7 Papers & Radios | 李德毅院士认知物理学前瞻性观点论文;AI从零开始学会玩我的世界
本周论文包括 李德毅院士前瞻性观点论文:《认知物理学 —— 薛定谔、图灵和维纳的启示和超越》;AI 从零开始学会玩《我的世界》,DeepMind AI 通用化取得突破。
目录:
1. STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing 2. Cell-type-specific prediction of 3D chromatin organization enables high-throughput in silico genetic screening 3. Cognitive Physics - The Enlightenment by Schrödinger, Turing, Wiener and Beyond 4. Performance of ChatGPT on USMLE: Potential for AI-Assisted Medical Education Using Large Language Models 5. Mastering Diverse Domains through World Models 6. ParkPredict+: Multimodal Intent and Motion Prediction for Vehicles in Parking Lots with CNN and Transformer 7. ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders 8. ArXiv Weekly Radiostation:NLP、CV、ML 更多精选论文(附音频)
论文 1:STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing
- 作者:Zefeng Cai
- 论文地址:https://arxiv.org/pdf/2210.11888.pdf
论文 2:Cell-type-specific prediction of 3D chromatin organization enables high-throughput in silico genetic screening
- 作者:Jimin Tan 等
- 论文地址:https://www.nature.com/articles/s41587-022-01612-8
论文 3:Cognitive Physics - The Enlightenment by Schrödinger, Turing, Wiener and Beyond
- 作者:DEYI LI
- 论文地址:https://spj.science.org/doi/10.34133/icomputing.0009
论文 4:Performance of ChatGPT on USMLE: Potential for AI-Assisted Medical Education Using Large Language Models
- 作者:Tiffany H. Kung 等
- 论文地址:https://www.medrxiv.org/content/10.1101/2022.12.19.22283643v2
但是近期有一篇论文居然在作者一栏明确署名 ChatGPT,这是怎么回事?这篇论文是发表在医学研究论文平台 medRxiv 上的《Performance of ChatGPT on USMLE: Potential for AI-Assisted Medical Education Using Large Language Models》,ChatGPT 是论文的第三作者。
论文 5:Mastering Diverse Domains through World Models
- 作者:Danijar Hafner 等
- 论文地址:https://arxiv.org/abs/2301.04104v1
DreamerV3 符合的领域包括连续和离散动作、视觉和低维输入、2D 和 3D 世界、不同的数据量、奖励频率和奖励等级。值得一提的是,DreamerV3 是第一个在没有人类数据或主动教育的情况下从零开始在《我的世界》(Minecraft)中收集钻石的算法。研究人员表示,这样的通用算法可以使强化学习得到广泛应用,并有望扩展到硬决策问题。
论文 6:ParkPredict+: Multimodal Intent and Motion Prediction for Vehicles in Parking Lots with CNN and Transformer
- 作者:Xu Shen 等
- 论文地址:https://arxiv.org/abs/2204.10777
论文 7:ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
- 作者:Sanghyun Woo 等
- 论文地址:https://arxiv.org/pdf/2301.00808v1.pdf
ArXiv Weekly Radiostation 机器之心联合由楚航、罗若天发起的ArXiv Weekly Radiostation,在 7 Papers 的基础上,精选本周更多重要论文,包括NLP、CV、ML领域各 10 篇精选,并提供音频形式的论文摘要简介,详情如下:
本周 10 篇 NLP 精选论文是:
1. Improving And Analyzing Neural Speaker Embeddings for ASR. (from Hermann Ney) 2. Dual Learning for Large Vocabulary On-Device ASR. (from Kyunghyun Cho) 3. Structured Case-based Reasoning for Inference-time Adaptation of Text-to-SQL parsers. (from Soumen Chakrabarti, Sunita Sarawagi) 4. NarrowBERT: Accelerating Masked Language Model Pretraining and Inference. (from Noah A. Smith) 5. Multilingual Entity and Relation Extraction from Unified to Language-specific Training. (from Jian Yang) 6. Facilitating Contrastive Learning of Discourse Relational Senses by Exploiting the Hierarchy of Sense Relations. (from Bonnie Webber) 7. A Cognitive Evaluation of Instruction Generation Agents tl;dr They Need Better Theory-of-Mind Capabilities. (from Hal Daumé III) 8. ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation Generalization. (from Yu Sun) 9. Scaling Laws for Generative Mixed-Modal Language Models. (from Luke Zettlemoyer) 10. A Multi-Modal Geographic Pre-Training Method. (from Xin Li)
本周 10 篇 CV 精选论文是:
1. Dynamic Grained Encoder for Vision Transformers. (from Jian Sun, Nanning Zheng) 2. Accidental Light Probes. (from Richard Szeliski, Noah Snavely) 3. CARD: Semantic Segmentation with Efficient Class-Aware Regularized Decoder. (from Liang Chen) 4. In Defense of Structural Symbolic Representation for Video Event-Relation Prediction. (from Shih-Fu Chang) 5. Benchmarking Robustness in Neural Radiance Fields. (from Alan Yuille) 6. Edge Preserving Implicit Surface Representation of Point Clouds. (from Xiaogang Wang, Liang Wang) 7. Domain Expansion of Image Generators. (from Jun-Yan Zhu, Daniel Cohen-Or, Eli Shechtman) 8. Pix2Map: Cross-modal Retrieval for Inferring Street Maps from Images. (from Deva Ramanan) 9. TarViS: A Unified Approach for Target-based Video Segmentation. (from Deva Ramanan, Bastian Leibe) 10. Few-shot Semantic Segmentation with Support-induced Graph Convolutional Network. (from Yang Gao)
本周 10 篇 ML 精选论文是:
1. Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning. (from Bernhard Schölkopf) 2. Online Hyperparameter Optimization for Class-Incremental Learning. (from Bernt Schiele) 3. Does compressing activations help model parallel training?. (from Eric P. Xing) 4. ExcelFormer: A Neural Network Surpassing GBDTs on Tabular Data. (from Jian Wu) 5. Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching. (from Honglak Lee) 6. A Dietary Nutrition-aided Healthcare Platform via Effective Food Recognition on a Localized Singaporean Food Dataset. (from Beng Chin Ooi) 7. Federated Learning and Blockchain-enabled Fog-IoT Platform for Wearables in Predictive Healthcare. (from Konstantinos Plataniotis) 8. Learning Symbolic Representations for Reinforcement Learning of Non-Markovian Behavior. (from Sheila A. McIlraith) 9. Architect, Regularize and Replay (ARR): a Flexible Hybrid Approach for Continual Learning. (from Davide Maltoni) 10. Adversarial training with informed data selection. (from Pascal Frossard)
© THE END 转载请联系本公众号获得授权 投稿或寻求报道:[email protected]