Binjie Zhang

I am a Ph.D. candidate in Computer Science at the National University of Singapore (NUS), advised by Assistant Prof. Mike Zheng Shou in Show Lab.

My research interests are LLM agents — harness design, memory, tool use, and self-evolution — together with vision–language and video understanding, world / predictive models, and lifelong and compatible representation learning. Broadly, I want to build systems where multi-modal agents can reuse what they already know, anticipate what comes next, and keep improving after deployment.

From January to June 2026, I was an AI Research Intern at TikTok (ByteDance) in Singapore, where I owned production LLM-agent systems for large-scale e-commerce (intellectual-property) governance. The work spanned five threads: (i) business landing of agents in real e-commerce moderation pipelines; (ii) an agent harness / framework for rapidly composing skill-based agents; (iii) training-free memory optimization; (iv) long-horizon context management; and (v) self-evolution — agent-native loops that keep models improving with minimal human intervention. I drove each system from research prototype to production deployment.

Before NUS I received my M.Eng. in Computer Science and Technology from Tsinghua University, supervised by Prof. Chun Yuan, and my B.Eng. in Information Engineering from East China University of Science and Technology (ECUST), where I ranked 1 / 92.

Before that, I spent several years at Tencent ARC Lab (Shenzhen) as an AI research intern, where I led a line of first-author work on backward-compatible representation learning and hot-refresh model upgrades for large-scale image and video retrieval (ICLR’22, IJCAI’22 long oral, AAAI’23, arXiv’23), as well as on cross-modality video understanding.