Yunbo Long

Yunbo Long

PhD Student at University of Cambridge ((Data Understanding & Generation))

About Me

Yunbo is a PhD candidate at the University of Cambridge focusing on unifying data understanding and data generation through latent-space modeling with Diffusion-based Generative Models (like DLMs). His work develops principled frameworks that bridge representation learning and controllable generation across heterogeneous data regimes: discrete (natural language), mixed-type tabular, structured relational/graph data, and emerging multimodal combinations. A central theme is designing architectures and training objectives that faithfully capture semantics, uncertainty, structure, and cross-domain correspondences while remaining computationally and statistically efficient.

Before this, Yunbo completed a MPhil’s degree in Engineering Department at the University of Cambridge, where his research focused on a DP-based personalized clustering federated learning method. Prior to that, he earned a First-Class Honours degree in Engineering from the University of Birmingham, with his undergraduate thesis exploring the application of deep reinforcement learning algorithms for autonomous robotic dismantling tasks.

News

  • 2025.10: EvoEmo: Towards Evolved Emotional Policies for LLM Agents in Multi-Turn Negotiation is under review ⭐️⭐️⭐️

  • 2025.10: EmoDebt: Bayesian-Optimized Emotional Intelligence for Strategic Agent-to-Agent Debt Recovery is under review ⭐️⭐️⭐️

  • 2025.9: EQ-Negotiator: Emotion Policing Personas for Anti-Manipulation in Credit Collection Dialogues is under review ⭐️⭐️⭐️

  • 2025.9: ExpoTab: One-Step Mixed-Type Tabular Data Generation using Manifold Learning is under review ⭐️⭐️⭐️

  • 2025.8: TopologicalFederatedClusteringviaGravitationalPotentialFieldsunder Local Differential Privacy is under review ⭐️⭐️⭐️

  • 2025.7: LLM-TabLogic: Preserving Inter-Column Logical Relationships in Synthetic Tabular Data via Prompt-Guided Latent Diffusion is under review ⭐️⭐️⭐️

  • 2025.6: Efficient and privacy-preserved link prediction via condensed graphs published in Expert Systems with Applications 🎉🎉🎉

  • 2025.5: Random Walk Guided Hyperbolic Graph Distillation (Y Long, L Xu, S Schoepf, A Brintrup) is on arXiv 🚀🚀

  • 2025.5: Haplo-caller: A deep learning method for haplotype identification from mixed clonal samples is published in VeriXiv 🎉

  • 2025.4: PA-CFL: Privacy-Adaptive Clustered Federated Learning for Transformer-Based Sales Forecasting on Heterogeneous Retail Data is under review ⭐️

  • 2025.3: Evaluating inter-column logical relationships in synthetic tabular data generation is accepted as ICLR 2025 Tiny Paper 🎉🎉🎉

  • 2025.1: Leveraging synthetic data to tackle machine learning challenges in supply chains: challenges, methods, applications, and research opportunities is accepted in IJPR 🎉🎉

  • 2024.10: Leveraging unsupervised learning for cost-effective visual anomaly detection is accepted! 🎉

Funding

  • Conference Scholarship, Department of Engineering, Cambridge University
  • Queens College PhD Scholarship, Cambridge University

Services

Journal Reviewer(2025）

  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS) x2
  • IEEE Transactions on Knowledge and Data Engineering (TKDE) x3
  • IEEE Transactions on Information Forensics & Security (TIFS) x1
  • IEEE Transactions on Dependable and Secure Computing (TDSC) x2
  • IEEE Transactions on Mobile Computing (TMC) x2
  • IEEE Transactions on Systems, Man and Cybernetics (TSMC) x1
  • IEEE Transactions on Fuzzy System (TFS) x1
  • ACM Transactions on Knowledge Discovery from Data (TKDD) x1

Conference Reviewer(2025）

  • NeurIPS
  • AAAI
  • ICLR

Contact

  • Address: Queens’ College, Silver St, CB3 9ET
  • Email: yl892@cam.ac.uk
  • Phone: (44)7419736389