首页/论文/2002.05512

arXiv 2002.055122020-02-12cs.LGcs.CVeess.IVstat.ML

Real or Not Real, that is the Question

The Chinese University of Hong Kong（香港中文大学）；Nanyang Technological University（南洋理工大学）

Yuanbo Xiangli, Yubin Deng, Bo Dai, Chen Change Loy, Dahua Lin

备注：: ICLR2020 spotlight. 1) train GAN by maximizing kl-divergence. 2) train non-progressive GAN (DCGAN) architecture at 1024*1024 resolution

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

While generative adversarial networks (GAN) have been widely adopted in various topics, in this paper we generalize the standard GAN to a new perspective by treating realness as a random variable that can be estimated from multiple angles. In this generalized framework, referred to as RealnessGAN, the discriminator outputs a distribution as the measure of realness. While RealnessGAN shares similar theoretical guarantees with the standard GAN, it provides more insights on adversarial learning. Compared to multiple baselines, RealnessGAN provides stronger guidance for the generator, achieving improvements on both synthetic and real-world datasets. Moreover, it enables the basic DCGAN architecture to generate realistic images at 1024*1024 resolution when trained from scratch.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Educational Question Mining At Scale: Prediction, Analysis and Personalization

Microsoft Research Cambridge（微软研究院剑桥分部）

Online education platforms enable teachers to share a large number of educational resources such as questions to form exercises and quizzes for students. With large volumes of available questions, it is important to have an automated way to quantify their properties and intelligently select them for students, enabling effective and personalized learning experiences. In this work, we propose a framework for mining insights from educational questions at scale. We utilize the state-of-the-art Bayesian deep learning method, in particular partial variational auto-encoders (p-VAE), to analyze real s…

2021-03-01cs.CYcs.LGstat.AP

A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input

Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）

We propose a method for automatically answering questions about images by bringing together recent advances from natural language processing and computer vision. We combine discrete reasoning with uncertain predictions by a multi-world approach that represents uncertainty about the perceived world in a bayesian framework. Our approach can handle human questions of high complexity about realistic scenes and replies with range of answer like counts, object classes, instances and lists of them. The system is directly trained from question-answer pairs. We establish a first benchmark for this task…

2015-05-05cs.AIcs.CLcs.CV

GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering

Stanford University（斯坦福大学）

We introduce GQA, a new dataset for real-world visual reasoning and compositional question answering, seeking to address key shortcomings of previous VQA datasets. We have developed a strong and robust question engine that leverages scene graph structures to create 22M diverse reasoning questions, all come with functional programs that represent their semantics. We use the programs to gain tight control over the answer distribution and present a new tunable smoothing technique to mitigate question biases. Accompanying the dataset is a suite of new metrics that evaluate essential qualities such…

2019-05-10cs.AIcs.CLcs.CV

RA-QA：一种用于在现实世界异质性下呼吸音频问答的基准系统

RA-QA: A Benchmarking System for Respiratory Audio Question Answering Under Real-World Heterogeneity

本文提出RA-QA基准系统，通过标准化数据生成流程和统一评估协议，整合900万组异构问答对，评估通用音频语言模型和领域特定架构在现实异质性下的表现。

2026-06-29cs.LGcs.SDeess.AS

Answering Questions on COVID-19 in Real-Time

Korea University（高丽大学）

The recent outbreak of the novel coronavirus is wreaking havoc on the world and researchers are struggling to effectively combat it. One reason why the fight is difficult is due to the lack of information and knowledge. In this work, we outline our effort to contribute to shrinking this knowledge vacuum by creating covidAsk, a question answering (QA) system that combines biomedical text mining and QA techniques to provide answers to questions in real-time. Our system also leverages information retrieval (IR) approaches to provide entity-level answers that are complementary to QA models. Evalua…

2020-10-09cs.AIcs.CLcs.LG

GraphEQA：利用3D语义场景图进行实时具身问答

GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering

Carnegie Mellon University（卡内基梅隆大学）；Neya Systems（Neya系统）；Agility Robotics（敏捷机器人）；Hello Robot；Bosch Center for AI（博世人工智能中心）

GraphEQA利用实时3D语义场景图和任务相关图像作为多模态记忆，结合分层规划引导探索，在未知环境中完成具身问答，在HM-EQA和OpenEQA基准上以更高成功率和更少步骤超越基线，并在真实环境验证。

2025-09-24cs.CLcs.CVcs.LG

更多相关论文收起更多论文

Building the Intent Landscape of Real-World Conversational Corpora with Extractive Question-Answering Transformers

