|
name
|
twitter:site
|
@idivinci
|
|
name
|
twitter:title
|
Selected Research Projects
|
|
name
|
twitter:description
|
Interestingness as an Inductive Heuristic for Future Compression Progress Vincent Herrmann, Jürgen Schmidhuber Interestingness is an essential ingredient for open-ended learning and artificial general intelligence. It can be described as a heuristic assessing the pote... Multiple Token Divergence—Measuring and Steering In-Context Computation Density Vincent Herrmann*, Eric Alcaide*, Michael Wand, Jürgen Schmidhuber The divergence between the prediction distributions of the full model and a computational shortcut allows us to measure and steer the computational effort of... Measuring In-Context Computation Complexity via Hidden State Prediction Vincent Herrmann, Róbert Csordás, Jürgen Schmidhuber Can we measure when to what degree a sequence model or LLM is doing something interesting? We propose hidden state unpredictability as a measure, and show th... Automatic Album Sequencing Vincent Herrmann*, Dylan Ashley*, Jürgen Schmidhuber We present a tool that automatically sequences an arbitrary collection of music tracks into multiple coherent orders. The underlying model was trained on man... On the Distillation of Stories for Transferring Narrative Arcs in Collections of Independent Media Dylan Ashley*, Vincent Herrmann*, Zachary Friggstad, Jürgen Schmidhuber The act of telling stories is a fundamental part of what it means to be human. This work introduces the concept of narrative information, which we define to ... Learning useful representations of recurrent neural network weight matrices Vincent Herrmann, Francesco Faccio, Jürgen Schmidhuber Recurrent Neural Networks are general-purpose computers. The program of an RNN is its weight matrix. How to learn useful representations of RNN weights that ... Unsupervised Musical Object Discovery from Audio Joonsu Gha, Vincent Herrmann, Jürgen Schmidhuber, Anand Gopalakrishnan Our novel MusicSlots method adapts SlotAttention to the audio domain, to achieve unsupervised music decomposition. Mindstorms in natural language-based societies of mind Mingchen Zhuge*, Haozhe Liu*, Francesco Faccio*, Dylan Ashley*, Róbert Csordás, Anand Gopalakrishnan, Abdullah Hamdi, Hasan Abed Al Kader Hammoud, Vincent Herrmann, et al. We imagine societies of mind as consisting of a collection of multimodal neural networks, including large language models, which engage in a “mindstorm” to s... Goal-conditioned generators of deep policies Francesco Faccio*, Vincent Herrmann*, Aditya Ramesh, Louis Kirsch, Jürgen Schmidhuber We study goal-conditioned neural nets (NNs) that learn to generate deep NN policies in form of context-specific weight matrices, similar to Fast Weight Progr... Learning one abstract bit at a time through self-invented experiments encoded as neural networks Vincent Herrmann, Louis Kirsch, Jürgen Schmidhuber There are two important things in science–finding answers to given questions, and coming up with good questions. Our artificial scientists not only learn to ... Generative Transformer-based Models of Symbolic Polyphonic Music Vincent Herrmann Master thesis on generating classical music with the help of transformers. Written at the Bosch Center for Artificial Intelligence. Immersions - Visualizing and sonifying how an artificial ear hears music Vincent Herrmann Real-time exploration of a sound processing neural network. Some Wavelet Visualizations Vincent Herrmann Recently I started to learn how to use d3.js, a JavaScript library for interactive data-driven visualizations. As a first little project, I decided to make i... Wasserstein GAN and the Kantorovich-Rubinstein Duality Vincent Herrmann Derivation of the Kantorovich-Rubinstein duality for the use in Wasserstein Generative Adversarial Networks Wavelets II - Vanishing Moments and Spectral Factorization Vincent Herrmann Explanation of the most important properties of Daubechies wavelets and the algorithm to calculate them Wavelets I - From Filter Banks to the Dilation Equation Vincent Herrmann Derivation of the dilation and wavelet equation from an implementation of the Fast Wavelet Transform Werden Roboter jemals so werden wie wir? (German) Vincent Herrmann Dies ist ein kurzes Essay, das ich im Frühjahr 2016 zu einer vorgegebenen Fragestellung geschrieben habe:Werden Roboter jemals so werden wie wir? Und wolle...
