16 papers
Understanding Machine Taste: Aesthetic Agreement Across Foundation Models in K-pop
Kaishen Wang, Yucheng Pan, Xuehao Cui +2
As foundation models enter creative industries, understanding their aesthetic preferences becomes an important step toward AI-assisted creative decision making. In this work, we in…
TTMark: Pairwise Distortion-Free Watermarking Beyond Single-Token Entropy
Ruibo Chen, Zhengmian Hu, Donghang Lu +5
Distortion-free watermarking enables reliable attribution of machine-generated text while preserving output distribution. However, existing methods operate independently on each ge…
Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio
Georgios Milis, Yubin Qin, Yihan Wu +1
As policy catches up with the capabilities of generative AI, watermarking is central to content provenance efforts. Inference-time watermarks for autoregressive models are unfit fo…
EnvTriCascade: An Environment-Aware Tri-Stage Cascaded Framework for ESDD2 2026 Challenge
Hengyan Huang, Xiaoxuan Guo, Jiayi Zhou +5
ADD in real-world scenarios has evolved from speech-only spoofing to more challenging component-level settings, where speech and environmental sounds may be independently manipulat…
Compositional Adversarial Training for Robust Visual Watermarking
Anirudh Satheesh, Michael-Andrei Panaitescu-Liess, Andrew Xu +4
Robust watermarking is typically trained with random post-processing augmentation, but random sampling under-covers the combinatorial space of realistic attack pipelines and rarely…
Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models
Kaishen Wang, Heng Huang
Recent advances in Large Language Models (LLMs) and Text-to-Image (T2I) models have led to the emergence of Unified Multimodal Models (UMMs), where multimodal understanding and ima…
MCMark: Distortion-Free Multi-Bit Watermarking for Long Messages
Xuehao Cui, Ruibo Chen, Yihan Wu +1
Large language models now produce text indistinguishable from human writing, which increases the need for reliable provenance tracing. Multi-bit watermarking can embed identifiers…
More Haste, Less Speed: Weaker Single-Layer Watermark Improves Distortion-Free Watermark Ensembles
Ruibo Chen, Yihan Wu, Xuehao Cui +2
Watermarking has emerged as a crucial technique for detecting and attributing content generated by large language models. While recent advancements have utilized watermark ensemble…
Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following
Tianyi Xiong, Yi Ge, Ming Li +13
Large multimodal models (LMMs) are increasingly adopted as judges in multimodal evaluation systems due to their strong instruction following and consistency with human preferences.…
ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generation
Kaishen Wang, Ruibo Chen, Tong Zheng +1
Recent text-to-image (T2I) models have made remarkable progress in generating visually realistic and semantically coherent images. However, they still suffer from randomness and in…
Robust Distortion-Free Watermark for Autoregressive Audio Generation Models
Yihan Wu, Georgios Milis, Ruibo Chen +1
The rapid advancement of next-token-prediction models has led to widespread adoption across modalities, enabling the creation of realistic synthetic media. In the audio domain, whi…
POET: Preference Optimization for Enhanced Text-to-Image Generation
Ruibo Chen, Jiacheng Pan, Heng Huang +1
Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models often struggle with simple or underspecified user prompts due to a distribut…
Leave No TRACE: Black-box Detection of Copyrighted Dataset Usage in Large Language Models via Watermarking
Jingqi Zhang, Ruibo Chen, Yingqing Yang +3
Large Language Models (LLMs) are increasingly fine-tuned on smaller, domain-specific datasets to improve downstream performance. These datasets often contain proprietary or copyrig…
Model Correlation Detection via Random Selection Probing
Ruibo Chen, Sheng Zhang, Yihan Wu +3
The growing prevalence of large language models (LLMs) and vision-language models (VLMs) has heightened the need for reliable techniques to determine whether a model has been fine-…
Analyzing and Evaluating Unbiased Language Model Watermark
Yihan Wu, Xuehao Cui, Ruibo Chen +1
Verifying the authenticity of AI-generated text has become increasingly important with the rapid advancement of large language models, and unbiased watermarking has emerged as a pr…
An Ensemble Framework for Unbiased Language Model Watermarking
Yihan Wu, Ruibo Chen, Georgios Milis +1
As large language models become increasingly capable and widely deployed, verifying the provenance of machine-generated content is critical to ensuring trust, safety, and accountab…