no code implementations • 12 Dec 2023 • Tom Davidson, Jean-Stanislas Denain, Pablo Villalobos, Guillem Bas
State-of-the-art AI systems can be significantly improved without expensive retraining via "post-training enhancements"-techniques applied after initial training like fine-tuning the system to use a web browser.
1 code implementation • 18 Jul 2023 • Danny Halawi, Jean-Stanislas Denain, Jacob Steinhardt
The first phenomenon, overthinking, appears when we decode predictions from intermediate layers, given correct vs. incorrect few-shot demonstrations.
1 code implementation • 27 Jun 2022 • Jean-Stanislas Denain, Jacob Steinhardt
Model visualizations provide information that outputs alone might miss.
no code implementations • NeurIPS 2021 • Frances Ding, Jean-Stanislas Denain, Jacob Steinhardt
To understand neural network behavior, recent works quantitatively compare different networks' learned representations using canonical correlation analysis (CCA), centered kernel alignment (CKA), and other dissimilarity measures.
3 code implementations • 3 Aug 2021 • Frances Ding, Jean-Stanislas Denain, Jacob Steinhardt
To understand neural network behavior, recent works quantitatively compare different networks' learned representations using canonical correlation analysis (CCA), centered kernel alignment (CKA), and other dissimilarity measures.
no code implementations • 27 Feb 2020 • Achille Thin, Nikita Kotelevskii, Jean-Stanislas Denain, Leo Grinsztajn, Alain Durmus, Maxim Panov, Eric Moulines
In this contribution, we propose a new computationally efficient method to combine Variational Inference (VI) with Markov Chain Monte Carlo (MCMC).