Skip to content
View TimStrohmeyer's full-sized avatar

Highlights

  • Pro

Organizations

@docling-project

Block or report TimStrohmeyer

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
TimStrohmeyer/README.md

Hi, I'm Tim 👋

Ph.D. student at ETH Zürich · Pre-Doctoral Researcher at IBM Research – Zurich

I work on multimodal machine learning for document understanding — My research focuses on multimodal machine learning for document understanding. I work within the Docling Team, focusing on Vision-Language Models for document parsing and chemical structure extraction.

At ETH I am part of the Computer Vision Lab led by Prof. Dr. Ender Konukoglu. At IBM Research I work with Dr. Peter W. J. Staar in the AI for Knowledge group, as part of the team behind Docling. I hold an M.Sc. in Robotics, Cognition, Intelligence from TU Munich.


🔬 Research interests

Computer Vision · Multimodal Machine Learning · Vision-Language Models · Document AI · OCR · Optical Chemical Structure Recognition · AI for Chemistry

📄 Selected publications

Year Work Venue
2026 MarkushGrapher-2: End-to-end Multimodal Recognition of Chemical Structuresfirst author CVPR 2026
2026 Identify, Locate, Link: End-to-End Key-Value Extraction from Document Images ICDAR 2026
2025 Advanced Layout Analysis Models for Docling arXiv:2509.11720

Full list on Google Scholar.

🧰 Tools I work with

Python PyTorch Hugging Face Docker Linux Git

🎵 Beyond research

I also make music WITHOUT AI :) My tracks are on Spotify:

Spotify

📫 Get in touch

Website IBM Research Google Scholar LinkedIn

📧 tstrohmeyer@ethz.ch (ETH) · Tim.Strohmeyer1@ibm.com (IBM) · tim.strohmeyer@t-online.de (personal)

Always happy to talk about document AI, chemistry-aware models, or collaborations.

Popular repositories Loading

  1. 6D-Pose-Estimation-for-Unseen-Categories 6D-Pose-Estimation-for-Unseen-Categories Public

    Forked from m13ammed/6D-Pose-Estimation-for-Unseen-Categories

    Explore 6D pose estimation's frontier using functional mapping. Extend pose estimation to unseen object categories through globally-informed correspondences, achieved by learned functional mapping.

    Python

  2. Agentic_RAG Agentic_RAG Public

    This is a test architecture for an agentic RAG pipeline. This architecture is able to answer wiki questions as well as questions requiring sql prompting (template based text-to-sql)

    Jupyter Notebook

  3. Leitlinien_GPT Leitlinien_GPT Public

    RAG system build on top of AWMF medical guidelines

    Jupyter Notebook

  4. docling-metrics docling-metrics Public

    Forked from docling-project/docling-metrics

    Core package for type and interface definitions of docling metric implementations

    C++

  5. TimStrohmeyer TimStrohmeyer Public