| Oct 08, 2026 | Currently working with TikTok Search on Agentic Search and Tako, with contributions to scenario-aware policies, evidence-driven iteration, and ongoing data / training / evaluation design. |
| Oct 08, 2026 | Current submissions: SGRC, StateTrackBench, and PathComp are under review at ICLR 2027; POU-OPD is under review at AAAI. |
| Jun 20, 2026 | ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents accepted to ECCV 2026. |
| Mar 07, 2026 | Submitted ReGRPO (reflection-augmented RL for tool-using agents) to ECCV 2026 as first author. |
| Jan 30, 2026 | Exploring continual vision–language–action adaptation and egocentric future prediction. |
| Jan 06, 2026 | Started as an AI Research Intern at TikTok Shop (ByteDance) in Singapore, working on reusable agent harnesses, model iteration, and evidence-driven risk discovery. |
| Feb 01, 2023 | Darwinian Model Upgrades accepted to AAAI 2023. |
| Jan 10, 2023 | Started as a Ph.D. student at Show Lab, NUS, advised by Prof. Mike Zheng Shou. |
| May 01, 2022 | Towards Universal Backward-Compatible Representation Learning accepted to IJCAI 2022 (long oral). |
| Jan 20, 2022 | Hot-Refresh Model Upgrades accepted to ICLR 2022; received the Tencent Technology Breakthrough Award and SZCCF Science and Technology Award. |