Ziqian Zeng

SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought

GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners

L3A: Label-Augmented Analytic Adaptation for Multi-Label Class Incremental Learning

Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning

PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration

SpatialEdit: Unlocking the Spatial Capability in Multimodal Large Language Model Driven Image Editing