Hello, this is

Zhangchen Xu (徐张晨).

#Bio

Zhangchen is a third-year PhD student in the Network Security Lab at the University of Washington, advised by Prof. Radha Poovendran. His research focuses on developing stronger and safer large language models (LLMs), with particular emphasis on data generation, post-training, and inference-time algorithms. His work has been widely adopted across academia and industry, contributing to the training of state-of-the-art models including Kimi-K2, DeepSeek-VL, Skywork-Reward, SmolLM, and LLaVA-OneVision. He received the Best Paper Award at DataWorld @ ICML 2025. Prior to joining UW, he completed his bachelor’s degree from the University of Electronic Science and Technology of China (UESTC) and the University of Glasgow (UofG), advised by Prof. Lei Zhang, where he primarily focused on distributed algorithms and blockchain systems.

Email -> zxu9 [a-t] uw [d-o-t] edu. Feel free to reach out if you would like to discuss Synthetic Data, Safety, and Post-training of LLMs, SLMs and VLMs.

#Research Interests

I work on Generative AI, with a current focus on the synthetic data generation, post-training, and safety of large language models (LLMs). My current research directions include:

#Synthetic Data Generation

I conduct data-centric research focused on enhancing LLMs with synthetic data.

• 🐦 Magpie [ICLR’25] is a family of SOTA synthetic datasets for LLM alignment -> Huggingface SmolLM, LLaMA-MoE, LLaVA-OneVision, Alibaba VideoLLaMA, DeepSeek-VL, and Skywork-Reward.
• 🐱 KodCode [ACL’25] is the largest fully-synthetic open-source dataset providing verifiable solutions and tests for LLM coding -> Kimi K2.
• 🦁 VisualSphinx is a synthetic open-source dataset for visual logic reasoning.

#LLM Post-Training

1. Model distillation from powerful LLMs to smaller models. My analysis papers in this topic include:

• Larger Models’ Paradox [NAACL’25] examines the choices of response generators for LLM alignment.
• Small Model Learnability Gap [ACL’25] investigates how to let small models (≤3B parameters) benefit from long chain-of-thought (CoT) reasoning via distillation.

2. Reinforcement Learning for enhanced reasoning ability. My papers in this topic include:

• TinyV investigates the impact of false negatives in reinforcement learning with Verifiable Reward (RLVR).
• Temporal Sampling examines the phenomenon of Temporal Forgetting during LLM post-training.

#LLM Safety

I investigate emerging threats in LLMs (e.g., Artprompt [ACL’24], ChatBug [AAAI’25], SafeChain [ACL’25]), and explore inference-time defenses (e.g., SafeDecoding [ACL’24], CleanGen [EMNLP’24], Shield [AsiaCCS’24]).

#Distributed Algorithms

I have also been working on distributed algorithms during my undergrad & early PhD.

Federated Learning. Work includes ACE [Usenix’24] (contribution evaluation attack) and Brave [AsiaCCS’24].

Distributed Consensus. Work includes Voting Validity [IPDPS’23], Wireless Distributed Consensus, and Distributed Consensus Network.

#Selected Work (see here for full publication list)