paper-with-me

홈 › Papers

eDIF: A European Deep Inference Fabric for Remote Interpretability of LLM

2025-08-14 · Irma Heithoff. Marc Guggenberger, Sandra Kalogiannis, Susanne Mayer, Fabian Maag, Sigurd Schacht, Carsten Lanquillon arxiv

This paper presents a feasibility study on the deployment of a European Deep Inference Fabric (eDIF), an NDIF-compatible infrastructure designed to support mechanistic interpretability research on large language models. The need for widespread accessibility of LLM interpretability infrastructure in Europe drives this initiative to democratize advanced model analysis capabilities for the research community. The project introduces a GPU-based cluster hosted at Ansbach University of Applied Sciences and interconnected with partner institutions, enabling remote model inspection via the NNsight API. A structured pilot study involving 16 researchers from across Europe evaluated the platform's technical performance, usability, and scientific utility. Users conducted interventions such as activation patching, causal tracing, and representation analysis on models including GPT-2 and DeepSeek-R1-70B. The study revealed a gradual increase in user engagement, stable platform performance throughout, and a positive reception of the remote experimentation capabilities. It also marked the starting point for building a user community around the platform. Identified limitations such as prolonged download durations for activation data as well as intermittent execution interruptions are addressed in the roadmap for future development. This initiative marks a significant step towards widespread accessibility of LLM interpretability infrastructure in Europe and lays the groundwork for broader deployment, expanded tooling, and sustained community collaboration in mechanistic interpretability research.

📄 PDF Abstract BibTeX arXiv:2508.10553

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

EDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing Image Super-Resolution

2023-10-30 · Yi Xiao, Qiangqiang Yuan, Kui Jiang, Jiang He 외

Recently, convolutional networks have achieved remarkable development in remote sensing image Super-Resoltuion (SR) by minimizing the regression objectives, e.g., MSE loss. However, despite achieving impressive performan…

Image Super-ResolutionSuper-Resolution

RSHazeDiff: A Unified Fourier-aware Diffusion Model for Remote Sensing Image Dehazing

2024-05-15 · Jiamei Xiong, Xuefeng Yan, Yongzhen Wang, Wei Zhao 외

Haze severely degrades the visual quality of remote sensing images and hampers the performance of road extraction, vehicle detection, and traffic flow monitoring. The emerging denoising diffusion probabilistic model (DDP…

DenoisingImage DehazingNoise Estimationvehicle detection

WaveDiffUR: A diffusion SDE-based solver for ultra magnification super-resolution in remote sensing images

2024-12-25 · Yue Shi, Liangxiu Han, Darren Dancy, Lianghao Han

Deep neural networks have recently achieved significant advancements in remote sensing superresolu-tion (SR). However, most existing methods are limited to low magnification rates (e.g., 2 or 4) due to the escalating ill…

Super-Resolution

MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices

2023-11-28 · Yang Zhao, Yanwu Xu, Zhisheng Xiao, HaoLin Jia 외

The deployment of large-scale text-to-image diffusion models on mobile devices is impeded by their substantial model size and slow inference speed. In this paper, we propose \textbf{MobileDiffusion}, a highly efficient t…

Computational EfficiencyImage GenerationText to Image GenerationText-to-Image Generation

Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance

2025-10-12 · Jiachi Zhao, Zehong Wang, Yamei Liao, Chuxu Zhang 외 arxiv

Graph generation is a fundamental problem in graph learning with broad applications across Web-scale systems, knowledge graphs, and scientific domains such as drug and material discovery. Recent approaches leverage diffu…

Graph GenerationKnowledge GraphsGraph Learning