Bell Canada（加拿大贝尔）

For companies with customer service, mapping intents inside their conversational data is crucial in building applications based on natural language understanding (NLU). Nevertheless, there is no established automated technique to gather the intents from noisy online chats or voice transcripts. Simple clustering approaches are not suited to intent-sparse dialogues. To solve this intent-landscape task, we propose an unsupervised pipeline that extracts the intents and the taxonomy of intents from real-world dialogues. Our pipeline mines intent-span candidates with an extractive Question-Answering…

2022-08-30cs.AIcs.CLcs.LG

UQ：评估语言模型在未解决问题上的表现

UQ: Assessing Language Models on Unsolved Questions

Stanford University（斯坦福大学）；University of Washington（华盛顿大学）；UNC（北卡罗来纳大学）；Rutgers University（罗格斯大学）；Contextual AI

针对当前AI基准存在的困难与现实张力问题，提出UQ测试平台，通过异步评估未解决问题、结合验证器和社区验证，推动模型在真实挑战中的能力提升，顶级模型仅15%通过率。

2025-08-25cs.AIcs.CLcs.LG

Spatial-RAG：面向真实世界地理空间推理问题的空间检索增强生成

Spatial-RAG: Spatial Retrieval Augmented Generation for Real-World Geospatial Reasoning Questions

Emory University（埃默里大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）

提出 Spatial-RAG 框架，通过结合稀疏空间过滤与密集语义匹配的混合检索器，并进行空间与语义多目标优化，提升真实地理空间问答性能。

2025-06-11cs.ETcs.IRcs.LG

Speeding Up Question Answering Task of Language Models via Inverted Index

Boston University（波士顿大学）；eMentalist

Natural language processing applications, such as conversational agents and their question-answering capabilities, are widely used in the real world. Despite the wide popularity of large language models (LLMs), few real-world conversational agents take advantage of LLMs. Extensive resources consumed by LLMs disable developers from integrating them into end-user applications. In this study, we leverage an inverted indexing mechanism combined with LLMs to improve the efficiency of question-answering models for closed-domain questions. Our experiments show that using the index improves the averag…

2022-10-24cs.CLcs.IRcs.LG

NoisyEQA：针对噪声查询的具身问答基准

NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries

Nanyang Technological University（南洋理工大学）；RIKEN AIP（理化学研究所人工智能项目）

针对现实场景中人类提问常含噪声的问题，提出NoisyEQA基准，涵盖四类噪声，并引入自我纠正提示机制与评估指标，有效提升智能体答案准确性。

2024-12-14cs.AIcs.CVcs.LG

MSX销售副驾中生成式AI的案例研究：利用实时问答系统进行内容推荐以提升卖家生产力

A case study of Generative AI in MSX Sales Copilot: Improving seller productivity with a real-time question-answering system for content recommendation

Microsoft（微软）

本文提出面向微软MSX销售场景的实时问答内容推荐系统，利用LLM嵌入、提示词工程及双编码器加交叉编码器架构，在数秒内从大型销售内容库中精准推荐相关材料，并已集成至生产环境以提升卖家生产力。

2024-01-04cs.AIcs.IRcs.LG

A Pipeline for Generating, Annotating and Employing Synthetic Data for Real World Question Answering

Filament AI；University of Warwick（华威大学）；The Alan Turing Institute（艾伦·图灵研究所）；Queen Mary University of London（伦敦玛丽女王大学）

Question Answering (QA) is a growing area of research, often used to facilitate the extraction of information from within documents. State-of-the-art QA models are usually pre-trained on domain-general corpora like Wikipedia and thus tend to struggle on out-of-domain documents without fine-tuning. We demonstrate that synthetic domain-specific datasets can be generated easily using domain-general models, while still providing significant improvements to QA performance. We present two new tools for this task: A flexible pipeline for validating the synthetic QA data and training downstream models…

2022-11-30cs.CLcs.LG

Neural Multi-Task Learning for Teacher Question Detection in Online Classrooms

TAL Education Group（好未来教育集团）；Tsinghua University（清华大学）；Michigan State University（密歇根州立大学）

Asking questions is one of the most crucial pedagogical techniques used by teachers in class. It not only offers open-ended discussions between teachers and students to exchange ideas but also provokes deeper student thought and critical analysis. Providing teachers with such pedagogical feedback will remarkably help teachers improve their overall teaching quality over time in classrooms. Therefore, in this work, we build an end-to-end neural framework that automatically detects questions from teachers' audio recordings. Compared with traditional methods, our approach not only avoids cumbersom…

2020-05-16cs.AIcs.CLcs.LG