I'm a Ph.D. Candidate in Purdue ECE, expected to complete my Ph.D. in Dec 2026.
I build adaptive ML systems for efficient vision and multimodal models, with a focus on making VLM/LLM inference faster, more resource-aware, and deployable across embedded GPUs, server GPUs, and AI accelerators.
Actively seeking full-time opportunities as a Machine Learning Engineer or Research Scientist in ML systems, efficient inference, and AI infrastructure.
- Adaptive ML Systems
- Content- and Resource-Aware Compute Adaptation and Scheduling
- Efficient Vision and Multimodal Models
- SmartVL: Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs, accepted to ECCV 2026.
- Agile3D: Adaptive contention- and content-aware 3D object detection for embedded GPUs, accepted to ACM MobiSys 2025.
- Industry experience: Foundation Model Optimization at EmbodyX; AI Accelerator Software Toolchains and GenAI for Chip Design work at Sunlune.
🌱 Fun fact: I would like to spend one year living in Antarctica if there's any opportunity!