OpenAI 大话互联网 2022-07-25 09:44:22 A hazard analysis framework for code synthesis large language models Read paperAbstractCodex, a large language model (LLM) trained on a variety of codebases, exceeds the... 评论 分享 微信扫一扫：分享 微信点“扫一扫” 点右上“...”，便可分享本文
OpenAI 科技百花 2022-06-28 08:24:43 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 associa... 评论 分享 微信扫一扫：分享 微信点“扫一扫” 点右上“...”，便可分享本文
OpenAI 科技百花 2022-06-23 10:31:41 Learning to play Minecraft with Video PreTraining We trained a neural network to play Minecraft by Video PreTraining (VPT) on a massive unlabeled vide... 评论 分享 微信扫一扫：分享 微信点“扫一扫” 点右上“...”，便可分享本文
OpenAI 科技百花 2022-06-17 08:58:24 Evolution through large models Read paperAbstractThis paper pursues the insight that large language models (LLMs) trained to genera... 评论 分享 微信扫一扫：分享 微信点“扫一扫” 点右上“...”，便可分享本文
OpenAI 大话互联网 2022-06-13 13:11:51 AI-written critiques help humans notice flaws We trained “critique-writing” models to describe flaws in summaries. Human evaluators find flaws in ... 评论 分享 微信扫一扫：分享 微信点“扫一扫” 点右上“...”，便可分享本文
OpenAI 科技百花 2022-06-09 14:25:49 Techniques for training large neural networks Large neural networks are at the core of many recent advances in AI, but training them is a difficul... 评论 分享 微信扫一扫：分享 微信点“扫一扫” 点右上“...”，便可分享本文
OpenAI 大话互联网 2022-05-28 09:46:32 Teaching models to express their uncertainty in words Read paperAbstractWe show that a GPT-3 model can learn to express uncertainty about its own answers ... 评论 分享 微信扫一扫：分享 微信点“扫一扫” 点右上“...”，便可分享本文
IBM 科技百花 2022-04-24 13:03:02 Can an Image Classifier Suffice For Action Recognition? Download paperAbstractWe propose a new perspective to perform action recognition without temporal mo... 评论 分享 微信扫一扫：分享 微信点“扫一扫” 点右上“...”，便可分享本文
IBM 科技百花 2022-04-24 11:39:37 Linking Emergent and Natural Languages via Corpus Transfer Download paperAbstractThe study of language emergence aims to understand how human languages are sha... 评论 分享 微信扫一扫：分享 微信点“扫一扫” 点右上“...”，便可分享本文
IBM 科技百花 2022-04-24 10:23:41 RegionViT: Regional-to-Local Attention for Vision Transformers Download paperAbstractVision transformer (ViT) has recently shown its strong capability in achieving... 评论 分享 微信扫一扫：分享 微信点“扫一扫” 点右上“...”，便可分享本文
OpenAI 科技百花 2022-04-13 11:28:15 Hierarchical text-conditional image generation with CLIP latents Read paperAbstractContrastive models like CLIP have been shown to learn robust representations of im... 评论 分享 微信扫一扫：分享 微信点“扫一扫” 点右上“...”，便可分享本文
OpenAI nightclub 2022-04-13 08:26:36 Measuring Goodhart’s law Goodhart’s law famously says: “When a measure becomes a target, it ceases to be a good measure.” Alt... 评论 分享 微信扫一扫：分享 微信点“扫一扫” 点右上“...”，便可分享本文
