相关论文: SafeRoPE: Risk-specific Head-wise Embedding Rotati…

Adversarially perturbed images of text can cause sophisticated OCR systems to produce misleading or incorrect transcriptions from seemingly invisible changes to humans. Some of these perturbations even survive physical capture, posing…

Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising process guided by text embeddings extracted from pretrained vision-language models such as…

Transformer-based architectures achieve state-of-the-art performance across a wide range of tasks in natural language processing, computer vision, and speech processing. However, their immense capacity often leads to overfitting, especially…

In recent years, fueled by the rapid advancement of diffusion models, text-to-video (T2V) generation models have achieved remarkable progress, with notable examples including Pika, Luma, Kling, and Open-Sora. Although these models exhibit…

Recent text-to-image (T2I) models have exhibited remarkable performance in generating high-quality images from text descriptions. However, these models are vulnerable to misuse, particularly generating not-safe-for-work (NSFW) content, such…

Rotary Position Embedding (RoPE) is widely adopted in large language models, but when applied to vision-language models (VLMs) it couples text and image position indices and can introduce spurious cross-modal relative-position bias. We…

Diffusion transformers (DiTs) struggle to generate images at resolutions higher than their training resolutions. The primary obstacle is that the explicit positional encodings(PE), such as RoPE, need extrapolating to unseen positions which…

The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…

Mechanistic interpretability improves the safety, reliability, and robustness of large AI models. This study examined individual attention heads in vision transformers (ViTs) fine tuned on distorted 2D spectrogram images containing non…

Transformer encoders are widely deployed in large-scale web services for natural language understanding tasks such as text classification, semantic retrieval, and content ranking. However, their high inference latency and memory consumption…

Vision-language models remain susceptible to multimodal jailbreaks and over-refusal because safety hinges on both visual evidence and user intent, while many alignment pipelines supervise only the final response. To address this, we present…

Fine-tuning large language models (LLMs) on additional datasets is often necessary to optimize them for specific downstream tasks. However, existing safety alignment measures, which restrict harmful behavior during inference, are…

Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-to-image models may be tricked into generating…

Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, yet real-world deployment often requires continual capability expansion across sequential tasks. In such scenarios, Multimodal Continual…

Recent progress in image generation models (IGMs) enables high-fidelity content creation but also amplifies risks, including the reproduction of copyrighted content and the generation of offensive content. Image Generation Model Unlearning…

The unlearning problem of deep learning models, once primarily an academic concern, has become a prevalent issue in the industry. The significant advances in text-to-image generation techniques have prompted global discussions on privacy,…

Bridging the sim2real gap between computationally inexpensive models and complex physical systems remains a central challenge in machine learning applications to engineering problems, particularly in multi-scale settings where reduced-order…

Current deepfake detection models achieve state-of-the-art performance on pristine academic datasets but suffer severe spatial attention drift under real-world compound degradations, such as blurring and severe lossy compression. To address…

Current video generation techniques excel at single-shot clips but struggle to produce narrative multi-shot videos, which require flexible shot arrangement, coherent narrative, and controllability beyond text prompts. To tackle these…

Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…