Several papers under review or published, including 'EvoEmo: Towards Evolved Emotional Policies for LLM Agents in Multi-Turn Negotiation', 'EQ-Negotiator: Emotion Policing Personas for Anti-Manipulation in Credit Collection Dialogues', 'ExpoTab: One-Step Mixed-Type Tabular Data Generation using Manifold Learning'. Additionally, published 'Efficient and privacy-preserved link prediction via condensed graphs' in Expert Systems with Applications and 'Haplo-caller: A deep learning method for haplotype identification from mixed clonal samples' in VeriXiv.
Research Experience
Currently a PhD student at the University of Cambridge working on data understanding and generation. Previous research experience includes developing a DP-based personalized clustering federated learning method while pursuing his MPhil at the University of Cambridge.
Education
PhD candidate at the University of Cambridge, Department of Engineering, focusing on data understanding and generation; MPhil in Engineering from the University of Cambridge, where his research focused on a DP-based personalized clustering federated learning method; First-Class Honours degree in Engineering from the University of Birmingham, with an undergraduate thesis exploring the application of deep reinforcement learning algorithms for autonomous robotic dismantling tasks.
Background
Research interests include unifying data understanding and data generation through latent-space modeling with Diffusion-based Generative Models; focusing on building principled frameworks that bridge representation learning and controllable generation across heterogeneous data regimes such as natural language, mixed-type tabular, structured relational/graph data, and emerging multimodal combinations.
Miscellany
Recipient of Conference Scholarship from the Department of Engineering, Cambridge University, and Queens College PhD Scholarship, Cambridge University. Served as a reviewer for multiple IEEE journals and conferences.