- HyperNoise and SAEs for VLMs accepted at NeurIPS 2025
- RankDPO accepted at ICCV 2025
- ReNO accepted at NeurIPS 2024
- EgoCVR accepted at ECCV 2024
- CIReVL accepted at ICLR 2024
Research Experience
Researcher at Genmo: Working on video generation (July 2025 - Present)
Intern at Snap Research: Developed better preference optimization methods for text-to-image models (April 2024 - ?)
Intern at Naver Labs Europe: Developed self-supervised learning methods for learning from noisy and imbalanced data (Specific time not provided)
Education
PhD: University of Tübingen; Advisor: Not explicitly mentioned; Time: Until June 2025; Field: Vision and Language.
Bachelor's and Master's: International Institute of Information Technology, Hyderabad; Advisor: Prof. Vineet Gandhi; Time: Before that; Field: Computer Vision.
Background
Research Interests: Problems at the intersection of Vision and Language. Particularly enjoyed working on post-training diffusion models with human feedback. Aiming to improve the controllability and alignment of these models.