37 citations · 46 across the 7 of their papers we have counts for
8 papers
REKI: Registering Knowledge in VLAs
Juliette Marrie, Paul Pacaud, Adrien Ramanana Rahary +2
We introduce REKI, a 2.4B vision-language-action model (VLA) pretrained exclusively on public data that sets a new Pareto frontier between performance and model size: on LIBERO-Plu…
Multiplayer Interactive World Models with Representation Autoencoders
Anthony Hu, Václav Volhejn, Adrien Ramanana Rahary +24
We introduce the first multiplayer world model for highly dynamic environments governed by complex physical interactions. Whereas single-player world models treat the other agents…
CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion
Moritz Böhle, Amélie Royer, Juliette Marrie +2
Vision-language models (VLMs) are commonly trained by directly inserting image tokens from a pretrained vision encoder into the text stream of a language model. This allows text an…
B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
Shreyash Arya, Sukrut Rao, Moritz Böhle +1
B-cos Networks have been shown to be effective for obtaining highly human interpretable explanations of model decisions by architecturally enforcing stronger alignment between inpu…
Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
Sukrut Rao, Sweta Mahajan, Moritz Böhle +1
Concept Bottleneck Models (CBMs) have recently been proposed to address the 'black-box' problem of deep neural networks, by first mapping images to a human-understandable concept s…
Good Teachers Explain: Explanation-Enhanced Knowledge Distillation
Amin Parchami-Araghi, Moritz Böhle, Sukrut Rao +1
Knowledge Distillation (KD) has proven effective for compressing large teacher models into smaller student models. While it is well known that student models can achieve similar ac…
Temperature Schedules for Self-Supervised Contrastive Methods on Long-Tail Data
Anna Kukleva, Moritz Böhle, Bernt Schiele +2
Most approaches for self-supervised learning (SSL) are optimised on curated balanced datasets, e.g. ImageNet, despite the fact that natural data usually exhibits long-tail distribu…
Towards Better Understanding Attribution Methods
Sukrut Rao, Moritz Böhle, Bernt Schiele
Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been…