Jingjing Chen

Benchmarking Gaslighting Negation Attacks Against Multimodal Large Language Models

Bin Zhu, Yuesheng Gui, Huiyan Qi, Jingjing Chen et autres

Multimodal Large Language Models (MLLMs) have exhibited remarkable advancements in integrating different modalities, excelling in complex understanding and generation tasks. Despite their success, MLLMs remain vulnerable to conversational adversarial inputs. In this paper, we systematically study gaslighting negation attacks—a phenomenon where models, …

sg, cn (code pays fourni par la source)

Copyright Infringement Detection in Text-to-Image Diffusion Models via Differential Privacy

Xiafeng Man, Zhipeng Wei, Jingjing Chen

The widespread deployment of large vision models such as Stable Diffusion raises significant legal and ethical concerns, as these models can memorize and reproduce copyrighted content without authorization. Existing detection approaches often lack robustness and fail to provide rigorous theoretical underpinnings. To …

us, cn (code pays fourni par la source)

Escaping from saddle points with perturbed gradient estimation

Jingjing Chen, Sanyang Liu

cn (code pays fourni par la source)

Copyright Infringement Detection in Text-to-Image Diffusion Models via Differential Privacy

Xiafeng Man, Zhipeng Wei, Jingjing Chen

The widespread deployment of large vision models such as Stable Diffusion raises significant legal and ethical concerns, as these models can memorize and reproduce copyrighted content without authorization. Existing detection approaches often lack robustness and fail to provide rigorous theoretical underpinnings. To …

VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation

Feng Han, Chao Gong, Zhipeng Wei, Jingjing Chen et autres

Recently, autoregressive image generation models have wowed audiences with their remarkable capability in creating surprisingly realistic images. Models such as GPT-4o and LlamaGen can not only produce images that faithfully mimic renowned artistic styles like Ghibli, Van Gogh, or Picasso, but also …

The effectiveness of stem cell‑derived extracellular vesicles therapy for intrauterine adhesions: a meta-analysis of preclinical studies

Yuanyuan Sun, Yan Luo, Jinyao Ning, Yitong Chai et autres

BACKGROUND: The therapeutic potential of stem cell-derived extracellular vesicles (EVs) for intrauterine adhesions (IUA) has attracted increasing preclinical investigation, yet a comprehensive and up-to-date meta-analysis is currently lacking. Before moving forward with clinical applications, it is essential to fully understand the impact …

cn (code pays fourni par la source)

CT and MRI manifestations of pancreatic hemangioma: a literature review and a new case report

Jingjing Chen, Dongmei Zou, Xu Cao

Pancreatic hemangioma is an extremely rare benign tumor occurring in the pancreas. Preoperative diagnosis is challenging due to its lack of specificity on clinical manifestations and imaging examinations. Pancreatic lesion was found on physica

cn (code pays fourni par la source)

Efficient Prompt Tuning for Hierarchical Ingredient Recognition

Yuesheng Gui, Bin Benjamin Zhu, Jingjing Chen, Chong‐Wah Ngo

Fine-Grained ingredient recognition presents a significant challenge due to the diverse appearances of ingredients, resulting from different cutting and cooking methods. While existing approaches have shown promising results, they still require extensive training costs and focus solely on fine-grained ingredient recognition. In …

cn, sg (code pays fourni par la source)

Stable and Ultrasensitive X‐Ray Detectors Based on Oriented Single‐Crystal Perovskite Rods

Depeng Chu, Naiming Liu, Shenghui Xie, Yaohui Li et autres

Abstract Metal‐halide perovskite single crystals (SCs) are promising candidates for next‐generation X‐ray detectors. X‐ray detectors fabricated using perovskite FAPbI 3 SCs exhibit high detection sensitivity. However, two pressing issues still need to be addressed for practical applications: the orientation‐controlled growth and environmentally …

cn (code pays fourni par la source)

Efficient Prompt Tuning for Hierarchical Ingredient Recognition

Yuesheng Gui, Bin Benjamin Zhu, Jingjing Chen, Chong‐Wah Ngo

Fine-grained ingredient recognition presents a significant challenge due to the diverse appearances of ingredients, resulting from different cutting and cooking methods. While existing approaches have shown promising results, they still require extensive training costs and focus solely on fine-grained ingredient recognition. In …

An Integration-Enhanced ZNN Approach for Chaotic Combination Synchronization with External Disturbances$$^{*}$$

Chenfu Yi, Mingdong Zhu, Jingjing Chen, Jinghui Peng

cn (code pays fourni par la source)

Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image

Pengkun Jiao, Na Zhao, Jingjing Chen, Yu–Gang Jiang

cn, sg (code pays fourni par la source)