From the 2 of 16 linked papers with an AI index.
16 papers
FARI: Robust One-Step Inversion for Watermarking in Diffusion Models
Jindong Yang, Han Fang, Weiming Zhang +2
The paper introduces FARI, a fast one-step inversion method combined with lightweight adversarial LoRA fine-tuning to robustly extract watermarks from diffusion-generated images, a…
DNA: Dual-stage Native Attribution for Generated Image Source Tracing
Chao Wang, Kejiang Chen, Zijin Yang +4
The paper proposes DNA, a two‑stage framework that attributes generated images to their source models without additional training by first screening at the family level and then pi…
PTL-Diffusion: Manifold-Aware Diffusion with Periodic Terminal Laws
Danqi Zhuang, Jisui Huang, Xiaoyue Xi +4
Standard diffusion models typically use a single time-homogeneous Gaussian terminal distribution as the reference law for generation. While this choice is analytically convenient a…
BareWave: Waveform-Native Flow-Matching Text-to-Speech
Wei Fan, Chao-Hong Tan, Qian Chen +5
Removing intermediate representations and separately trained decoding stages has become an important direction in generative modeling. In text-to-speech, however, high-quality syst…
ReTokSync: Self-Synchronizing Tokenization Disambiguation for Generative Linguistic Steganography
Yaofei Wang, Rui Wang, Weilong Pang +4
Generative linguistic steganography (GLS) enables covert communication by embedding secret messages into the natural language generation process. In practical deployment, however,…
Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries
Ki Sen Hung, Xi Yang, Chang Liu +7
A central goal of LLM alignment is to balance helpfulness with harmlessness, yet these objectives conflict when the same knowledge serves both legitimate and malicious purposes. Th…