Memes Don’t Act Alone: Meet MemeWeaver for Safer Feeds

Kari Jaaskelainen

14 Jan 2026 — 1 min read

Memes don’t act alone—neither should moderation

Women are twice as likely as men to face gender-based harassment online. MemeWeaver is a new AI that spots sexist and misogynistic memes by looking beyond single posts to the web of related memes they live in.

Instead of judging an image or caption in isolation, MemeWeaver builds a graph that connects memes with shared visuals, text, or themes, then reasons across those links. This richer context helps it catch subtle dog whistles and community in‑jokes that standard models miss.

Multimodal: fuses image and text signals end to end.
Relational: learns meaningful connections between memes.
Proven: beats strong baselines on the MAMI and EXIST benchmarks and trains faster.

Beyond better accuracy, the learned graph reveals how harmful narratives spread—offering actionable insights for moderators and researchers.

Paper by Paolo Italiani, David Gimeno-Gomez, Luca Ragazzi, Gianluca Moro, and Paolo Rosso. Read more: https://arxiv.org/abs/2601.08684v1

Paper: https://arxiv.org/abs/2601.08684v1

Register: https://www.AiFeta.com

#AI #ContentModeration #OnlineSafety #HateSpeech #Sexism #Misogyny #Memes #ComputerVision #NLP

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added