7 papers
Seeing Without Exposing: Adaptive Privacy Control for Open-World, Context-Hungry MLLMs
Siyuan Xu, Yibing Liu, Peilin Chen +3
Multimodal large language models (MLLMs) have raised new privacy challenges. On the data side, user-provided inputs often include unpredictable sensitive information; while on the…
When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editing
Siyuan Xu, Yibing Liu, Peilin Chen +3
Multimodal Large Language Models (MLLMs) enable flexible instruction-driven image editing, but privacy risks arise when user images expose diverse and user-specific private content…
RAISE: RAG Design as an Architecture Search Problem
Zhen Chen, Yibing Liu, Weihao Xie +3
Retrieval-augmented generation (RAG) systems expose numerous design choices spanning query rewriting, chunking, retrieval depth, reranking, and context compression. In practice, th…
OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories
Yibing Liu, Yangze Liu, Xiaolong Yin +4
Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external write…
Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models
Kecheng Chen, Ziru Liu, Xijia Tao +9
Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive language models, offering stronger global awareness and highly parallel generati…
When Privacy Meets Recovery: The Overlooked Half of Surrogate-Driven Privacy Preservation for MLLM Editing
Siyuan Xu, Yibing Liu, Peilin Chen +3
Privacy leakage in Multimodal Large Language Models (MLLMs) has long been an intractable problem. Existing studies, though effectively obscure private information in MLLMs, often o…