Institution profile

Friedrich-Schiller-Universität Jena

Academic institutioneurope · de
Official website
Research library129linked papers
Opportunities0open roles
Selected work

Representative Papers

Autonomous Microscopy Experiments through Large Language Model Agents

Dec 18, 2024arXiv.org

Existing self-driving laboratories (SDLs) rely on static experimental protocols, limiting their ability to emulate scientists’ adaptive reasoning and intuition in dynamic environments. Method: We propose AILA, the first large language model (LLM)-based autonomous agent system for end-to-end atomic force microscopy (AFM) experimentation—encompassing experimental design, execution, analysis, and closed-loop decision-making. Contribution/Results: We introduce AFMBench, the first benchmark for evaluating LLMs in AFM-driven scientific discovery, uncovering critical deficiencies in multi-agent coordination (73% failure rate), instruction following, and safety alignment, while empirically delineating LLMs’ scientific reasoning boundaries. Leveraging task-decomposition prompting, hardware interface integration, and a multi-agent architecture, AILA achieves autonomous AFM calibration, high-resolution feature identification, and nanomechanical property quantification. Results further reveal substantial accuracy degradation in foundational tasks (e.g., document retrieval), underscoring robustness and trustworthiness as central challenges in AI for Science.

2 citationsRead paper

Physics-Informed Deep Learning Model for Cross-Modality Super-Resolution in Fluorescence Microscopy

Jul 23, 2026

This work addresses the limitation of purely data-driven approaches in cross-modal fluorescence microscopy super-resolution, which often violate the physical laws governing optical imaging. To overcome this, the authors propose a physics-informed generative adversarial network that integrates the microscope-specific point spread function (PSF) as a prior for translating confocal microscopy images to stimulated emission depletion (STED) super-resolution images. For the first time, the PSF is explicitly embedded into the training objective of the generative model, significantly enhancing both structural fidelity and physical plausibility of the synthesized images. Experimental results demonstrate that the proposed PSF-guided model outperforms non-PSF baselines in terms of structural accuracy, local bias control, and frequency-domain consistency, yielding outputs that more closely resemble real STED images.

0 citationsRead paper
Recent publications

Latest Papers

Physics-Informed Deep Learning Model for Cross-Modality Super-Resolution in Fluorescence Microscopy

Jul 23, 2026

This work addresses the limitation of purely data-driven approaches in cross-modal fluorescence microscopy super-resolution, which often violate the physical laws governing optical imaging. To overcome this, the authors propose a physics-informed generative adversarial network that integrates the microscope-specific point spread function (PSF) as a prior for translating confocal microscopy images to stimulated emission depletion (STED) super-resolution images. For the first time, the PSF is explicitly embedded into the training objective of the generative model, significantly enhancing both structural fidelity and physical plausibility of the synthesized images. Experimental results demonstrate that the proposed PSF-guided model outperforms non-PSF baselines in terms of structural accuracy, local bias control, and frequency-domain consistency, yielding outputs that more closely resemble real STED images.

0 citationsRead paper

On the Faithfulness of Post-Hoc Concept Bottleneck Models

Jun 29, 2026

This work addresses a critical limitation in existing post-hoc concept bottleneck models, which rely solely on task accuracy and thus fail to detect semantically unfaithful concepts—such as predictive artifacts mistakenly treated as valid concepts. The study formally characterizes the mechanisms underlying such unfaithfulness, identifying two failure modes driven by covariate shift in auxiliary data and label noise from vision-language models. To overcome this, the authors propose a novel evaluation paradigm that decouples semantic faithfulness from predictive accuracy. Through theoretical analysis of error upper bounds, experiments on both synthetic and real-world benchmarks, and a new faithfulness metric, the proposed approach effectively uncovers semantic distortions entirely overlooked by conventional evaluation metrics, demonstrating its necessity and efficacy across multiple benchmarks.

0 citationsRead paper