Research Interests
Reinforcement Learning, Robot Learning, World Models, Curiosity & Open-endedness
Short CV
- 2025-: PhD, Model-based RL for the Real-world, University of Tübingen
- 2021-2025: M.Sc Computer Science & Research Assistant, University of Freiburg - Research in generalization in world models and reinforcement learning, cross embodiment generalization, and mobile navigation.
- 2021: Research Scientist, Agara AI - Developed hierarchical text classification system using language models.
- 2017-2021: Research Engineer & Leadership Staff, Zoho Corporation - Developed Grammar error correction system, text translation and question answering with language models. Research in interpretability of language models.
- 2015-2017: Software Engineer, Zoho Corporation - Developed iOS, native Linux, and full stack applications.
Selected Publications
- Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization: Sai Prasanna*, Karim Farid*, Raghu Rajan, and André Biedenkapp
- Perception Matters: Enhancing Embodied AI with Uncertainty-Aware Semantic Segmentation: Sai Prasanna*, Daniel Honerkamp*, Kshitij Sirohi*, Tim Welschehold, Wolfram Burgard, and Abhinav Valada
- When BERT plays the lottery, all tickets are winning: Sai Prasanna, Anna Rogers, and Anna Rumshisky
Search for Sai Prasanna Raman's papers on the Publications page