even when the training data consists…
When and How Does CLIP Enable Domain and Compositional Generalization?
Elias Kempf, Simon Schrodi, Max Argus +1
The remarkable generalization performance of contrastive vision-language models like CLIP is often attributed to the diversity of their training distributions. However, key questio…
Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning
Soumajyoti Sarkar, Leonard Lausen, Volkan Cevher +3
Sparse Mixture of Expert (SMoE) models have emerged as a scalable alternative to dense models in language modeling. These models use conditionally activated feedforward subnetworks…
Concept Bottleneck Models Without Predefined Concepts
Simon Schrodi, Julian Schur, Max Argus +1
There has been considerable recent interest in interpretable concept-based models such as Concept Bottleneck Models (CBMs), which first predict human-interpretable concepts and the…
Constrained Reinforcement Learning with Smoothed Log Barrier Function
Baohe Zhang, Yuan Zhang, Lilli Frison +2
Reinforcement Learning (RL) has been widely applied to many control tasks and substantially improved the performances compared to conventional control methods in many domains where…
Is Mamba Capable of In-Context Learning?
Riccardo Grazzi, Julien Siems, Simon Schrodi +2
State of the art foundation models such as GPT-4 perform surprisingly well at in-context learning (ICL), a variant of meta-learning concerning the learned ability to solve tasks du…
Latent Diffusion Counterfactual Explanations
Karim Farid, Simon Schrodi, Max Argus +1
Counterfactual explanations have emerged as a promising method for elucidating the behavior of opaque black-box models. Recently, several works leveraged pixel-space diffusion mode…
Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
David T. Hoffmann, Simon Schrodi, Jelena Bratulić +3
In this work, we study rapid improvements of the training loss in transformers when being confronted with multi-step decision tasks. We found that transformers struggle to learn th…