Zobrazeno 1 - 10
of 12 935
pro vyhledávání: '"Bau, A"'
Autor:
Mueller, Aaron, Brinkmann, Jannik, Li, Millicent, Marks, Samuel, Pal, Koyena, Prakash, Nikhil, Rager, Can, Sankaranarayanan, Aruna, Sharma, Arnab Sen, Sun, Jiuding, Todd, Eric, Bau, David, Belinkov, Yonatan
Interpretability provides a toolset for understanding how and why neural networks behave in certain ways. However, there is little unity in the field: most studies employ ad-hoc evaluations and do not share theoretical foundations, making it difficul
Externí odkaz:
http://arxiv.org/abs/2408.01416
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
Autor:
Karvonen, Adam, Wright, Benjamin, Rager, Can, Angell, Rico, Brinkmann, Jannik, Smith, Logan, Verdun, Claudio Mayrink, Bau, David, Marks, Samuel
What latent features are encoded in language model (LM) representations? Recent work on training sparse autoencoders (SAEs) to disentangle interpretable features in LM representations has shown significant promise. However, evaluating the quality of
Externí odkaz:
http://arxiv.org/abs/2408.00113
Autor:
Fiotto-Kaufman, Jaden, Loftus, Alexander R, Todd, Eric, Brinkmann, Jannik, Juang, Caden, Pal, Koyena, Rager, Can, Mueller, Aaron, Marks, Samuel, Sharma, Arnab Sen, Lucchetti, Francesca, Ripa, Michael, Belfki, Adam, Prakash, Nikhil, Multani, Sumeet, Brodley, Carla, Guha, Arjun, Bell, Jonathan, Wallace, Byron, Bau, David
The enormous scale of state-of-the-art foundation models has limited their accessibility to scientists, because customized experiments at large model sizes require costly hardware and complex engineering that is impractical for most researchers. To a
Externí odkaz:
http://arxiv.org/abs/2407.14561
Publikováno v:
Physica B: Condensed Matter 2024
In this study, based on the quantum kinetic equation approach, we systematically present the radio-electric effect in asymmetric semi-parabolic quantum wells under the influence of a laser radiation field taking into account the electron-longitudinal
Externí odkaz:
http://arxiv.org/abs/2407.09938
LLMs process text as sequences of tokens that roughly correspond to words, where less common words are represented by multiple tokens. However, individual tokens are often semantically unrelated to the meanings of the words/concepts they comprise. Fo
Externí odkaz:
http://arxiv.org/abs/2406.20086
Autor:
Gölz, Thorsten, Baù, Enrico, Zhang, Jinhua, Kaltenecker, Korbinian, Trauner, Dirk, Maier, Stefan A., Keilmann, Fritz, Lohmüller, Theobald, Tittl, Andreas
Understanding the biophysical and biochemical properties of molecular nanocarriers under physiological conditions and with minimal interference is crucial for advancing nanomedicine, photopharmacology, drug delivery, nanotheranostics and synthetic bi
Externí odkaz:
http://arxiv.org/abs/2406.02513
Art reinterpretation is the practice of creating a variation of a reference work, making a paired artwork that exhibits a distinct artistic style. We ask if such an image pair can be used to customize a generative model to capture the demonstrated st
Externí odkaz:
http://arxiv.org/abs/2405.01536
Autor:
Gölz, Thorsten, Baù, Enrico, Aigner, Andreas, Mancini, Andrea, Barkey, Martin, Keilmann, Fritz, Maier, Stefan A., Tittl, Andreas
Photonic metasurfaces offer exceptional control over light at the nanoscale, facilitating applications spanning from biosensing, and nonlinear optics to photocatalysis. Many metasurfaces, especially resonant ones, rely on periodicity for the collecti
Externí odkaz:
http://arxiv.org/abs/2404.17346
Theory of local $\mathbb{Z}_{2}$ topological markers for finite and periodic two-dimensional systems
Autor:
Baù, Nicolas, Marrazzo, Antimo
Publikováno v:
Phys. Rev. B 110, 054203 (2024)
The topological phases of two-dimensional time-reversal symmetric insulators are classified by a $\mathbb{Z}_{2}$ topological invariant. Usually, the invariant is introduced and calculated by exploiting the way time-reversal symmetry acts in reciproc
Externí odkaz:
http://arxiv.org/abs/2404.04598
We investigate the mechanisms of factual recall in the Mamba state space model. Our work is inspired by previous findings in autoregressive transformer language models suggesting that their knowledge recall is localized to particular modules at speci
Externí odkaz:
http://arxiv.org/abs/2404.03646