Ph.D. Candidate in Computer Science, Virginia Tech
I am a Ph.D. candidate at Virginia Tech, advised by Prof. Pinar Yanardag. I study the internal representations of generative models, how they encode meaning, structure, and style, to make image and video generation easier to understand and control.
My recent work spans controllable generation, diffusion model distillation, and analysis of how generative models represent concepts internally. I want to understand why these systems behave the way they do, not just improve their outputs.
Highlights
- Publications at CVPR 2026, AAAI 2026, ICCV 2025 (Highlight), ICML 2025 (Oral), and CVPR 2024.
- Research internships at Waymo (2026), Amazon (2025), and Adobe (2024).
- Industry deployment experience with diffusion-based services serving over 5 million daily requests.
- Co-organizer of the ICCV 2025 and CVPR 2026 Personalization in Generative AI (P13N) workshops.
Experience
- Waymo - Research Intern (May 2026 - Present)
- Virginia Tech - Research Assistant (Aug 2023 - Present)
- Amazon - Applied Scientist Intern (May 2025 - Aug 2025)
- Adobe - Research Intern, Video Generative AI (May 2024 - Aug 2024)
- Lyrebird Studio - Machine Learning Engineer (Nov 2022 - Aug 2023)
- Vispera - Computer Vision Research Engineer (Oct 2019 - Nov 2022)
Recent News
Jun 2026
Launched an interview prep website for organizing Research Scientist and Applied Scientist interview preparation.
May 2026
Selected as an Outstanding Reviewer at CVPR 2026.
May 2026
Released the Aligning Latent Geometry for Spherical Flow Matching in Image Generation preprint on arXiv.
May 2026
Started a research internship at Waymo.
Selected Research
Aligning Latent Geometry for Spherical Flow Matching in Image Generation
arXiv preprint · 2026
MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models
AAAI 2026 (Main Technical Track) · 2026
CLoRA: A Contrastive Approach to Compose Multiple LoRA Models
ICCV 2025 (Highlight) · 2025
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
ICML 2025 (Oral) · 2025