← authors · overview

• CoCurve: Cross-Module Co-Pruning Curvature for Training-Free Structured LLM Pruning
  2026
• VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems
  2026
• Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle
  2026
• AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs
  2026
• Q-CLIP: Unleashing the Power of Vision-Language Models for Video Quality Assessment through Unified Cross-Modal Adaptation
  2025
• Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models
  2025
• Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models
  2025
• Spattack: Subgroup Poisoning Attacks on Federated Recommender Systems
  2025
• Spattack: Subgroup Poisoning Attacks on Federated Recommender Systems
  2025
• SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devices
  2025
• AutoHete: An Automatic and Efficient Heterogeneous Training System for LLMs
  2025
• Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter
  2025
• Federated Learning in the Sky: Aerial-Ground Air Quality Sensing Framework with UAV Swarms
  2020