activity
20242026
collaborators

9 papers

cs.AI2026

LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models

Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck +5

Large Language Models (LLMs) exhibit impressive general-purpose capabilities but also introduce serious safety risks, particularly the potential for deception as models acquire inc…

cs.CV2025

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…

cs.AI2025

DPO Learning with LLMs-Judge Signal for Computer Use Agents

Man Luo, David Cobbley, Xin Su +4

Computer use agents (CUA) are systems that automatically interact with graphical user interfaces (GUIs) to complete tasks. CUA have made significant progress with the advent of lar…

cs.CV2025

Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders

Matthew Lyle Olson, Musashi Hinck, Neale Ratzlaff +4

The ImageNet hierarchy provides a structured taxonomy of object categories, offering a valuable lens through which to analyze the representations learned by deep vision models. In…

cs.CL2024

Steering Large Language Models to Evaluate and Amplify Creativity

Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck +2

Although capable of generating creative text, Large Language Models (LLMs) are poor judges of what constitutes "creativity". In this work, we show that we can leverage this knowled…

cs.CV2024

FiVL: A Framework for Improved Vision-Language Alignment through the Lens of Training, Evaluation and Explainability

Estelle Aflalo, Gabriela Ben Melech Stan, Tiep Le +5

Large Vision Language Models (LVLMs) have achieved significant progress in integrating visual and textual inputs for multimodal reasoning. However, a recurring challenge is ensurin…