📰 Recent News
📋 Sep 2026: Accepted Area Chair invitations for ICLR 2027, AISTATS 2027, and IJCNN 2027.
✈️ Aug 2026: Visited Beijing & Hangzhou funded by the CEP project!
📝 Aug 2026: Our two Papers, FedPref: Federated Preference Learning for Structured Radiology Report Extraction and Authority-Preserving Evaluation of Medical Vision-Language Assistants, have been accepted by MICCAI 2026 2nd Emerging LLM/LMM Applications in Medical Imaging (ELAMI)!
✈️ Jun 2026: Attended DiGRA 2026 in Maynooth, Ireland! The slides for my talk on Why do we suffer for fun? can be found
here.
📝 Jun 2026: Our team has been awarded two project grants from the Swiss AI Initiative. They give us access to the CSCS Alps compute and related resources from the Swiss National AI Institute!
✈️ May 2026: Attended AAMAS 2026 in Cyprus!
📝 May 2026: Honoured to contribute to the The Science and Humanities Research Olympiad (SHRO 2026) as a research mentor!
📝 Feb 2026: Our Paper, Why Do We Suffer for Fun? Ordeal Pleasure in Souls-like Games, has been accepted by DiGRA 2026!
✈️ Jan 2026: Attended AAAI 2026 in Singapore! Honored to participate in invite-only industry dialogues and talent events hosted by Huawei, Ant Group, and China Telecom (TeleAI) alongside the conference.
📝 Jan 2026: Our Paper, Unveiling and Mitigating Untargeted Poisoning Attacks on Federated Knowledge Graph Embedding, has been accepted by WWW (The ACM Web Conference) 2026!
📝 Dec 2025: Our Paper, Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol, has been accepted by AAMAS 2026 as an Extended Abstract!
📝 Nov 2025: Our Paper, Provably Reliable Tool-Using AI Agents: Formal Guarantees on Error Accumulation in the Model Context Protocol, has been accepted by AAAI TrustAgent workshop as a Research Long Paper!
📝 Oct 2025: Our Paper, Revisiting the Byzantine Resilience of Federated Reinforcement Learning: A Distillation Perspective, has been accepted by IEEE TrustCom 2025 as a Research Full Paper!
✈️ Jul 2025: Attended IJCNN 2025 in Rome! The slides for my talk on our position on Sequential Privacy can be found
here.
✈️ Jul 2025: Visited beautiful Malta for DiGRA 2025! The slides for my 30-mins talk on analyzing Black Myth: Wukong as a cultural mediator can be found
here. If you are interested in cultural representation study through interactive media such as video games, feel free to drop me a message!
🎉 Jun 2025: I relocated to Zurich, Switzerland for conducting postdoc research at ETH Zurich!
✈️ May 2025: Wrapped up an incredible week at AAMAS 2025 in Detroit! Honored that our paper FedRLHF: A Convergence-Guaranteed Federated Framework for Privacy-Preserving and Personalized RLHF was selected as one of the premier papers at the conference, and received an invitation for fast-track submission to JAAMAS! Slides for FedRLHF can be found
here.
📝 Apr 2025: Our Paper, Diversifying Robot Locomotion Behaviors with Extrinsic Behavioral Curiosity, has been accepted by ICML 2025!
📝 Mar 2025: Our Paper, Generative Quality Diversity Imitation Learning for Robot Skill Acquisition, has been accepted by ICLR 2025 Workshop on Generative Models for Robot Learning!
🎉 Mar 2025: I joined A*STAR's Centre for Frontier AI Research (CFAR) as a Scientist!
🎓 Mar 2025: My PhD was conferred!
📝 Dec 2024: Checkout our AAMAS-25 paper
FedRLHF (Federated RLHF), a framework that balances the global performance and personalization in LLMs fine-tuning, while preserving user privacy!