AIConfPaper
← Search

Oliver Deussen

13 accepted papers

2026

AutoPercep: A Pipeline for Onboard Neighbor Position Estimation Toward Large-Scale Swarm Robotics

Ruiheng Wu, Simay Atasoy Bingöl, Oliver Deussen, Heiko Hamann, Iain D. Couzin, Andreagiovanni Reina +1
ICRA 2026poster

Autonomous mobile robots must know each other's positions to coordinate their actions and motion. Beyond collision avoidance, relative position estimation is essential for spatial coordination tasks such as collective motion, leader–follower dynamics, or formation control.To overcome the scalability…

Cited by 0code ↗Scholar ↗
2026

SongEcho: Towards Cover Song Generation via Instance-Adaptive Element-wise Linear Modulation

Sifei Li, Yang Li, Zizhou Wang, Yuxin Zhang, Fuzhang Wu, Oliver Deussen +2
ICLR 2026poster

Cover songs constitute a vital aspect of musical culture, preserving the core melody of an original composition while reinterpreting it to infuse novel emotional depth and thematic emphasis. Although prior research has explored the reinterpretation of instrumental music through melody-conditioned te…

Cited by 0Source ↗code ↗Scholar ↗
2024

Lighting Image/Video Style Transfer Methods by Iterative Channel Pruning

Kexin Wu, Fan Tang, Ning Liu, Oliver Deussen, Thi Ngoc Hanh Le, Weiming Dong +1
ICASSP 2024accepted

Deploying style transfer methods on resource-constrained devices is challenging, which limits their real-world applicability. To tackle this issue, we propose using pruning techniques to accelerate various visual style transfer methods. We argue that typical pruning methods may not be well-suited fo…

Cited by 0Source ↗Scholar ↗
2024

Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms

Felix Petersen, Christian Borgelt, Tobias Sutter, Hilde Kuehne, Oliver Deussen, Stefano Ermon
NeurIPS 2024poster

When training neural networks with custom objectives, such as ranking losses and shortest-path losses, a common problem is that they are, per se, non-differentiable. A popular approach is to continuously relax the objectives to provide gradients, enabling learning. However, such differentiable relax…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2024

Uncertainty Quantification via Stable Distribution Propagation

Felix Petersen, Aashwin Ananda Mishra, Hilde Kuehne, Christian Borgelt, Oliver Deussen, Mikhail Yurochkin
ICLR 2024poster

We propose a new approach for propagating stable probability distributions through neural networks. Our method is based on local linearization, which we show to be an optimal approximation in terms of total variation distance for the ReLU non-linearity. This allows propagating Gaussian and Cauchy in…

Cited by 9Source ↗PDF ↗Scholar ↗
2023

ISAAC Newton: Input-based Approximate Curvature for Newton's Method

Felix Petersen, Tobias Sutter, Christian Borgelt, Dongsung Huh, Hilde Kuehne, Yuekai Sun +1
ICLR 2023poster

We present ISAAC (Input-baSed ApproximAte Curvature), a novel method that conditions the gradient using selected second-order information and has an asymptotically vanishing computational overhead, assuming a batch size smaller than the number of neurons. We show that it is possible to compute a goo…

Cited by 9Source ↗PDF ↗code ↗Scholar ↗
2022

Deep Differentiable Logic Gate Networks

Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen
NeurIPS 2022accept

Recently, research has increasingly focused on developing efficient neural network architectures. In this work, we explore logic gate networks for machine learning tasks by learning combinations of logic gates. These networks comprise logic gates such as "AND" and "XOR", which allow for very fast ex…

Cited by 40Source ↗PDF ↗code ↗Scholar ↗
2022

Differentiable Top-k Classification Learning

Felix Petersen, Hilde Kuehne, Christian Borgelt, Oliver Deussen
ICML 2022spotlight

The top-k classification accuracy is one of the core metrics in machine learning. Here, k is conventionally a positive integer, such as 1 or 5, leading to top-1 or top-5 training objectives. In this work, we relax this assumption and optimize the model for multiple k simultaneously instead of using…

Cited by 43Source ↗PDF ↗code ↗Scholar ↗
2022

GenDR: A Generalized Differentiable Renderer

Felix Petersen, Bastian Goldluecke, Christian Borgelt, Oliver Deussen
CVPR 2022poster

In this work, we present and study a generalized family of differentiable renderers. We discuss from scratch which components are necessary for differentiable rendering and formalize the requirements for each component.We instantiate our general differentiable renderer, which generalizes existing di…

Cited by 30PDF ↗code ↗Scholar ↗
2022

Monotonic Differentiable Sorting Networks

Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen
ICLR 2022poster

Differentiable sorting algorithms allow training with sorting and ranking supervision, where only the ordering or ranking of samples is known. Various methods have been proposed to address this challenge, ranging from optimal transport-based differentiable Sinkhorn sorting algorithms to making class…

Cited by 32Source ↗PDF ↗code ↗Scholar ↗
2021

Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision

Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen
ICML 2021spotlight

Sorting and ranking supervision is a method for training neural networks end-to-end based on ordering constraints. That is, the ground truth order of sets of samples is known, while their absolute values remain unsupervised. For that, we propose differentiable sorting networks by relaxing their pair…

Cited by 43Source ↗PDF ↗Scholar ↗
2021

Learning with Algorithmic Supervision via Continuous Relaxations

Felix Petersen, Christian Borgelt, Hilde Kuehne, Oliver Deussen
NeurIPS 2021poster

The integration of algorithmic components into neural architectures has gained increased attention recently, as it allows training neural networks with new forms of supervision such as ordering constraints or silhouettes instead of using ground truth labels. Many approaches in the field focus on the…

Cited by 35Source ↗PDF ↗code ↗Scholar ↗