|
|
name
|
twitter:url
|
https://vincentherrmann.github.io/research/
|
|
name
|
twitter:card
|
summary
|
|
name
|
HandheldFriendly
|
True
|
|
name
|
MobileOptimized
|
320
|
|
name
|
viewport
|
width=device-width, initial-scale=1.0
|
|
property
|
og:locale
|
en
|
|
property
|
og:site_name
|
Vincent Herrmann
|
|
property
|
og:title
|
Selected Research Projects
|
|
property
|
og:url
|
https://vincentherrmann.github.io/research/
|
|
property
|
og:description
|
Interestingness as an Inductive Heuristic for Future Compression Progress Vincent Herrmann, Jürgen Schmidhuber Interestingness is an essential ingredient for open-ended learning and artificial general intelligence. It can be described as a heuristic assessing the pote... Multiple Token Divergence—Measuring and Steering In-Context Computation Density Vincent Herrmann*, Eric Alcaide*, Michael Wand, Jürgen Schmidhuber The divergence between the prediction distributions of the full model and a computational shortcut allows us to measure and steer the computational effort of... Measuring In-Context Computation Complexity via Hidden State Prediction Vincent Herrmann, Róbert Csordás, Jürgen Schmidhuber Can we measure when to what degree a sequence model or LLM is doing something interesting? We propose hidden state unpredictability as a measure, and show th... Automatic Album Sequencing Vincent Herrmann*, Dylan Ashley*, Jürgen Schmidhuber We present a tool that automatically sequences an arbitrary collection of music tracks into multiple coherent orders. The underlying model was trained on man... On the Distillation of Stories for Transferring Narrative Arcs in Collections of Independent Media Dylan Ashley*, Vincent Herrmann*, Zachary Friggstad, Jürgen Schmidhuber The act of telling stories is a fundamental part of what it means to be human. This work introduces the concept of narrative information, which we define to ... Learning useful representations of recurrent neural network weight matrices Vincent Herrmann, Francesco Faccio, Jürgen Schmidhuber Recurrent Neural Networks are general-purpose computers. The program of an RNN is its weight matrix. How to learn useful representations of RNN weights that ... Unsupervised Musical Object Discovery from Audio Joonsu Gha, Vincent Herrmann, Jürgen Schmidhuber, Anand Gopalakrishnan Our novel MusicSlots method adapts SlotAttention to the audio domain, to achieve unsupervised music decomposition. Mindstorms in natural language-based societies of mind Mingchen Zhuge*, Haozhe Liu*, Francesco Faccio*, Dylan Ashley*, Róbert Csordás, Anand Gopalakrishnan, Abdullah Hamdi, Hasan Abed Al Kader Hammoud, Vincent Herrmann, et al. We imagine societies of mind as consisting of a collection of multimodal neural networks, including large language models, which engage in a “mindstorm” to s... Goal-conditioned generators of deep policies Francesco Faccio*, Vincent Herrmann*, Aditya Ramesh, Louis Kirsch, Jürgen Schmidhuber We study goal-conditioned neural nets (NNs) that learn to generate deep NN policies in form of context-specific weight matrices, similar to Fast Weight Progr... Learning one abstract bit at a time through self-invented experiments encoded as neural networks Vincent Herrmann, Louis Kirsch, Jürgen Schmidhuber There are two important things in science–finding answers to given questions, and coming up with good questions. Our artificial scientists not only learn to ... Generative Transformer-based Models of Symbolic Polyphonic Music Vincent Herrmann Master thesis on generating classical music with the help of transformers. Written at the Bosch Center for Artificial Intelligence. Immersions - Visualizing and sonifying how an artificial ear hears music Vincent Herrmann Real-time exploration of a sound processing neural network. Some Wavelet Visualizations Vincent Herrmann Recently I started to learn how to use d3.js, a JavaScript library for interactive data-driven visualizations. As a first little project, I decided to make i... Wasserstein GAN and the Kantorovich-Rubinstein Duality Vincent Herrmann Derivation of the Kantorovich-Rubinstein duality for the use in Wasserstein Generative Adversarial Networks Wavelets II - Vanishing Moments and Spectral Factorization Vincent Herrmann Explanation of the most important properties of Daubechies wavelets and the algorithm to calculate them Wavelets I - From Filter Banks to the Dilation Equation Vincent Herrmann Derivation of the dilation and wavelet equation from an implementation of the Fast Wavelet Transform Werden Roboter jemals so werden wie wir? (German) Vincent Herrmann Dies ist ein kurzes Essay, das ich im Frühjahr 2016 zu einer vorgegebenen Fragestellung geschrieben habe:Werden Roboter jemals so werden wie wir? Und wolle...
|
|
property
|
og:type
|
article
|
|
property
|
article:published_time
|
2026-06-08T12:50:11+00:00
|
