Koustava Goswami

Research Scientist


I am a Research Scientist at Adobe Research India. I am broadly interested in representation learning and natural language processing. More specifically, I am interested in developing deep algorithms for low-resource settings and applications. During my PhD, I have focused on building different novel unsupervised deep models using representation learning, which can be applied to diverse low-resource languages and applications across language families. One of my works is to enhance the performance of the multilingual sentence embedding models for low-resource domains in zero-shot settings by injecting better word representations. My significant contributions during PhD include the invention of different unsupervised loss functions, including the Maximum Likelihood Clustering (MLC) loss function and the designing of a new machine learning framework called the Anchor-Learner framework. I have also worked on instructional learning using prompt engineering for few-shot model training. During PhD, I have also had internship stints at Bosch Research Germany and Huawei Research Centre Ireland. My published research papers appeared in various NLP conferences including EMNLP, COLING, LREC, IEEE, Frontier Journal, NAACL etc.

Previously, I was a PhD candidate in the Insight Centre for Data Analytics lab at the University of Galway . During my PhD, I was a research intern at Bosch Research Germany and Huawei Research Centre Ireland.

My publications can be found here

For more details please visit my Linkedin page.


CoPL: Contextual Prompt Learning for Vision-Language Understanding

Goswami, K., Karanam, S., Udhayanan, P., J, J., Srinivasan, B. (Feb. 22, 2024)

AAAI 2024

Iterative Multi-Granular Image Editing Using Diffusion Models

J, J., Udhayanan, P., Shukla, T., Agarwal, A., Karanam, S., Goswami, K., Srinivasan, B. (Jan. 4, 2024)

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis

Agarwal, A., Karanam, S., J, J., Saxena, A., Goswami, K., Srinivasan, B. (Oct. 2, 2023)

International Conference on Computer Vision (ICCV)