Guancheng Wan

DAWN: Distributed LLM Multi-Agent Workflow Synthesis AAAI 2026 Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Segmentation AAAI 2026 Domain-Aware Suppression and Aggregation for Federated DG ReID AAAI 2026 FedSDR: Federated Graph Learning with Structural Noise Detection and Reconstruction CVPR 2026 Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy ACL 2026 PurMM: Attention-Guided Test-Time Backdoor Purification in Multimodal Large Language Models AAAI 2026 RAAS: LLM Agentic System Architecture Search with GRPO CVPR 2026 Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning ACL 2026 Towards Robust Text-Attributed Federated Graph Learning: Multimodal Threats and Defense AAAI 2026 S^2FGL: Spatial Spectral Federated Graph Learning ICML 2025 An Empirical Study of Federated Prompt Learning for Vision Language Model IJCAI 2025 Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning ICML 2025 Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems ICLR 2025 Does One-shot Give the Best Shot? Mitigating Model Inconsistency in One-shot Federated Learning ICML 2025 EAGLES: Towards Effective, Efficient, and Economical Federated Graph Learning via Unified Sparsification ICML 2025 EARTH: Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph ICML 2025 EMOE: Modality-Specific Enhanced Dynamic Emotion Experts CVPR 2025 Energy-based Backdoor Defense Against Federated Graph Learning ICLR 2025 Federated Disentangled Tuning with Textual Prior Decoupling and Visual Dynamic Adaptation ICML 2025 FedPHA: Federated Prompt Learning for Heterogeneous Client Adaptation ICML 2025 FedSPA: Generalizable Federated Graph Learning under Homophily Heterogeneity CVPR 2025 G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks ICML 2025 GHOST: Generalizable One-Shot Federated Graph Learning with Proxy-Based Topology Knowledge Retention ICML 2025 G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems ACL 2025 Label-Free Backdoor Attacks in Vertical Federated Learning AAAI 2025 Learn from Downstream and Be Yourself in Multimodal Large Language Models Fine-Tuning ICML 2025 LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models CVPR 2025 MasRouter: Learning to Route LLMs for Multi-Agent Systems ACL 2025 Protein Large Language Models: A Comprehensive Survey EMNLP 2025 Rethink GraphODE Generalization within Coupled Dynamical System ICML 2025 Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models ICML 2025 Federated Graph Learning under Domain Shift with Generalizable Prototypes AAAI 2024 FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference NeurIPS 2024 Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning NeurIPS 2024 S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning ICML 2024 Federated Graph Semantic and Structural Learning IJCAI 2023