English
Related papers

Related papers: SafeRoPE: Risk-specific Head-wise Embedding Rotati…

200 papers

Recent diffusion-based image editing methods commonly rely on text or high-level instructions to guide the generation process, offering intuitive but coarse control. In contrast, we focus on explicit, prompt-free editing, where the user…

Graphics · Computer Science 2026-04-24 Etai Sella , Yoav Baron , Hadar Averbuch-Elor , Daniel Cohen-Or , Or Patashnik

Rotary positional embeddings (RoPE) are widely used in large language models to encode token positions through multiplicative rotations, yet their behavior at long context lengths remains poorly characterized. In this work, we reinterpret…

Machine Learning · Computer Science 2026-02-12 Feilong Liu

Recent advances in text-to-image (T2I) diffusion models have enabled impressive generative capabilities, but they also raise significant safety concerns due to the potential to produce harmful or undesirable content. While concept erasure…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Nanxiang Jiang , Zhaoxin Fan , Enhan Kang , Daiheng Gao , Yun Zhou , Yanxia Chang , Zheng Zhu , Yeying Jin , Wenjun Wu

The widespread deployment of text-to-image diffusion models is significantly challenged by the generation of visually harmful content, such as sexually explicit content, violence, and horror imagery. Common safety interventions, ranging…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Lingyun Zhang , Yu Xie , Zhongli Fang , Yu Liu , Ping Chen

Many recent text-to-speech (TTS) systems are built on transformer architectures and employ cross-attention mechanisms for text-speech alignment. Within these systems, rotary position embedding (RoPE) is commonly used to encode positional…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-16 Hyeongju Kim , Juheon Lee , Jinhyeok Yang , Jacob Morton

Recent progress in video generative models has enabled the creation of high-quality videos from multimodal prompts that combine text and images. While these systems offer enhanced controllability, they also introduce new safety risks, as…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Ruize Ma , Minghong Cai , Yilei Jiang , Jiaming Han , Yi Feng , Yingshui Tan , Xiaoyong Zhu , Bo Zhang , Bo Zheng , Xiangyu Yue

Training multimodal generative models on large, uncurated datasets can result in users being exposed to harmful, unsafe and controversial or culturally-inappropriate outputs. While model editing has been proposed to remove or filter…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Jordan Vice , Naveed Akhtar , Mubarak Shah , Richard Hartley , Ajmal Mian

Rotary Position Embedding (RoPE) has shown strong performance in text-based Large Language Models (LLMs), but extending it to video remains a challenge due to the intricate spatiotemporal structure of video frames. Existing adaptations,…

Artificial Intelligence · Computer Science 2025-11-03 Zikang Liu , Longteng Guo , Yepeng Tang , Tongtian Yue , Junxian Cai , Kai Ma , Qingbin Liu , Xi Chen , Jing Liu

The widespread deployment of text-to-image models is challenged by their potential to generate harmful content. While existing safety methods, such as prompt rewriting or model fine-tuning, provide valuable interventions, they often…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Lingyun Zhang , Yu Xie , Yanwei Fu , Ping Chen

The rapid advancement of diffusion models has enabled high-fidelity and semantically rich text-to-image generation; however, ensuring fairness and safety remains an open challenge. Existing methods typically improve fairness and safety at…

Computer Vision and Pattern Recognition · Computer Science 2025-10-09 Silpa Vadakkeeveetil Sreelatha , Sauradip Nag , Muhammad Awais , Serge Belongie , Anjan Dutta

The rise of text-to-video generation models has raised growing concerns over content authenticity, copyright protection, and malicious misuse. Watermarking serves as an effective mechanism for regulating such AI-generated content, where…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Yang Yang , Xinze Zou , Zehua Ma , Han Fang , Weiming Zhang

Text-to-image (T2I) models are widespread, but their limited safety guardrails expose end users to harmful content and potentially allow for model misuse. Current safety measures are typically limited to text-based filtering or concept…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Runtao Liu , I Chieh Chen , Jindong Gu , Jipeng Zhang , Renjie Pi , Qifeng Chen , Philip Torr , Ashkan Khakzar , Fabio Pizzati

Learning-based quadruped controllers achieve impressive agility but typically lack formal safety guarantees under model uncertainty, perception noise, and unstructured contact conditions. We introduce SafeMind, a differentiable stochastic…

Robotics · Computer Science 2026-04-13 Zukun Zhang , Kai Shu , Mingqiao Mo

The attention module, which is a crucial component in Transformer, cannot scale efficiently to long sequences due to its quadratic complexity. Many works focus on approximating the dot-then-exponentiate softmax function in the original…

Machine Learning · Computer Science 2021-11-04 Shengjie Luo , Shanda Li , Tianle Cai , Di He , Dinglan Peng , Shuxin Zheng , Guolin Ke , Liwei Wang , Tie-Yan Liu

The rise of text-to-image (T2I) models has increasingly raised concerns regarding the generation of risky content, such as sexual, violent, and copyright-protected images, highlighting the need for effective safeguards within the models…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Chenyu Zhang

We propose RoPECraft, a training-free video motion transfer method for diffusion transformers that operates solely by modifying their rotary positional embeddings (RoPE). We first extract dense optical flow from a reference video, and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Ahmet Berke Gokmen , Yigit Ekin , Bahri Batuhan Bilecen , Aysegul Dundar

Text-to-image (T2I) models can generate not-safe-for-work (NSFW) content, motivating multi-stage safety pipelines with both text and image filters. Newer LLM-based filters detect latent intent beyond keywords, making token-level…

Machine Learning · Computer Science 2026-05-26 Zixuan Chen , Hao Lin , Ke Xu , Xinghao Jiang , Tanfeng Sun

Long-context large language models (LLMs) have achieved remarkable advancements, driven by techniques like Rotary Position Embedding (RoPE) (Su et al., 2023) and its extensions (Chen et al., 2023; Liu et al., 2024c; Peng et al., 2023). By…

Computation and Language · Computer Science 2025-10-24 Bowen Yang , Bharat Venkitesh , Dwarak Talupuru , Hangyu Lin , David Cairuz , Phil Blunsom , Acyr Locatelli

The remarkable ability of diffusion models to generate high-fidelity images has led to their widespread adoption. However, concerns have also arisen regarding their potential to produce Not Safe for Work (NSFW) content and exhibit social…

Computation and Language · Computer Science 2025-05-22 Zhiwen Li , Die Chen , Mingyuan Fan , Cen Chen , Yaliang Li , Yanhao Wang , Wenmeng Zhou

With the advance of generative AI, the text-to-image (T2I) model has the ability to generate various contents. However, the generated contents cannot be fully controlled. There is a potential risk that T2I model can generate unsafe images…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Dong Han , Salaheldin Mohamed , Yong Li