👋 Hello!

🔬 About Me

I am a Machine Learning and Computer Vision Researcher, developing intelligent systems that can understand and operate in complex, real-world human environments. My work focuses on bridging the gap between foundational research and practical, industry-relevant applications. Currently pursuing a PhD at TU Berlin and working as a Research Associate at Fraunhofer IPK, Berlin.

🎓 Google Scholar • 💼 LinkedIn • 𝕏 / Twitter

• 🏭 Industrial Automation
• 🎥 Egocentric Vision
• 📉 Data Efficiency
• 🧠 Continual Learning
• 🔀 Multimodality
• 🤖 Robotics

For inquiries and questions, please reach out via the 📬 Contact page.

🎤 Talks, Presentations & Activities

• Invited Talk at TU Berlin
  Research on Egocentric and Exocentric Vision for Industrial Applications
  AI in Manufacturing, IWF, Berlin in November 2025


• 🏆 Winner- Food Waste Detection Hackathon
  Participated in and won a hackathon on food waste detection using Computer Vision & AI, sponsored by Voxel51 at Hasso Plattner Institute in August 2025


• Talk at Sorbonne University
  Developing Industrial Egocentric Assistants: Integrating Continual Learning, Data Management, and Multimodal Understanding
  Center for Artificial Intelligence, Paris in April 2025


• Podcast Interview- Heise Online (KI-Update)
  Topic: Current research in Industrial AI and Egocentric Vision
  KI-Update Deep-Dive: “AI glasses in industry” in March 2025
  🔗 Heise Online


• Berlin Science Week- Research Talk & Demo
  Public presentation of ongoing research in November 2024


• 🏆 Winner- AI Grid Hackathon
  Developed novel solutions for sustainable AI in industry during an international hackathon challenge in September 2024


• 🛠 Workshop Participation
  Attended and contributed to AI Grid Summer School workshops on computer vision, time series forecasting, and prompt engineering in September 2024


• 🏆 Science Slam Hamburg- Winner
  Top-rated talk (≈200 audience) on Artificial Intelligence in July 2024


• Control Trade Fair- Technology Demonstration
  Represented the Machine Vision team with live demos (anomaly detection, object detection, egocentric vision).
  Stuttgart in April 2024


• Fraunhofer Vision Session- Invited Talk
  Industrial continual learning with a focus on energy consumption and computational footprint in November 2023


• VisionRead Talks- Internal Knowledge-Sharing
  Six talks covering recent research in Computer Vision & AI in 2023–2024

📄 First-Author Publications

• Chavan, V., Imgrund, Y., Dao, T., Bai, S., Wang, B., Lu, Z., Heimann, O., & Krüger, J. (2025).
  IndEgo: A Dataset of Industrial Scenarios and Collaborative Work for Egocentric Assistants.
  In: Advances in Neural Information Processing Systems (NeurIPS 2025).
  🔗 Conference Page


• Chavan, V., Cenaj, A., Shen, S., Bar, A., Binwani, S., Del Becaro, T., Funk, M., Greschner, L., Hung, R., Klein, S., Kleiner, R., Krause, S., Olbrych, S., Parmar, V., Sarafraz, J., Soroko, D., Withanage Don, D., Zhou, C., Vu, H.T.D., Semnani, P., Weinhardt, D., André, E., Krüger, J., & Fresquet, X. (2025).
  Feeling Machines: Ethics, Culture, and the Rise of Emotional AI.
  arXiv preprint.
  🔗 arXiv


• Chavan, V., Heimann, O., & Krüger, J. (2024).
  On the Application of Egocentric Computer Vision to Industrial Inspection.
  In: ECCV 2024 Workshops.
  🔗 Springer Link


• Chavan, V., Heimann, O., & Krüger, J. (2024).
  A System 1 and System 2 Perspective on Continual Learning for Practical Implementation.
  In: ECCV 2024 Workshops.
  🔗 Springer Link


• Chavan, V., Koch, P., Schlüter, M., Briese, C., & Krüger, J. (2024).
  Active Data Collection and Management for Real-World Continual Learning via Pretrained Oracle.
  In: CVPR 2024 Workshops.
  🔗 CVPR OpenAccess


• Chavan, V., Koch, P., Schlüter, M., & Briese, C. (2023).
  Towards Realistic Evaluation of Industrial Continual Learning Scenarios with an Emphasis on Energy Consumption and Computational Footprint.
  In: ICCV 2023.
  🔗 IEEE Xplore

💿 Datasets

• IndEgo- Coming soon
  A large-scale dataset of industrial scenarios and collaborative work for egocentric assistants.


• InVar-100
  A dataset of industrial objects in varied contexts. 🔗 Hugging Face