大模型推理能力 - arXivDaily 专题

2307.11922 2023-07-25 cs.LG cs.AI cs.CL 67%

Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors

Kolby Nottingham, Yasaman Razeghi, Kyungmin Kim, JB Lanier, Pierre Baldi, Roy Fox, Sameer Singh

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

2306.08640 2023-06-29 cs.CV 67%

AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn

Difei Gao, Lei Ji, Luowei Zhou, Kevin Qinghong Lin, Joya Chen, Zihan Fan, Mike Zheng Shou

专题命中规划推理：reasoning(abstract)；planning(abstract)

Comments Project page: https://showlab.github.io/assistgpt/

2306.13905 2023-06-27 cs.CL cs.AI cs.LG 67%

Spatio-temporal Storytelling? Leveraging Generative Models for Semantic Trajectory Analysis

Shreya Ghosh, Saptarshi Sengupta, Prasenjit Mitra

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 8 pages, 1 figure, Submitted for peer review

2306.11025 2023-06-21 cs.LG cs.AI cs.CL q-fin.ST 67%

Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting

Xinli Yu, Zheng Chen, Yuan Ling, Shujing Dong, Zongyi Liu, Yanbin Lu

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2306.05052 2023-06-09 cs.LG cs.AI cs.CL 67%

Interpretable Medical Diagnostics with Structured Data Extraction by Large Language Models

Aleksa Bisercic, Mladen Nikolic, Mihaela van der Schaar, Boris Delibasic, Pietro Lio, Andrija Petrovic

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2305.05662 2023-06-05 cs.CV 67%

InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language

Zhaoyang Liu, Yinan He, Wenhai Wang, Weiyun Wang, Yi Wang, Shoufa Chen, Qinglong Zhang, Zeqiang Lai, Yang Yang, Qingyun Li, Jiashuo Yu, Kunchang Li, Zhe Chen, Xue Yang, Xizhou Zhu, Yali Wang, Limin Wang, Ping Luo, Jifeng Dai, Yu Qiao

专题命中规划推理：reasoning(abstract)；planning(abstract)

Comments Technical Report

2210.08726 2023-06-01 cs.CL cs.AI cs.IR cs.LG 67%

RARR: Researching and Revising What Language Models Say, Using Language Models

Luyu Gao, Zhuyun Dai, Panupong Pasupat, Anthony Chen, Arun Tejasvi Chaganty, Yicheng Fan, Vincent Y. Zhao, Ni Lao, Hongrae Lee, Da-Cheng Juan, Kelvin Guu

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ACL 2023

2305.12647 2023-05-23 cs.AI cs.CL cs.HC cs.LG 67%

Reflective Linguistic Programming (RLP): A Stepping Stone in Socially-Aware AGI (SocialAGI)

Kevin A. Fischer

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 12 pages

2305.11206 2023-05-22 cs.CL cs.AI cs.LG 67%

LIMA: Less Is More for Alignment

Chunting Zhou, Pengfei Liu, Puxin Xu, Srini Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, Susan Zhang, Gargi Ghosh, Mike Lewis, Luke Zettlemoyer, Omer Levy

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

2305.03653 2023-05-08 cs.IR 67%

Query Expansion by Prompting Large Language Models

Rolf Jagerman, Honglei Zhuang, Zhen Qin, Xuanhui Wang, Michael Bendersky

专题命中规划推理：chain-of-thought(abstract)；CoT(abstract)

Comments 7 pages, 2 figures

2211.04604 2023-04-26 cs.RO cs.AI cs.CL cs.CV cs.LG 67%

StructDiffusion: Language-Guided Creation of Physically-Valid Structures using Unseen Objects

Weiyu Liu, Yilun Du, Tucker Hermans, Sonia Chernova, Chris Paxton

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to Robotics: Science and Systems (RSS) 2023. The previous version appeared in CoRL Workshop on Language and Robot Learning 2022

2303.09031 2023-03-17 cs.CL cs.AI cs.LG 67%

A Picture is Worth a Thousand Words: Language Models Plan from Pixels

Anthony Z. Liu, Lajanugen Logeswaran, Sungryull Sohn, Honglak Lee

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

2302.12367 2023-02-27 cs.CL cs.AI cs.LG 67%

Extracting Victim Counts from Text

Mian Zhong, Shehzaad Dhuliawala, Niklas Stoehr

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Long paper accepted at EACL 2023 main conference

2206.14576 2023-02-22 cs.CL cs.AI cs.LG 67%

Using cognitive psychology to understand GPT-3

Marcel Binz, Eric Schulz

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2205.13349 2023-02-08 cs.CV 67%

Learning What and Where: Disentangling Location and Identity Tracking Without Supervision

Manuel Traub, Sebastian Otte, Tobias Menge, Matthias Karlbauer, Jannik Thümmel, Martin V. Butz

专题命中规划推理：reasoning(abstract)；planning(abstract)

