I am a research scientist and tech lead at ByteDance Seed, specializing in training multimodal large language models (LLMs) and LLM agents using reinforcement learning (RL). I earned my PhD from Nanyang Technological University (NTU, Singapore), where my research centered on โ€œAdversarial Robustness of Deep Reinforcement Learningโ€.

Recent news

  • ๐Ÿ† Received Spot Bonus award from Bytedance (rate=2/366).
  • ๐ŸŽ‰ One paper accepted by ICML-2025 as spotlight (acceptance rate=2.6%).
  • ๐ŸŽ‰ One paper accepted by ICLR-2025.
  • ๐Ÿš€ [Feb 2025] As the tech lead and main contributor, our speech to speech LLM trained using Reinforcement Learning has been released on Doubao ่ฑ†ๅŒ….
  • ๐ŸŽ‰ One paper accepted by AAAI-2025.
  • ๐ŸŽ‰ One paper accepted by KDD-2025.
  • ๐Ÿ”ฅ Our paper was nominated as the best paper in SIGIR-2024.
  • ๐ŸŽ‰ Two papers accepted by SIGIR-2024.
  • ๐Ÿ† Received outstanding employee award from Shanda gruop (rate=4/360).
  • ๐Ÿ”ฅ My research work on audio watermarking was recently featured on Linkedin
  • ๐ŸŽ‰ One paper accepted by NeurIPS-2023.
  • ๐Ÿ”ฅโœจ [Aug 2023] I was invited by AI-TIME to give a talk.
  • ๐Ÿ”ฅ Our work on ChatGPT driven Voice base Conversational Recommender Systems has been posted by several Chinese media platforms, such as ่ฏญ้Ÿณไน‹ๅฎถ, ็ซๅฑฑ่ฏญ้Ÿณ
  • ๐Ÿ”ฅ Our work about Audio QR Code has been highlighted by IJCAI-2023 officially ๐Ÿ”ฌLinked-in, Facebook, Twitter.
  • ๐ŸŽ‰ One paper accepted by InterSpeech-2023.
  • ๐ŸŽ‰ One paper accepted by IJCAI-2023.
  • ๐ŸŽ‰ One paper accepted by SIGIR-2023.
  • ๐ŸŽ‰ One paper accepted by IEEE TPAMI.
  • ๐ŸŽ‰ One paper accepted by CIKM-2022.
  • ๐Ÿ”ฅ My research papers are reported by several Chinese media platforms, such as PaperWeekly, ่ฏญ้Ÿณไน‹ๅฎถ๏ผŒๆทฑ็ง‘ๆŠ€๏ผŒ็ซๅฑฑๅผ•ๆ“Ž.
  • ๐ŸŽ‰ One paper accepted by IEEE TPAMI.
  • ๐ŸŽ‰ Two paper accepted by SIGKDD-2022.
  • ๐ŸŽ‰ One paper accepted by IJCAI-2022.
  • ๐ŸŽ‰ One paper accepted by SIGIR-2022.
  • ๐ŸŽ‰ One paper accepted by AAMAS-2022.
  • ๐Ÿ”ฅ My research on โ€œadversarial robustness of deep reinforcement learningโ€ has been featured with title โ€œExpecting the Unexpected from AIโ€.
  • ๐Ÿ† Received Research Highlight Award from ASTAR Singapore.

Experience

  • ๐Ÿ’ผ [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.
  • ๐Ÿ’ผ [Aug 2023] I joined Shanda Group as an AI scientist inspired by Mr Chen Tianqiaoโ€™s ambition on AI, working on internal start-up and venture capital investment consultation on AI.
  • ๐ŸŽ“ [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.
  • ๐Ÿ’ผ [June 2021] I joined Bytedance AI lab (Singapore) as a research scientist
  • ๐ŸŽ“๐Ÿ“œ [May 2021] PhD thesis submission in NTU