3 citations · 4 across the 11 of their papers we have counts for
12 papers
BMND: Direct Poisson Denoising by N-Dimensional Block Matching and Collaborative Filtering
Christof Duhme, Lars Schiefelbein, Florian Büther +1
Poisson denoising of scientific data requires methods that account for signal-dependent noise while accommodating different data dimensionalities and preserving quantitative intens…
UNIFUSION: Adapting Autoregressive Language Models into Discrete Diffusion under a Unified Reverse-Rate Objective
Xiaoyi Jiang, Jingyuan Li, Yixuan Jiang +4
Existing methods mainly adapt pretrained autoregressive (AR) language models to masked diffusion, whereas we directly adapt them to uniform-noise diffusion, where every token remai…
Mean-to-Score Discrete Diffusion: Posterior-Mean Denoisers for Score Entropy
Jingyuan Li, Xiaoyi Jiang, Yixuan Jiang +4
Score Entropy Discrete Diffusion (SEDD) parameterizes discrete reverse processes with unconstrained positive score ratios. While positivity guarantees nonnegative reverse jump rate…
OLEDLM: A Unified Language Model for OLED Molecular Design
Fukang Wen, Yuchong Tang, Jingyuan Li +9
The development of organic light-emitting diode (OLED) materials faces the compounded challenges of an astronomically large chemical space, stringent quantum-chemical constraints,…
Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and Direction
Jingyuan Li, Xiaoyi Jiang, Fukang Wen +5
Discrete diffusion models based on continuous-time Markov chains (CTMCs) have shown strong performance on language and discrete data generation, yet existing approaches typically p…
Covariance-Aware Goodness for Scalable Forward-Forward Learning
Xiaoyi Jiang, Bashir M. Al-Hashimi, Kai Xu
The Forward-Forward algorithm eliminates global gradient flow and full network activations storage. However, in convolutional settings, existing BP-free FF methods significantly un…
Exploring Sparsity and Smoothness of Arbitrary Lp Norms in Adversarial Attacks
Christof Duhme, Florian Eilers, Xiaoyi Jiang
Adversarial attacks against deep neural networks are commonly constructed under norm constraints, most often using , or , and potentially regularized…
Perturbing the Phase: Analyzing Adversarial Robustness of Complex-Valued Neural Networks
Florian Eilers, Christof Duhme, Xiaoyi Jiang
Complex-valued neural networks (CVNNs) are rising in popularity for all kinds of applications. To safely use CVNNs in practice, analyzing their robustness against outliers is cruci…
Transformer-based Parameter Fitting of Models derived from Bloch-McConnell Equations for CEST MRI Analysis
Christof Duhme, Chris Lippe, Verena Hoerr +1
Chemical exchange saturation transfer (CEST) MRI is a non-invasive imaging modality for detecting metabolites. It offers higher resolution and sensitivity compared to conventional…
Clifford Kolmogorov-Arnold Networks
Matthias Wolff, Francesco Alesiani, Christof Duhme +1
We introduce Clifford Kolmogorov-Arnold Network (ClKAN), a flexible and efficient architecture for function approximation in arbitrary Clifford Algebra spaces. We propose the use o…
CVKAN: Complex-Valued Kolmogorov-Arnold Networks
Matthias Wolff, Florian Eilers, Xiaoyi Jiang
In this work we propose CVKAN, a complex-valued Kolmogorov-Arnold Network (KAN), to join the intrinsic interpretability of KANs and the advantages of Complex-Valued Neural Networks…
DeepCSHAP: Utilizing Shapley Values to Explain Deep Complex-Valued Neural Networks
Florian Eilers, Xiaoyi Jiang
Deep Neural Networks are widely used in academy as well as corporate and public applications, including safety critical applications such as health care and autonomous driving. The…