PulseAugur
EN
LIVE 18:25:57

OpenAI details DALL-E 2 pre-training mitigations for safety and bias

By PulseAugur Editorial · [1 sources] ·

OpenAI has detailed its pre-training mitigations for the DALL·E 2 image generation model, focusing on how the training data was modified to reduce risks. The company filtered out violent and sexual imagery from the dataset to prevent the model from generating such content. Additionally, OpenAI addressed potential biases introduced by data filtering and implemented techniques to mitigate image memorization by removing visually similar images. AI

RANK_REASON The article details safety mitigations applied during the pre-training of a specific AI model, DALL-E 2, which is a research-oriented disclosure.

Read on OpenAI News →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

OpenAI details DALL-E 2 pre-training mitigations for safety and bias

COVERAGE [1]

  1. OpenAI News TIER_1 English(EN) ·

    DALL·E 2 pre-training mitigations

    In order to share the magic of DALL·E 2 with a broad audience, we needed to reduce the risks associated with powerful image generation models. To this end, we put various guardrails in place to prevent generated images from violating our content policy.

RELATED TOPICS