Naresh Kumar Devulapally#
I am a PhD candidate (chair’s fellow) at UB’s CVML Lab in the Computer Science Department at University at Buffalo. My research is advised by Dr. Vishnu Lokhande.
My Research
My research focuses on enhancing reliability, robustness and alignment in Generative AI models. My goal is to build Responsible, Trustworthy AI models.
Updates#
-
👨🏻🏫 Invited Guest Lectures on Diffusion Models in CSE 555: Pattern Recognition course at UB.
- Instructor: Prof. Ifeoma Nwogu.
-
🎉 Token-to-Token Similarity Reduction in dLLMs for Edit-Friendly Hard Prompt Inversion is accepted to CVPR 2026!
-
👨🏻🏫 Invited Guest Lectures on CNNs and Diffusion Models in CSE 573: Computer Vision course at UB.
- Instructor: Prof. Junsong Yuan.
-
🎉 Recipient of CSE Graduate Teaching Award for my Summer CVIP course at UB.
-
🎉 Passed Oral Qualifying Examination at UB!
-
👨🏻🏫 Taught CSE 4/573: Computer Vision and Image Processing at UB, Summer 2025.
-
🎉 Your Text Encoder can be an Object-Level Watermarking Controller is accepted at ICCV 2025!
- (with: Adobe Research, Prof. Siwei Lyu).
-
🎉 Latent Diffusion Unlearning: Protecting Against Unauthorized Personalization Through Trajectory Shifted Perturbations is accepted at ACM MM 2025!
- (with: Adobe Research, CVG at UMBC).
My collaborators:
Before joining UB as a PhD Candidate, I completed my Masters (Thesis) in CS at UB. My thesis, Towards Generalizable and Robust Multimodal ML models for Video Emotion Recognition is co-supervised of Dr. Junsong Yuan and Dr. Sreyasee Das Bhattacharjee. During my masters at UB, my research was published at venues such as ACM Multimedia 2023, BigMM 2024, and ICME 2024. My research project PRIMAL (Privacy Preserving Multimodal Emotion Recognition in conversation) received a honorable mention at Agrusa L. Student Innovation Competition 2022.
Before joining UB as a Master’s student, I worked as a Data Scientist-III (for ~2.5 years). During this time, I led global-scale AI solutions for clients including Unilever, BOSCH, DOLE etc. I led the ideation and development of Trade Promotion Optimization at Carbynetech (India) which continues to generate ~$50k every year.
My Teaching#
I Love Teaching!!!
My PhD is immensely motivated by my extreme passion for teaching. I aim to impart the knowledge that I received over to the next generation of researchers.
Check out my RateMyProfessor Ratings.
I have been fortunate to teach:
Computer Vision and Generative AI course at UB. (Summer 2025).
Contact Details#
📍 301C Davis Hall, Buffalo NY, 14260
✉️ Email: devulapa@buffalo.edu