I am a Principal Research Scientist specializing in Multimodal Large Language Models (LLMs). Previously, I was a Research Scientist and Tech Lead at ByteDance Seed, where I focused on multimodal LLMs and Reinforcement Learning. I received my PhD from Nanyang Technological University (NTU, Singapore) in 2022, where I worked on Deep Reinforcement Learning.

“Your time is limited, so don’t waste it living someone else’s life.” — Steve Jobs

Recent news

• 🎉 Two papers accepted by ICLR 2026. ParaS2S, VLM Model Merge.
• 🏆 Received Outstanding Team award (Spot Bonus in Q3) from Bytedance Seed.
• 🎉 Our Bytedance Seed tech report about Multimodal LLM Agent has been released.
• 🎉 Two papers accepted by NeurIPS-2025. “Robust SuperAlignment” selected as spotlight.
• 🎉 Two papers accepted by ICCV-2025; One ICCV paper was selected as highlight.
• 🏆 Received Spot Bonus award for Breakthrough In New Area from Bytedance Seed (rate=2/366).
• 🎉 One paper accepted by ICML-2025 as spotlight (acceptance rate=2.6%).
• 🚀 [Feb 2025] As the tech lead and main contributor, our speech to speech LLM trained using Reinforcement Learning has been released on Doubao 豆包.
• 🎉 Papers accepted by ICLR-2025, AAAI-2025, KDD-2025.
• 🔥 Our paper was nominated as the best paper in SIGIR-2024.
• 🏆 Received outstanding employee award from Shanda gruop (rate=4/360).
• 🔥 My research work on audio watermarking was recently featured on Linkedin
• 🎉 One paper accepted by NeurIPS-2023.
• 🔥✨ Invited talk for AI-TIME.
• 🔥 Our work about Audio QR Code has been highlighted by IJCAI-2023 officially 🔬Linked-in, Facebook, Twitter.
• 🔥 My research papers are reported by several Chinese media platforms, such as PaperWeekly, 语音之家，深科技，火山引擎.
• 🔥 My research on “adversarial robustness of deep reinforcement learning” has been featured with title “Expecting the Unexpected from AI”.
• 🏆 Received Research Highlight Award from ASTAR Singapore.

Experience

• 💼 [Feb 2026] I left Bytedance Seed to pursue agentic interaction models. Many thanks my wonderful teammates for the models we trained together.
• 💼 [Jun 2024] I returned to Bytedance Seed as a research scientist and tech lead to build up the reinforcement learning pipeline for speech to speech LLMs.
• 💼 [Aug 2023] I joined Shanda Group as an AI scientist inspired by Mr Chen Tianqiao’s ambition on AI, working on internal start-up and venture capital investment consultation on AI.
• 🎓 [Jan 2022]I finished my oral defense and received my PhD degree. Many thanks to my supervisor Prof Yew-Soon Ong and many other collaborators.
• 💼 [June 2021] I joined Bytedance AI lab (Singapore) as a research scientist
• 🎓📜 [May 2021] PhD thesis submission in NTU