2.2k citations · 10.5k across the 216 of their papers we have counts for
240 papers
DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models
Adam Pardyl, Siddhartha Gairola, Sukrut Rao +4
Concept-based vision models represent images through an intermediate layer of human-inspectable concepts, so what a model relies on can be traced to those concepts. However, those…
AnyBottle: A Recipe to Only Keep the Concepts You Really Need
Wolfgang Stammer, Sukrut Rao, Hevra Petekkaya +2
Concept bottleneck models (CBMs) make predictions inspectable and intervenable by routing them through human-interpretable concepts, but originally required concept annotations. An…
Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond
Simone Facchiano, Jan Eric Lenssen, Bernt Schiele +3
As state-of-the-art text-to-image flow models achieve near-photorealistic quality, controlling their outputs, e.g., suppressing harmful content while promoting benign alternatives,…
TeMo: Temperature Modulation for Multimodal Contrastive Learning
Dhimitrios Duka, Bernt Schiele, Hilde Kuehne +1
Contrastive learning approaches achieve strong performance by training models to bring similar samples closer while pushing dissimilar samples apart. A crucial component of contras…
DataComp-VLM: Improved Open Datasets for Vision-Language Models
Matteo Farina, Vishaal Udandarao, Thao Nguyen +33
Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchmarks for evaluating such curat…
TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment
Sweta Mahajan, Sukrut Rao, Jiahao Xie +2
Vision-language models such as CLIP are highly useful for diverse tasks due to their shared image-text embedding space. Despite this, the image and text embeddings are often poorly…