Hritik Bansal
Graduate student @ UCLA
bias
large language models
in-context learning
text to image generative models
ethical interventions
task-specific pruning
induction heads
2
presentations
2
number of views
SHORT BIO
My research is centered around Generalizable Multimodal Machine Learning for language, vision, and climate. Specifically, I am working on multimodal models for learning general-purpose representations, and generative AI. I also work on large language models in NLP.
Presentations
Rethinking the Role of Scale for In-Context Learning: An Interpretability-based Case Study at 66 Billion Scale
Hritik Bansal and 5 other authors
How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?
Hritik Bansal and 3 other authors