Rishika Bhagwatkar

I am a research master’s student at Mila and UdeM, Montreal, under the supervision ofProf. Irina Rish. My main research interests are robustness in multimodal models and scaling. Currently, I am interning at ServiceNow Research with Dr. Krishnamurthy Dvijotham on robustness in agentic systems. I am also collaborating with Dr. Francesco Croce and Prof. Nicolas Flammarion at the Theory of ML lab, EPFL, on the robustness of discrete representations in vision-language models. Prior to this, I was interning at EPFL’s NLP lab (Summer@EPFL) with Prof. Antoine Bosselut and Dr. Syrielle Montariol. Before my master’s, I was a research intern at ALMAnaCH, Inria, Paris, under the supervision of Dr. Djamé Seddah. My work was focused on studying the interactions of various modalities in real-time game sessions.   During my bachelor’s, I worked on the conjunction of self-supervised and continual learning with Prof. Christopher Kanan at the Rochester Institute of Technology, New York. As a DAAD WISE Scholar, I worked on appraisal-based emotion recognition from social media data under Dr. Roman Klinger and Dr. Carina Silberer at the University of Stuttgart. I completed my bachelor’s thesis on contrastive learning and domain adaptation from the Department of Electronics and Communication Engineering at the Visvesvaraya National Institute of Technology, India. There, I also mentored projects on understanding and improving language (and multimodal) representations at IvLabs and served as the vice-chairperson of the IEEE Student Branch. Besides research, I like to spend my time quilling, reading, and visiting new places.