182 citations · 204 across the 11 of their papers we have counts for
18 papers
Interpreting Model Reasoning through Behavioral Counterfactuals
Shawn Im, James Oldfield, Adel Bibi +1
Faithfully understanding the internal process that occurs as models form their chain of thought is an important problem with the rise in model capabilities. However, this remains c…
How Much Do Activation Monitors Benefit from Original Model Computations?
James Oldfield, Shawn Im, Jay J Culligan +3
One powerful way to safeguard AI systems is to monitor their internal computations--where signs of undesirable behavior might be more easily detectable than from models' inputs and…
Towards a Unified Misuse Monitoring Benchmark
Aniruddh Pramod, James Oldfield, Adel Bibi
LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request is split into innocuous sub-r…
BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents
Ziyan Wang, Shuqing Shi, James Oldfield +5
In decentralized consumer-to-consumer (C2C) marketplaces, people list goods, negotiate with strangers, and rate one another, so trust rests on reputation. Large language model (LLM…
-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation Signals
Aoxi Liu, Yupeng Chen, James Oldfield +5
Despite the emergence of diffusion large language models (D-LLMs) as an alternative to autoregressive large language models (AR-LLMs), safety monitoring for D-LLMs remains largely…
fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery
Andreas D. Demou, Panagiotis Koromilas, James Oldfield +2
Many features in pretrained Transformers span multiple layers: they emerge through stages of inference, persist in the residual stream, or are built jointly by parallel MLPs. Cross…
PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
Panagiotis Koromilas, Andreas D. Demou, James Oldfield +2
Sparse autoencoders (SAEs) interpret neural network representations by decomposing activations into sparse combinations of dictionary atoms. However, SAEs assume features combine a…
Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
James Oldfield, Philip Torr, Ioannis Patras +2
Monitoring large language models' (LLMs) activations is an effective way to detect harmful requests before they lead to unsafe outputs. However, traditional safety monitors often r…
Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
James Oldfield, Shawn Im, Sharon Li +3
Multilayer perceptrons (MLPs) are an integral part of large language models, yet their dense representations render them difficult to understand, edit, and steer. Recent methods le…
Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
James Oldfield, Markos Georgopoulos, Grigorios G. Chrysos +5
The Mixture of Experts (MoE) paradigm provides a powerful way to decompose dense layers into smaller, modular computations often more amenable to human interpretation, debugging, a…
Parts of Speech-Grounded Subspaces in Vision-Language Models
James Oldfield, Christos Tzelepis, Yannis Panagakis +2
Latent image representations arising from vision-language models have proved immensely useful for a variety of downstream tasks. However, their utility is limited by their entangle…
ContraCLIP: Interpretable GAN generation driven by pairs of contrasting sentences
Christos Tzelepis, James Oldfield, Georgios Tzimiropoulos +1
This work addresses the problem of discovering non-linear interpretable paths in the latent space of pre-trained GANs in a model-agnostic manner. In the proposed method, the discov…
PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs
James Oldfield, Christos Tzelepis, Yannis Panagakis +2
Recent advances in the understanding of Generative Adversarial Networks (GANs) have led to remarkable progress in visual editing and synthesis tasks, capitalizing on the rich seman…
Cluster-guided Image Synthesis with Unconditional Models
Markos Georgopoulos, James Oldfield, Grigorios G Chrysos +1
Generative Adversarial Networks (GANs) are the driving force behind the state-of-the-art in image generation. Despite their ability to synthesize high-resolution photo-realistic im…
Tensor Component Analysis for Interpreting the Latent Space of GANs
James Oldfield, Markos Georgopoulos, Yannis Panagakis +2
This paper addresses the problem of finding interpretable directions in the latent space of pre-trained Generative Adversarial Networks (GANs) to facilitate controllable image synt…
Tensor Methods in Computer Vision and Deep Learning
Yannis Panagakis, Jean Kossaifi, Grigorios G. Chrysos +4
Tensors, or multidimensional arrays, are data structures that can naturally represent visual data of multiple dimensions. Inherently able to efficiently capture structured, latent…
Enhancing Facial Data Diversity with Style-based Face Aging
Markos Georgopoulos, James Oldfield, Mihalis A. Nicolaou +2
A significant limiting factor in training fair classifiers relates to the presence of dataset bias. In particular, face datasets are typically biased in terms of attributes such as…
Adversarial Learning of Disentangled and Generalizable Representations for Visual Attributes
James Oldfield, Yannis Panagakis, Mihalis A. Nicolaou
Recently, a multitude of methods for image-to-image translation have demonstrated impressive results on problems such as multi-domain or multi-attribute transfer. The vast majority…