Related papers: Value-Aligned Prompt Moderation via Zero-Shot Agen…
Aligning Vision-Language Models (VLMs) with safety standards is essential to mitigate risks arising from their multimodal complexity, where integrating vision and language unveils subtle threats beyond the reach of conventional safeguards.…
Creative generation is the synthesis of new, surprising, and valuable samples that reflect user intent yet cannot be envisioned in advance. This task aims to extend human imagination, enabling the discovery of visual concepts that exist in…
Text-to-Image (T2I) models have made remarkable progress in generating images from text prompts, but their output quality and safety still depend heavily on how prompts are phrased. Existing safety methods typically refine prompts using…
As Vision-Language Models (VLMs) demonstrate increasing capabilities across real-world applications such as code generation and chatbot assistance, ensuring their safety has become paramount. Unlike traditional Large Language Models (LLMs),…
The proliferation of Large Language Models (LLMs) in real-world applications poses unprecedented risks of generating harmful, biased, or misleading information to vulnerable populations including LGBTQ+ individuals, single parents, and…
Accurate rejection of sensitive or harmful visual content, i.e., harmful image guardrail, is critical in many application scenarios. This task must continuously adapt to the evolving safety policies and content across various domains and…
In autoregressive (AR) image generation, models based on the 'next-token prediction' paradigm of LLMs have shown comparable performance to diffusion models by reducing inductive biases. However, directly applying LLMs to complex image…
Ensuring cultural values alignment in Large Language Models (LLMs) remains a critical challenge, as these models often embed Western-centric biases from their training data, leading to misrepresentations and fairness concerns in…
Vision-language models (VLMs) are essential for contextual understanding of both visual and textual information. However, their vulnerability to adversarially manipulated inputs presents significant risks, leading to compromised outputs and…
Single-prompt first-token probabilities from zero-shot vision-language model (VLM) safety classifiers are treated as decision scores, but we show they are unreliable under semantically equivalent prompt reformulation: even when the binary…
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…
Detecting illicit visual content demands more than image-level NSFW flags; moderators must also know what objects make an image illegal and where those objects occur. We introduce a zero-shot pipeline that simultaneously (i) detects if an…
Ensuring that online discussions are civil and productive is a major challenge for social media platforms. Such platforms usually rely both on users and on automated detection tools to flag inappropriate arguments of other users, which…
Radiology Report Generation (RRG) is a critical step toward automating healthcare workflows, facilitating accurate patient assessments, and reducing the workload of medical professionals. Despite recent progress in Large Medical…
Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently solve complex tasks. We extend this paradigm to safety…
Despite recent progress in text-to-image (T2I) generation, existing models often struggle to faithfully capture user intentions from short and under-specified prompts. While prior work has attempted to enhance prompts using large language…
Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated…
Vision-language agents have achieved remarkable progress in a variety of multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to…
Large Vision-Language Models (LVLMs) can be vulnerable to adversarial images that subtly bias their outputs toward plausible yet incorrect responses. We introduce a general, efficient, and training-free defense that combines image…
Due to the subtleness, implicity, and different possible interpretations perceived by different people, detecting undesirable content from text is a nuanced difficulty. It is a long-known risk that language models (LMs), once trained on…