7 papers
RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL Attacks
Hanbo Huang, Yiran Zhang, Hao Zheng +5
Large language model (LLM) watermarking has shown promise in detecting AI-generated content and mitigating misuse, with prior work claiming robustness against paraphrasing and text…
Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning
Xuan Gong, Hanbo Huang, Hao Zheng +4
Long chain-of-thought (CoT) reasoning improves large vision--language models, but visual information often fades during generation, limiting long-horizon multimodal reasoning. Exis…
RLSpoofer: A Lightweight Evaluator for LLM Watermark Spoofing Resilience
Hanbo Huang, Xuan Gong, Yiran Zhang +2
Large language model (LLM) watermarking has emerged as a promising approach for detecting and attributing AI-generated text, yet its robustness to black-box spoofing remains insuff…
Convergence Dynamics of Over-Parameterized Score Matching for a Single Gaussian
Yiran Zhang, Weihang Xu, Mo Zhou +2
Score matching has become a central training objective in modern generative modeling, particularly in diffusion models, where it is used to learn high-dimensional data distribution…
From Generation to Detection: A Multimodal Multi-Task Dataset for Benchmarking Health Misinformation
Zhihao Zhang, Yiran Zhang, Xiyue Zhou +4
Infodemics and health misinformation have significant negative impact on individuals and society, exacerbating confusion and increasing hesitancy in adopting recommended health mea…
SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards
Jixiang Hong, Yiran Zhang, Guanzhong Wang +3
Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still strugg…