11 papers
DreamReader: An Interpretability Toolkit for Text-to-Image Models
Nirmalendu Prakash, Narmeen Oozeer, Michael Lan +6
Despite the rapid adoption of text-to-image (T2I) diffusion models, causal and representation-level analysis remains fragmented and largely limited to isolated probing techniques.…
Learning from Reasoning Failures via Synthetic Data Generation
Gabriela Ben Melech Stan, Estelle Aflalo, Avinash Madasu +2
Training models on synthetic data has emerged as an increasingly important strategy for improving the performance of generative AI. This approach is particularly helpful for large…
Pruning the Paradox: How CLIP's Most Informative Heads Enhance Performance While Amplifying Bias
Avinash Madasu, Vasudev Lal, Phillip Howard
CLIP is one of the most popular foundation models and is heavily used for many vision-language tasks, yet little is known about its inner workings. As CLIP is increasingly deployed…
Probing the Representational Power of Sparse Autoencoders in Vision Models
Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff +4
Sparse Autoencoders (SAEs) have emerged as a popular tool for interpreting the hidden states of large language models (LLMs). By learning to reconstruct activations from a sparse b…
Debias your Large Multi-Modal Model at Test-Time via Non-Contrastive Visual Attribute Steering
Neale Ratzlaff, Matthew Lyle Olson, Musashi Hinck +4
Large Multi-Modal Models (LMMs) have demonstrated impressive capabilities as general-purpose chatbots able to engage in conversations about visual inputs. However, their responses…
Cultural Awareness in Vision-Language Models: A Cross-Country Exploration
Avinash Madasu, Vasudev Lal, Phillip Howard
Vision-Language Models (VLMs) are increasingly deployed in diverse cultural contexts, yet their internal biases remain poorly understood. In this work, we propose a novel framework…