Shangjian Yin
Hi! My name is Shangjian Yin. I'm a first-year CS PhD student at the University of California, Riverside, advised by Zhouxing Shi. Previously, I was a Research Intern at Microsoft AI, and I am grateful to be supported by the UC Riverside CSE Departmental Fellowship.
Currently, I am interested in (1) building unified post-training frameworks that improve both open-ended, non-verifiable abilities and verifiable reasoning skills, (2) making post-training and inference more transparent and efficient, and (3) building small but capable multimodal agent systems for local use.
Google Scholar / GitHub / CV / Email
News
- [09/2025] I joined the UCR CSE Department as a CS PhD student.
Selected Research
Dorado: Efficient Reasoning Post-Training with Hybrid Data Supervision
PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch
From Individual to Common: An Early Exploration of Consensus in Non-verifiable Data for Preference Optimization
Align Large Language Model with Human Preference via Extremely Self-Synthetic Data
ECLM: Entity-Level Large Language Model for Spoken Language Understanding with Chain of Intent
MIDLM: Multi-Intent Detection with Bidirectional Large Language Models
Uni-MIS: United Multiple Intent Spoken Language Understanding via Multi-View Intent-Slot Interaction
Latest update: 03/2026.