3 papers
cs.CR2026
TokenScanner: Detecting Backdoors and Discovering Triggers in Text-to-Image LoRAs via Full Vocabulary Scanning
Boliang Liu, Jing Zhang
LoRAs are widely studied for adapting base text-to-image diffusion models. However, a backdoored LoRA can hide a backdoor: it behaves normally in most cases, but produces attacker-…
cs.LG2026
Foundation Models for Generalizable Semantic and Goal-Oriented Communication
Boliang Liu, Wint Yi Poe, Riccardo Trivisonno +1
Semantic and goal-oriented communication is increasingly studied for 6G, but generalization beyond seen data remains a key weakness under tight rate budgets. Many existing systems…
cs.RO2026
ComVLA: Communication-Aware Split Inference for VLA Models in 6G-Connected Robotics
Boliang Liu, Wint Yi Poe, Jingyun Di +2
Connected robotics is an emerging 6G application where mobile robots follow natural-language instructions to manipulate physical objects. The Vision-Language-Action (VLA) models th…