Institution profile

Technical University of Denmark

Academic institutioneurope · dk
Official website
Research library528linked papers
Opportunities0open roles
Selected work

Representative Papers

Equivariant Neural Diffusion for Molecule Generation

Jun 12, 2025Neural Information Processing Systems

Existing 3D molecular diffusion models struggle to simultaneously satisfy SE(3) equivariance and high generation quality. To address this, we propose the first equivariant neural diffusion model specifically designed for 3D molecular generation. Our core innovation is a learnable, time- and data-dependent equivariant forward process—enabling strict SE(3) equivariance (i.e., invariance under rigid rotations and translations) in diffusion modeling for the first time, thereby overcoming the limitations of conventional fixed noise schedules. The model integrates an SE(3)-equivariant neural network backbone with a coordinate-aware denoising architecture, preserving theoretical equivariance while substantially enhancing representational capacity and generative flexibility. Extensive experiments on standard molecular generation benchmarks demonstrate state-of-the-art or best-in-class performance in both unconditional and conditional generation tasks. Moreover, the generated molecules exhibit significantly improved validity, chemical feasibility, and structural fidelity.

11 citationsRead paper

NUDF: Neural Unsigned Distance Fields for High Resolution 3D Medical Image Segmentation

Mar 28, 2022IEEE International Symposium on Biomedical Imaging

High-resolution 3D medical image segmentation faces dual challenges of memory bottlenecks and fine-detail loss, especially for topologically complex and morphologically variable structures such as the left atrial appendage. To address this, we propose Neural Unsigned Distance Fields (NUDF), the first method to introduce neural implicit distance fields into medical image segmentation. NUDF employs a coordinate-encoded MLP to directly learn a continuous unsigned distance field from raw CT volumes, thereby avoiding downsampling artifacts and memory constraints inherent to discrete voxel grids. It enables high-fidelity 3D mesh reconstruction with arbitrary topology—including open surfaces—and incorporates continuous distance-based supervision alongside end-to-end differentiable mesh extraction. Evaluated on left atrial appendage segmentation in CT, NUDF achieves sub-voxel accuracy (mean surface error ≈ voxel spacing), significantly outperforming conventional discrete voxel-based methods while reducing memory consumption by an order of magnitude.

4 citations1 influentialRead paper

An Overview of Cyber Security Funding for Open Source Software

Dec 08, 2024arXiv.org

Open-source software (OSS) serves as critical infrastructure yet faces persistent security maintenance and sustainability crises due to chronic human resource shortages. Method: This study investigates cybersecurity-oriented OSS funding mechanisms, conducting a qualitative thematic analysis of policy documents, project reports, and funding data from two specialized funding organizations. Drawing on critical infrastructure theory, OSS sustainability research, and cybersecurity regulatory frameworks (e.g., GDPR, NIS2), it integrates these perspectives for the first time. Contribution/Results: The analysis identifies core funded domains—including network supply chains, cryptographic libraries, programming languages, and OS-level components—and reveals that funding decisions are jointly driven by cybersecurity imperatives and sustainability goals—neither alone suffices. A multidimensional funding logic framework is proposed, explicitly linking technical, regulatory, and socio-organizational dimensions. Findings provide both theoretical grounding and actionable guidance for refining OSS security funding strategies.

2 citationsRead paper

Load constrained wind farm flow control through multi-objective multi-agent reinforcement learning

Apr 13, 2026

This study presents a multi-agent reinforcement learning (MARL) framework for load-constrained wind farm flow control (WFFC). While wake steering can enhance total wind farm power, it often introduces increased structural loads on downstream turbines. To address this, we integrate an Independent Soft Actor-Critic (I-SAC) architecture with a data-driven, local inflow sector-averaged surrogate model to provide real-time estimates of Damage Equivalent Loads (DELs). By incorporating these estimates into a shaped reward function, turbine-specific agents are trained to maximize power production while adhering to specific load-increase thresholds ($\Delta_{max}$) of 10%, 20%, and 30% relative to a baseline controller. The framework is implemented within the WindGym environment using the DYNAMIKS flow solver with Dynamic Wake Meandering (DWM) model to capture non-stationary wake physics. Results indicate that the MARL agents successfully learn collaborative policies that prioritise power gain while actively retreating from high-DEL control strategies.

1 citationsRead paper

Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning

Jan 26, 2026

This study addresses catastrophic forgetting in large language models during continual fine-tuning, wherein learning new tasks leads to the loss of previously acquired knowledge. Through systematic investigation on Transformer models ranging from 109B to 400B parameters, the work reveals for the first time that this phenomenon is jointly driven by interference in attention weight gradients, drift in intermediate layer representations, and flattening of the loss landscape. Employing sequential task fine-tuning, gradient alignment analysis, representational similarity metrics, and perturbation tracking of attention heads, the authors demonstrate a strong correlation between forgetting severity and task similarity (Pearson r = 0.87). Notably, 15%–23% of critical attention heads suffer significant degradation during fine-tuning, with lower layers exhibiting heightened sensitivity, thereby providing both mechanistic insight and empirical grounding for continual learning in large-scale models.

1 citationsRead paper
Recent publications

Latest Papers