DeepMind 大话互联网 2023-01-28 08:38:12 Pragmatic Fairness: Developing Policies with Outcome Disparity Control DownloadView publicationAbstractWe introduce a causal framework for designing optimal policies... 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
DeepMind nightclub 2023-01-25 14:28:12 On a continuous time model of gradient descent dynamics and instability in deep learning DownloadView publicationAbstractThe recipe of success behind the deep learning phe... 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 2023-01-11 09:48:51 Forecasting potential misuses of language models for disinformation campaigns and how to reduce risk OpenAI researchers collaborated with Georgetown University’s Center for Security and Emerging Techno... 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 2022-12-16 10:25:05 Point-E: A system for generating 3D point clouds from complex prompts Read paperView code... 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 大话互联网 2022-11-26 09:26:16 Fairness Reprogramming Download paperAbstractDespite a surge of recent advances in promoting machine Learning (ML) fairness... 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 2022-10-19 15:12:20 Scaling laws for reward model overoptimization Read paperAbstractIn reinforcement learning from human feedback, it is common to optimize against a ... 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 大话互联网 2022-10-17 11:02:21 Prediction of Ship Traffic on Waterways for Optimized Usage of Harbours with Graph Neural Networks and the Transformer View publicationAbstractPorts generate myriad of data making them an appealing infrastructure to aut... 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 大话互联网 2022-09-29 08:06:32 FETA: Towards Specializing Foundational Models for Expert Task Applications Download paperAbstractFoundation Models (FMs) have demonstrated unprecedented capabilities including... 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 2022-09-21 11:13:20 Introducing Whisper We’ve trained and are open-sourcing a neural net called Whisper that approaches human level robustne... 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 2022-09-05 11:47:00 Deep Indexed Active Learning for Matching Heterogeneous Entity Representations Download paperAbstractGiven two large lists of records, the task in entity resolution (ER) is to fin... 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 大话互联网 2022-08-13 10:37:32 Global Self-Attention as a Replacement for Graph Convolution Download paperAbstractWe propose an extension to the transformer neural network architecture for gen... 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 2022-07-28 12:51:57 Efficient training of language models to fill in the middle Read paperAbstractWe show that autoregressive language models can learn to infill text after we appl... 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
