3 papers
cs.CV2024
HyperCLIP: Adapting Vision-Language models with Hypernetworks
Victor Akinwande, Mohammad Sadegh Norouzzadeh, Devin Willmott +3
Self-supervised vision-language models trained with contrastive objectives form the basis of current state-of-the-art methods in AI vision tasks. The success of these models is a d…
cs.LG2024
AcceleratedLiNGAM: Learning Causal DAGs at the speed of GPUs
Victor Akinwande, J. Zico Kolter
Existing causal discovery methods based on combinatorial optimization or search are slow, prohibiting their application on large-scale datasets. In response, more recent methods at…
cs.LG2023
Understanding prompt engineering may not require rethinking generalization
Victor Akinwande, Yiding Jiang, Dylan Sam +1
Zero-shot learning in prompted vision-language models, the practice of crafting prompts to build classifiers without an explicit training process, has achieved impressive performan…