1 citations · 1 across the 11 of their papers we have counts for
13 papers
Weight Oracles: Reading Neural Network Weights with Language Models
Krishna Kabra, Constantin Venhoff, Christian Schroeder de Witt
Interpretability methods for neural networks are predominantly reactive: they analyse activations produced during specific forward passes, requiring known inputs to find hidden cap…
Multimodal Model Diffing for Feature Discovery and Control
Hunar Batra, Lachin Naghashyar, Ashkan Khakzar +4
Multimodal Large Language Models (MLLMs) exhibit strong visual understanding, yet the internal features that cause these behaviors remain difficult to identify, audit, or control.…
Probing the Misaligned Thinking Process of Language Models
Kaiwen Zhou, Constantin Venhoff, Jonathan Michala +2
Large language models exhibit a growing range of misaligned behaviors such as strategic deception, sandbagging, and self-preservation. As they are increasingly deployed in high-sta…
Towards Understanding Multimodal Fine-Tuning: Spatial Features
Lachin Naghashyar, Hunar Batra, Ashkan Khakzar +4
Contemporary Vision-Language Models (VLMs) achieve strong performance on a wide range of tasks by pairing a vision encoder with a pre-trained language model, fine-tuned for visual-…
Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning
Chuan Qin, Constantin Venhoff, Sonia Joseph +2
Contrastive Language-Image Pre-training (CLIP) has become a cornerstone in vision-language representation learning, powering diverse downstream tasks and serving as the default vis…
Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval
Constantin Venhoff, Ashkan Khakzar, Sonia Joseph +2
Training vision language models (VLMs) aims to align visual representations from a vision encoder with the textual representations of a pretrained large language model (LLM). Howev…
Base Models Know How to Reason, Thinking Models Learn When
Constantin Venhoff, Iván Arcuschin, Philip Torr +2
What do thinking language models learn during training that their base models lack? We first present an unsupervised method that discovers a model's reasoning behaviors by training…
Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
Lorenz Hufe, Constantin Venhoff, Erblina Purelku +3
Typographic attacks exploit multi-modal systems by injecting text into images, leading to targeted misclassifications, malicious content generation and even Vision-Language Model j…
Reasoning-Finetuning Repurposes Latent Representations in Base Models
Jake Ward, Chuqiao Lin, Constantin Venhoff +1
Backtracking, an emergent behavior elicited by reasoning fine-tuning, has been shown to be a key mechanism in reasoning models' enhanced capabilities. Prior work has succeeded in m…
How Visual Representations Map to Language Feature Space in Multimodal LLMs
Constantin Venhoff, Ashkan Khakzar, Sonia Joseph +2
Effective multimodal reasoning depends on the alignment of visual and linguistic representations, yet the mechanisms by which vision-language models (VLMs) achieve this alignment r…
Understanding Reasoning in Thinking Language Models via Steering Vectors
Constantin Venhoff, Iván Arcuschin, Philip Torr +2
Recent advances in large language models (LLMs) have led to the development of thinking language models that generate extensive internal reasoning chains before producing responses…
Mixture of Experts Made Intrinsically Interpretable
Xingyi Yang, Constantin Venhoff, Ashkan Khakzar +4
Neurons in large language models often exhibit \emph{polysemanticity}, simultaneously encoding multiple unrelated concepts and obscuring interpretability. Instead of relying on pos…
SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders
Constantin Venhoff, Anisoara Calinescu, Philip Torr +1
A key challenge in interpretability is to decompose model activations into meaningful features. Sparse autoencoders (SAEs) have emerged as a promising tool for this task. However,…