I am a master's student in Computer Science (AI) at the University of Southern California, graduating in May 2027.
I build and evaluate LLMs and agents. My interests include reliable agent systems, model alignment, diffusion language models, and physical reasoning.
Previously, I worked on machine learning at TikTok, General Motors, and Shanghai AI Laboratory, with research experience at Princeton and UC Berkeley.
Seeking 2027 opportunities in software engineering (AI/ML) and machine learning engineering.
I am interested in how models learn, reason, and act reliably — from better training signals to agents that understand the world around them.
NeurIPS, 2026 · Poster
Predicts physical-state scene graphs from an image and a goal, combining latent graph reasoning with counterfactual supervision to support physical reasoning.
ICML, 2026
Uses geometry-derived preference signals to improve the 3D consistency of video diffusion models without human preference annotations.
Preprint, 2026
Studies hybrid attention as a way to adapt causal language models to bidirectional denoising, with controlled comparisons of generation quality and training efficiency.
Preprint, 2026
DMAPO selects 1,871 training examples from 54,236 candidates using multi-evaluator agreement and critique, examining data quality in preference optimization.
Preprint, 2026
Composes robot motion, scene priors, and object priors to synthesize demonstrations in new environments and support data-efficient robot learning.
CVPR OpenSUN3D Workshop, 2026
A data-centric map of 3D representations, datasets, learning paradigms, and applications spanning reconstruction, generation, and world modeling.
Post-training, multimodal moderation, and agent tooling for case replay and hard-example collection.
Causal evaluation and credit assignment for preventive actions in LLM agents.
Hybrid attention and confidence-aware decoding for pretrained diffusion language models.
Data-centric alignment through multi-evaluator agreement and preference optimization.
Agent orchestration, retrieval, and efficient vision-language model serving.
M.S. Computer Science · AI Track · 2025–2027
B.S. Computer Science (Honors) · 2021–2025