facebook-ai-research-6e2a417a·3 events·first seen Aliases: Facebook AI Research, Facebook Research, Meta (Facebook Research)
A new arXiv paper from Facebook Research evaluates whether mechanistic interpretability findings from open-weight models transfer to closed API-only models across prediction, attribution, and representation levels. Studying eleven models across four families (Llama, Qwen, GPT, Gemini), the authors find that prediction-level agreement substantially overstates attribution fidelity — models that agree on answers often disagree on why. They document an 'access-validity inversion' where white-box signals like attention patterns are stable across models but weakly predictive of causal attributions, undermining the common practice of using open surrogates to explain closed systems.
Meta / Facebook Research has released SAM 3, the third generation of their Segment Anything Model, with code for inference and finetuning, pretrained model checkpoints, and example notebooks. The repository has accumulated over 10,000 stars with strong daily momentum (+93). SAM 3 continues Meta's open-weights tradition in computer vision foundation models. No accompanying paper or technical blog post is referenced in this item.
Hugging Face has integrated fastText models into its Hub, enabling users to discover, share, and use fastText models through the standard Hub interface. fastText, originally developed by Facebook AI Research, is a widely-used library for efficient text classification and word vector representation. This integration extends the Hub's coverage of classical NLP tooling alongside modern transformer-based models.