Meghal Dani

I'm a Ph.D. student at IMPRS-IS, University of Tübingen in Germany, where I work on understanding vision and language models for their safe use in healthcare. I am also Guest PhD Student at Helmholtz-Munich and Technical University of Munich (TUM), Germany.

I am a part of ClinBrAIn, a clinical research in neuroscience initiative and supervised by Prof. Dr. Zeynep Akata and Dr. rer. nat. Stefanie Liebe. In first year of my Ph.D. I also worked at MIDAS lab with Prof. Dr. Med. Sergios Gatidis, who moved to Stanford in 2023.

My journey is an amalgamation of computer science and biology as I received my bachelors in Computer Science Engineering at BIT Mesra in 2016 and focussed on AI in healthcare later during her masters at IIIT Delhi, majoring in Computational Biology (2017-2019). I gained industry experience as full-time researcher (2019-2021) at Tata Research and Innovation Labs in the area of Deep Learning and AI under the supervision of Senior Scientist Dr. Lovekesh Vig and Ramya Hebbalaguppe.

Email  /  CV  /  Scholar  /  Twitter  /  Github

profile photo

Research

I'm interested in Computer Vision, Large Language Models (LLMs), Deep Learning, Generative AI, Medical Image Analysis and NeuroImaging.

teaser-image SemioLLM: Assessing Large Language Models for Semiological Analysis in Epilepsy Research
Meghal Dani, Muthu Jeyanthi Prakash, Zeynep Akata, Stefanie Liebe
International Conference on Machine Learning (ICML) Workshop, 2024
project page / PDF / Code Coming Soon / openreview
teaser-image DeViL: Decoding Vision features into Language
Meghal Dani*, Isabel Rio Torto*, Stephan Alaniz, Zeynep Akata
DAGM GCPR, 2023   (Oral), This work was also presented at ICCV-CLVL workshop, 2023
project page / PDF / code
teaser-image An efficient anchor-free universal lesion detection in CT-scans
Manu Sheoran*, Meghal Dani*, Monika Sharma, Lovekesh Vig
ISBI, 2022
PDF
teaser-image DKMA-ULD: Domain Knowledge augmented Multi-head Attention based Robust Universal Lesion Detection
Manu Sheoran*, Meghal Dani*, Monika Sharma, Lovekesh Vig
BMVC, 2022
PDF
teaser-image 3DPoseLite: A Compact 3D Pose Estimation Using Node Embeddings
Meghal Dani, Karan Narain, Ramya Hebbalaguppe
WACV, 2021
PDF
teaser-image PoseFromGraph: Compact 3-D Pose Estimation using Graphs
Meghal Dani, Additya Popli Ramya Hebbalaguppe
SIGGRAPH ASIA, 2020
PDF / Video
teaser-image Mid-air fingertip-based user interaction in mixed reality
Meghal Dani, Gaurav Garg, Ramakrishna Perla, Ramya Hebbalaguppe
ISMAR, 2018
PDF
Community service
Reviewer:
  • ECCV (2024)
  • MICCAI (2024)
  • ACCV (2024)
  • ICML Workshop on LLMs and Cognition (2024)
  • ICCV (2023)

Other:
  • Ph.D. Representative in Search Committee for Tenure-Track Professor of Machine Learning and Intelligent Systems, University of Tübingen
  • IMPRS-IS Interview Symposium Helper involved in recording and moderating candidate talks
  • Volunteer at Explainability in Machine Learning (Tübingen, 2023)

This website is adapted from template here: source code.