Scholar
Aditya Chinchure
Google Scholar ID: WZhACa8AAAAJ
University of British Columbia
Citations & Impact
Citations
135
H-index
3
i10-index
3
Publications
10
Co-authors
9
list available
Publications
Resume (English only)
Academic Achievements
- Publications: SPIKE-RL: Video-LLMs meet Bayesian Surprise (preprint); World Models must live in Parallel Worlds (NeurIPS 2025 Workshop); Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Models (EMNLP 2025); Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events (CVPR 2025); From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models (EMNLP 2024); TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models (ECCV 2024). Awards: Outstanding reviewer at CVPR 2025.
Research Experience
- Incoming research intern at Ideogram; Previously a visiting scholar at Toyota Technological Institute at Chicago, working with Dr. Matthew Turk; Intern at Borealis AI with Dr. Fred Tung.
Education
- PhD, University of British Columbia (UBC), Computer Vision and NLP Labs; Advisors: Dr. Leonid Sigal and Dr. Vered Shwartz; Supported by UBC Four Year Fellowship (4YF).
Background
- Research interests: Applying methods from human reasoning and cognition to develop vision-language models and evaluation tools. Focus on image and video understanding & reasoning, as well as bias and fairness in Generative AI.
Miscellany
- Hobby: Photography, with over 200 million views on Unsplash.
