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 the expense of semantic fidelity and image quality. In this work, we propose RespoDiff, a novel framework for responsible text-to-image generation that incorporates a dual-module transformation on the intermediate bottleneck representations of diffusion models. Our approach introduces two distinct learnable modules: one focused on capturing and enforcing responsible concepts, such as fairness and safety, and the other dedicated to maintaining semantic alignment with neutral prompts. To facilitate the dual learning process, we introduce a novel score-matching objective that enables effective coordination between the modules. Our method outperforms state-of-the-art methods in responsible generation by ensuring semantic alignment while optimizing both objectives without compromising image fidelity. Our approach improves responsible and semantically coherent generation by ~20% across diverse, unseen prompts.

Existing post-hoc approaches can remove undesired concepts but often degrade useful signals. We introduce SPLINCE--Simultaneous Projection for LINear concept removal and Covariance prEservation--which eliminates sensitive concepts from representations while exactly preserving their covariance with a target label. SPLINCE achieves this via an oblique projection that "splices out" the unwanted direction yet protects important label correlations. Theoretically, it is the unique solution that removes linear concept predictability and maintains target covariance with minimal embedding distortion. Empirically, SPLINCE outperforms baselines on benchmarks such as Bias in Bios and Winobias, removing protected attributes while minimally damaging main-task information.

After decades risking arrest, South Korea's tattoo artists step into the limelight When Kim Tae-nam took the stage last Saturday in Seoul, it was a moment he had long been waiting for - the career he had chosen was no longer illegal. He couldn't stop smiling, the relief spilling into his voice: This was only possible because of our effort, all your sweat and tears. Let's hear it from everyone: Tattoos are art! They had gathered on a rooftop in Seongsu, a hip Seoul neighbourhood, for Ink Bomb: more than 90 local tattooists and artists openly celebrating body art, which had thrived in the shadows for decades. Just days before, South Korea's top court had overturned its 1992 ruling that defined tattooing as a medical act - bringing to an end Korean tattooists' decades-long fight for legitimacy.

Others say they don't need us. It's time for us to think of ourselves not as the high priests of health care but as what we have always been: healers. Not long ago, I cared for a middle-aged man I'll call Jim, who was generally healthy but had recently started to feel sluggish. One of his friends told him to try a hormone supplement. After Jim saw on social media that Robert F. Kennedy, Jr., the Trump Administration's Secretary of Health and Human Services, had endorsed supplements as a part of an "anti-aging" regimen, he ordered one from a telehealth company. A few months later, he noticed swelling and pain in his calf. ChatGPT warned him that he might have a blood clot.

We asked teachers about their experiences with AI in the classroom -- here's what they said Since ChatGPT and other large language models burst into public consciousness, school boards are drafting policies, universities are hosting symposiums and tech companies are relentlessly promoting their latest AI-powered learning tools . In the race to modernize education, artificial intelligence (AI) has become the new darling of policy innovation. While AI promises efficiency and personalization, it also introduces complexity, ethical dilemmas and new demands . Teachers, who are at the heart of learning along with students, are watching this transformation with growing unease. For example, according to the Alberta Teachers' Association, 80 to 90 per cent of educators surveyed expressed concern about AI's potential negative effects on education.

Vision-Language Models (VLMs) inherit significant social biases from their training data, notably in gender representation. Current fairness interventions often adopt a difference-unaware perspective that enforces uniform treatment across demographic groups. These approaches, however, fail to distinguish between contexts where neutrality is required and those where group-specific attributes are legitimate and must be preserved. Building upon recent advances in difference-aware fairness for text-only models, we extend this concept to the multimodal domain and formalize the problem of difference-aware gender fairness for image captioning and text-to-image generation. We advocate for selective debiasing, which aims to mitigate unwanted bias in neutral contexts while preserving valid distinctions in explicit ones. To achieve this, we propose BioPro (Bias Orthogonal Projection), an entirely training-free framework. BioPro identifies a low-dimensional gender-variation subspace through counterfactual embeddings and applies projection to selectively neutralize gender-related information. Experiments show that BioPro effectively reduces gender bias in neutral cases while maintaining gender faithfulness in explicit ones, thus providing a promising direction toward achieving selective fairness in VLMs. Beyond gender bias, we further demonstrate that BioPro can effectively generalize to continuous bias variables, such as scene brightness, highlighting its broader applicability.

Existing AI bias evaluation benchmarks largely reflect Western perspectives, leaving African contexts underrepresented and enabling harmful stereotypes in applications across various domains. To address this gap, we introduce AfriStereo, the first open-source African stereotype dataset and evaluation framework grounded in local socio-cultural contexts. Through community engaged efforts across Senegal, Kenya, and Nigeria, we collected 1,163 stereotypes spanning gender, ethnicity, religion, age, and profession. Using few-shot prompting with human-in-the-loop validation, we augmented the dataset to over 5,000 stereotype-antistereotype pairs. Entries were validated through semantic clustering and manual annotation by culturally informed reviewers. Preliminary evaluation of language models reveals that nine of eleven models exhibit statistically significant bias, with Bias Preference Ratios (BPR) ranging from 0.63 to 0.78 (p <= 0.05), indicating systematic preferences for stereotypes over antistereotypes, particularly across age, profession, and gender dimensions. Domain-specific models appeared to show weaker bias in our setup, suggesting task-specific training may mitigate some associations. Looking ahead, AfriStereo opens pathways for future research on culturally grounded bias evaluation and mitigation, offering key methodologies for the AI community on building more equitable, context-aware, and globally inclusive NLP technologies.

Text-to-image (T2I) diffusion models often exhibit gender bias, particularly by generating stereotypical associations between professions and gendered subjects. This paper presents SAE Debias, a lightweight and model-agnostic framework for mitigating such bias in T2I generation. Unlike prior approaches that rely on CLIP-based filtering or prompt engineering, which often require model-specific adjustments and offer limited control, SAE Debias operates directly within the feature space without retraining or architectural modifications. By leveraging a k-sparse autoencoder pre-trained on a gender bias dataset, the method identifies gender-relevant directions within the sparse latent space, capturing professional stereotypes. Specifically, a biased direction per profession is constructed from sparse latents and suppressed during inference to steer generations toward more gender-balanced outputs. Trained only once, the sparse autoencoder provides a reusable debiasing direction, offering effective control and interpretable insight into biased subspaces. Extensive evaluations across multiple T2I models, including Stable Diffusion 1.4, 1.5, 2.1, and SDXL, demonstrate that SAE Debias substantially reduces gender bias while preserving generation quality. To the best of our knowledge, this is the first work to apply sparse autoencoders for identifying and intervening in gender bias within T2I models. These findings contribute toward building socially responsible generative AI, providing an interpretable and model-agnostic tool to support fairness in text-to-image generation.