Tianyu Du

Safeguarding Visual Privacy in Dataset Distillation: Robust Initialization via Augmentation

When Agents “Misremember” Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems

Bridging the Gap Between Preference Alignment and Machine Unlearning

Arcueid: Multi-trigger Cloud Shaping for Unified Backdoor Attack Paradigms

MASpi: A Unified Environment for Evaluating Prompt Injection Robustness in LLM-Based Multi-Agent Systems

Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding

CollabEdit: Towards Non-destructive Collaborative Knowledge Editing

Tool-Planner: Task Planning with Clusters across Multiple Tools

Privacy as a Free Lunch: Crafting Initial Distilled Datasets through the Kaleidoscope

Data-Evolution Learning