79 citations · 231 across the 15 of their papers we have counts for
15 papers
MAPS: Masked Attribution-based Probing of Strategies- A computational framework to align human and model explanations
Sabine Muzellec, Yousif Kashef Alghetaa, Simon Kornblith +1
Human core object recognition depends on the selective use of visual information, but the strategies guiding these choices are difficult to measure directly. We present MAPS (Maske…
Objective drives the consistency of representational similarity across datasets
Laure Ciernik, Lorenz Linhardt, Marco Morik +3
The Platonic Representation Hypothesis claims that recent foundation models are converging to a shared representation space as a function of their downstream task performance, irre…
When Does Perceptual Alignment Benefit Vision Representations?
Shobhita Sundaram, Stephanie Fu, Lukas Muttenthaler +5
Humans judge perceptual similarity according to diverse visual attributes, including scene layout, subject location, and camera pose. Existing vision models understand a wide range…
Aligning Machine and Human Visual Representations across Abstraction Levels
Lukas Muttenthaler, Klaus Greff, Frieda Born +6
Deep neural networks have achieved success across a wide range of applications, including as models of human behavior and neural representations in vision tasks. However, neural ne…
Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability
Jiri Hron, Laura Culp, Gamaleldin Elsayed +28
While many capabilities of language models (LMs) improve with increased training budget, the influence of scale on hallucinations is not yet fully understood. Hallucinations come i…
Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?
C. Daniel Freeman, Laura Culp, Aaron Parisi +27
We introduce and study the problem of adversarial arithmetic, which provides a simple yet challenging testbed for language model alignment. This problem is comprised of arithmetic…
Probing clustering in neural network representations
Thao Nguyen, Simon Kornblith
Neural network representations contain structure beyond what was present in the training labels. For instance, representations of images that are visually or semantically similar t…
Replacing softmax with ReLU in Vision Transformers
Mitchell Wortsman, Jaehoon Lee, Justin Gilmer +1
Previous research observed accuracy degradation when replacing the attention softmax with a point-wise activation such as ReLU. In the context of vision transformers, we find that…
Small-scale proxies for large-scale Transformer training instabilities
Mitchell Wortsman, Peter J. Liu, Lechao Xiao +13
Teams that have trained large Transformer-based models have reported training instabilities at large scale that did not appear when training with the same hyperparameters at smalle…
Getting aligned on representational alignment
Ilia Sucholutsky, Lukas Muttenthaler, Adrian Weller +30
Biological and artificial information processing systems form representations of the world that they can use to categorize, reason, plan, navigate, and make decisions. How can we m…
OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models
Anas Awadalla, Irena Gao, Josh Gardner +13
We introduce OpenFlamingo, a family of autoregressive vision-language models ranging from 3B to 9B parameters. OpenFlamingo is an ongoing effort to produce an open-source replicati…
Guiding Image Captioning Models Toward More Specific Captions
Simon Kornblith, Lala Li, Zirui Wang +1
Image captioning is conventionally formulated as the task of generating captions for images that match the distribution of reference image-caption pairs. However, reference caption…
Towards Generalist Biomedical AI
Tao Tu, Shekoofeh Azizi, Danny Driess +29
Medicine is inherently multimodal, with rich data modalities spanning text, imaging, genomics, and more. Generalist biomedical artificial intelligence (AI) systems that flexibly en…
Synthetic Data from Diffusion Models Improves ImageNet Classification
Shekoofeh Azizi, Simon Kornblith, Chitwan Saharia +2
Deep generative models are becoming increasingly powerful, now generating diverse high fidelity photo-realistic samples given text prompts. Have they reached the point where models…
Cost-Efficient Online Hyperparameter Optimization
Jingkang Wang, Mengye Ren, Ilija Bogunovic +2
Recent work on hyperparameters optimization (HPO) has shown the possibility of training certain hyperparameters together with regular parameters. However, these online HPO algorith…