🏢 Meta FAIR

LLM watermarking leaves detectable traces in subsequently trained models, enabling detection of synthetic data usage—a phenomenon termed ‘radioactivity’.

Iterative Reasoning Preference Optimization boosts large language model reasoning by iteratively refining preferences between generated reasoning steps, achieving significant accuracy gains on benchma…

Discrete Flow Matching (DFM) revolutionizes discrete data generation by introducing a novel flow paradigm that surpasses existing methods. DFM leverages flexible probability paths, enabling efficient …