Vision Sparse Autoencoders (SAEs) have become a popular tool in Mechanistic Interpretability due to their presumed ability to disentangle complex features learned by a model into monosemantic concepts. Despite their growing popularity, evaluating their interpretability remains an active topic of research. The bedrock m...
Teodor Chiaburu, Franz Motzkus, Frank Haußer et al.· 0 citations
This work develops PolyChirp, an approach combining biological domain expertise, automated dataset curation, neural architecture optimization and novel hardware to achieve multiclass bird species detection in the wild using newly designed tiny multiclass models that leverage recent microcontrollers and hardware acceler...
Nathan Duboisset, Zhaolan Huang, F. Biessmann et al.· 0 citations
Today most media content is consumed based on algorithmic recommendations. Evidence suggests that this can lead to politically biased media consumption patterns. Automated extraction of political agendas from texts can reveal and analyze political biases in online media -- and thus help fostering politically unbiased m...
This work evaluates Constrained Bayesian Optimization with the primary objective of minimizing energy consumption and subject to the constraint that the generalization performance is above some threshold and demonstrates that CBO achieves lower energy consumption without compromising the predictive performance of ML mo...
Pallavi Mitra, F. Biessmann· arXiv.org· 0 citations
These findings demonstrate that energy efficient model cascades require evaluation beyond clean accuracy, with explicit attention to routing reliability under distribution shift, and select a model cascade at the pareto-optimum of accuracy, routing quality, and energy consumption that achieves competitive predictive pe...
Pallavi Mitra, J. Kushwaha, F. Biessmann· 0 citations
The extraction of structured information from unstructured documents represents a critical component of digital transformations in all sectors. While proprietary solutions dominate commercial applications, a rapidly growing ecosystem of open-source Optical Character Recognition (OCR) engines, Large Language Models (LLM...
Large Language Models (LLMs) are being increasingly used in everyday applications. A major challenge in the context of LLMs or Artificial Intelligence (AI) in general is to ensure privacy when using them, meaning that personally identifiable information (PII) is removed from any text that enters an LLM. These challenge...
S. K. Saha, Tom Röhr, F. Biessmann· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
