Search

Peiran Dong

Causally Motivated Sycophancy Mitigation for Large Language Models
Durable Quantization Conditioned Misalignment Attack on Large Language Models
Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing
Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring
Poisoning Attack on Federated Knowledge Graph Embedding
Towards Test-Time Refusals via Concept Negation
Investigating Trojan Attacks on Pre-trained Language Model-powered Database Middleware
Distributed and Dynamic Service Placement in Pervasive Edge Computing Networks

Published with Wowchemy — the free, open source website builder that empowers creators.