5 papers
Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents
Yaopei Zeng, Congchao Wang, JianHang Chen +3
LLM agents operate in stateful environments, where a single erroneous step can waste limited interaction budget or cause irreversible effects before task failure becomes apparent.…
Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades
Zhongye Liu, Yaopei Zeng, Yurui Chang +1
While multimodal large language models (MLLMs) have shown strong visual reasoning abilities, serving a large model for every query is computationally expensive. MLLM cascades mitig…
ReLope: From Hidden-State Probing to a Decision Module for Multimodal LLM Routing
Yaopei Zeng, Congchao Wang, Blake JianHang Chen +1
Routing balances performance and cost in hybrid systems by escalating selected queries from a lightweight model to a powerful but expensive one. Hidden-state probes provide an effe…
GuardDoor: Safeguarding Against Malicious Diffusion Editing via Protective Backdoors
Yaopei Zeng, Yuanpu Cao, Lu Lin
The growing accessibility of diffusion models has revolutionized image editing but also raised significant concerns about unauthorized modifications, such as misinformation and pla…
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models
Yaopei Zeng, Yuanpu Cao, Bochuan Cao +3
Recent advances in diffusion models have significantly enhanced the quality of image synthesis, yet they have also introduced serious safety concerns, particularly the generation o…