Sonia Joseph

According to our database, Sonia Joseph authored at least 10 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

Interpreting Physics in Video World Models.

Sonia Joseph, Quentin Garrido, Randall Balestriero, Matthew Kowal, Thomas Fel, Shahab Bakhtiari, Blake A. Richards, Mike Rabbat

CoRR, February, 2026

Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning.

Chuan Qin, Constantin Venhoff, Sonia Joseph, Fanyi Xiao, Stefan Scherer

CoRR, January, 2026

2025

Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval.

Constantin Venhoff, Ashkan Khakzar, Sonia Joseph, Philip Torr, Neel Nanda

CoRR, December, 2025

Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry.

Thomas Fel, Binxu Wang, Michael A. Lepori, Matthew Kowal, Andrew Lee, Randall Balestriero, Sonia Joseph, Ekdeep Singh Lubana, Talia Konkle, Demba E. Ba, Martin Wattenberg

CoRR, October, 2025

From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers.

Praneet Suresh, Jack Stanley, Sonia Joseph, Luca Scimeca, Danilo Bzdok

CoRR, September, 2025

How Visual Representations Map to Language Feature Space in Multimodal LLMs.

Constantin Venhoff, Ashkan Khakzar, Sonia Joseph, Philip Torr, Neel Nanda

CoRR, June, 2025

Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video.

Sonia Joseph, Praneet Suresh, Lorenz Hufe, Edward Stevinson, Robert Graham, Yash Vadi, Danilo Bzdok, Sebastian Lapuschkin, Lee Sharkey, Blake Aaron Richards

CoRR, April, 2025

Steering CLIP's vision transformer with sparse autoencoders.

Sonia Joseph, Praneet Suresh, Ethan Goldfarb, Lorenz Hufe, Yossi Gandelsman, Robert Graham, Danilo Bzdok, Wojciech Samek, Blake Aaron Richards

CoRR, April, 2025

Decoding Vision Transformers: the Diffusion Steering Lens.

Ryota Takatsuki, Sonia Joseph, Ippei Fujisawa, Ryota Kanai

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025

2024

Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent.

Karolis Jucys, George Adamopoulos, Mehrab Hamidi, Stephanie Milani, Mohammad Reza Samsami, Artem Zholus, Sonia Joseph, Blake A. Richards, Irina Rish, Özgür Simsek

CoRR, 2024