135 citations · 193 across the 12 of their papers we have counts for
14 papers
OpenAssistant Conversations -- Democratizing Large Language Model Alignment
Andreas Köpf, Yannic Kilcher, Dimitri von Rütte +15
Aligning large language models (LLMs) with human preferences has proven to drastically improve usability and has driven rapid adoption as demonstrated by ChatGPT. Alignment techniq…
FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control
Dimitri von Rütte, Luca Biggio, Yannic Kilcher +1
Generating music with deep neural networks has been an area of active research in recent years. While the quality of generated samples has been steadily increasing, most methods ar…
Boosting Search Engines with Interactive Agents
Leonard Adolphs, Benjamin Boerschinger, Christian Buck +8
This paper presents first successful steps in designing search agents that learn meta-strategies for iterative query refinement in information-seeking tasks. Our approach uses mach…
Generative Minimization Networks: Training GANs Without Competition
Paulina Grnarova, Yannic Kilcher, Kfir Y. Levy +2
Many applications in machine learning can be framed as minimization problems and solved efficiently using gradient-based techniques. However, recent applications of generative mode…
Rethinking Neural Networks With Benford's Law
Surya Kant Sahu, Abhinav Java, Arshad Shaikh +1
Benford's Law (BL) or the Significant Digit Law defines the probability distribution of the first digit of numerical values in a data sample. This Law is observed in many naturally…
Meta Answering for Machine Reading
Benjamin Borschinger, Jordan Boyd-Graber, Christian Buck +7
We investigate a framework for machine reading, inspired by real world information-seeking problems, where a meta question answering system interacts with a black box environment.…
Adversarial Training is a Form of Data-dependent Operator Norm Regularization
Kevin Roth, Yannic Kilcher, Thomas Hofmann
We establish a theoretical link between adversarial training and operator norm regularization for deep neural networks. Specifically, we prove that -norm constrained projec…
The Odds are Odd: A Statistical Test for Detecting Adversarial Examples
Kevin Roth, Yannic Kilcher, Thomas Hofmann
We investigate conditions under which test statistics exist that can reliably detect examples, which have been adversarially manipulated in a white-box attack. These statistics can…
The best defense is a good offense: Countering black box attacks by predicting slightly wrong labels
Yannic Kilcher, Thomas Hofmann
Black-Box attacks on machine learning models occur when an attacker, despite having no access to the inner workings of a model, can successfully craft an attack by means of model t…
Parametrizing filters of a CNN with a GAN
Yannic Kilcher, Gary Becigneul, Thomas Hofmann
It is commonly agreed that the use of relevant invariances as a good statistical bias is important in machine-learning. However, most approaches that explicitly incorporate invaria…
Flexible Prior Distributions for Deep Generative Models
Yannic Kilcher, Aurelien Lucchi, Thomas Hofmann
We consider the problem of training generative models with deep neural networks as generators, i.e. to map latent codes to data points. Whereas the dominant paradigm combines simpl…
Semantic Interpolation in Implicit Models
Yannic Kilcher, Aurelien Lucchi, Thomas Hofmann
In implicit models, one often interpolates between sampled points in latent space. As we show in this paper, care needs to be taken to match-up the distributional assumptions on co…
Generator Reversal
Yannic Kilcher, Aurélien Lucchi, Thomas Hofmann
We consider the problem of training generative models with deep neural networks as generators, i.e. to map latent codes to data points. Whereas the dominant paradigm combines simpl…
Scalable Adaptive Stochastic Optimization Using Random Projections
Gabriel Krummenacher, Brian McWilliams, Yannic Kilcher +2
Adaptive stochastic gradient methods such as AdaGrad have gained popularity in particular for training deep neural networks. The most commonly used and studied variant maintains a…