7 papers
Orion-RAG: Path-Aligned Hybrid Retrieval for Graphless Data
Zhen Chen, Weihao Xie, Peilin Chen +2
Retrieval-Augmented Generation (RAG) has proven effective for knowledge synthesis, yet it encounters significant challenges in practical scenarios where data is inherently discrete…
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…
VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models: Methods and Results
Hanwei Zhu, Haoning Wu, Zicheng Zhang +26
This paper presents a summary of the VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models (LMMs), hosted as part of the ICCV 2025 Workshop on Visual Quali…
MolMark: Safeguarding Molecular Structures through Learnable Atom-Level Watermarking
Runwen Hu, Peilin Chen, Keyan Ding +1
AI-driven molecular generation is reshaping drug discovery and materials design, yet the lack of protection mechanisms leaves AI-generated molecules vulnerable to unauthorized reus…
Leveraging Diffusion Knowledge for Generative Image Compression with Fractal Frequency-Aware Band Learning
Lingyu Zhu, Xiangrui Zeng, Bolin Chen +3
By optimizing the rate-distortion-realism trade-off, generative image compression approaches produce detailed, realistic images instead of the only sharp-looking reconstructions pr…
Compact Visual Data Representation for Green Multimedia -- A Human Visual System Perspective
Peilin Chen, Xiaohan Fang, Meng Wang +2
The Human Visual System (HVS), with its intricate sophistication, is capable of achieving ultra-compact information compression for visual signals. This remarkable ability is coupl…