Comments Accepted at ICLR 2023

2207.08192 2022-10-18 cs.RO cs.CV 67%

BusyBot: Learning to Interact, Reason, and Plan in a BusyBoard Environment

Zeyi Liu, Zhenjia Xu, Shuran Song

专题命中规划推理：reasoning(abstract)；planning(abstract)

Comments CoRL 2022 camera-ready; Website: https://busybot.cs.columbia.edu/

2209.11302 2022-09-26 cs.RO cs.AI cs.CL cs.LG 67%

ProgPrompt: Generating Situated Robot Task Plans using Large Language Models

Ishika Singh, Valts Blukis, Arsalan Mousavian, Ankit Goyal, Danfei Xu, Jonathan Tremblay, Dieter Fox, Jesse Thomason, Animesh Garg

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

2205.15473 2022-06-01 cs.RO 67%

Free-Space Ellipsoid Graphs for Multi-Agent Target Monitoring

Aaron Ray, Alyssa Pierson, Daniela Rus

专题命中规划推理：reasoning(abstract)；planning(abstract)

Comments IEEE Intl. Conf. on Robotics and Automation (ICRA) 2022

2110.10237 2021-10-22 cs.RO 67%

Stochastic Assignment for Deploying Multiple Marsupial Robots

Chris, Lee, Graeme Best, Geoffrey A. Hollinger

专题命中规划推理：reasoning(abstract)；planning(abstract)

Journal ref Proc. IEEE International Symposium on Multi-Robot and Multi-Agent Systems (MRS) 2021

2109.04101 2021-09-10 cs.LG cs.AI cs.CL 67%

TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting

Haohai Sun, Jialun Zhong, Yunpu Ma, Zhen Han, Kun He

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments EMNLP 2021

1604.05508 2021-04-13 cs.RO cs.SE 67%

Intelligent Agent-Based Stimulation for Testing Robotic Software in Human-Robot Interactions

Dejanira Araiza-Illan, Anthony G. Pipe, Kerstin Eder

专题命中规划推理：reasoning(abstract)；planning(abstract)

2010.09054 2020-12-15 cs.MA 67%

Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences

Raphael Köster, Kevin R. McKee, Richard Everett, Laura Weidinger, William S. Isaac, Edward Hughes, Edgar A. Duéñez-Guzmán, Thore Graepel, Matthew Botvinick, Joel Z. Leibo

专题命中规划推理：reasoning(abstract)；planning(abstract)

2011.04548 2020-11-10 cs.AI cs.CL cs.LG 67%

Artificial Intelligence Decision Support for Medical Triage

Chiara Marchiori, Douglas Dykeman, Ivan Girardi, Adam Ivankay, Kevin Thandiackal, Mario Zusag, Andrea Giovannini, Daniel Karpati, Henri Saenz

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 10 pages, 5 figures, accepted to AMIA 2020

2010.10363 2020-10-26 cs.CL cs.AI cs.LG 67%

Bootleg: Chasing the Tail with Self-Supervised Named Entity Disambiguation

Laurel Orr, Megan Leszczynski, Simran Arora, Sen Wu, Neel Guha, Xiao Ling, Christopher Re

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

2001.03436 2020-01-13 cs.LG cs.AI cs.CL stat.ML 67%

Debate Dynamics for Human-comprehensible Fact-checking on Knowledge Graphs

Marcel Hildebrandt, Jorge Andres Quintero Serna, Yunpu Ma, Martin Ringsquandl, Mitchell Joblin, Volker Tresp

专题命中规划推理：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments AAAI 2019 Fall Symposium Series. arXiv admin note: substantial text overlap with arXiv:2001.00461

1909.04812 2019-09-20 cs.RO 67%

Proceedings of the AI-HRI Symposium at AAAI-FSS 2019

Justin W. Hart, Nick DePalma, Richard G. Freedman, Luca Iocchi, Matteo Leonetti, Katrin Lohan, Ross Mead, Emmanuel Senft, Jivko Sinapov, Elin A. Topp, Tom Williams

专题命中规划推理：reasoning(abstract)；planning(abstract)

Comments HTML file with clickable links to papers - All papers have been reviewed by at least two reviewers in a single blind fashion - Symposium website: https://ai-hri.github.io/2019/

1708.00133 2018-12-07 cs.CL cs.AI cs.LG 67%

Grounding Language for Transfer in Deep Reinforcement Learning

Karthik Narasimhan, Regina Barzilay, Tommi Jaakkola

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments JAIR 2018

1804.07855 2018-09-25 cs.CL cs.AI cs.LG 67%

Subgoal Discovery for Hierarchical Dialogue Policy Learning

Da Tang, Xiujun Li, Jianfeng Gao, Chong Wang, Lihong Li, Tony Jebara

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 11 pages, 6 figures, EMNLP 2018

1801.04223 2018-01-15 cs.IT math.IT 67%

Machine Intelligence Techniques for Next-Generation Context-Aware Wireless Networks

Tadilo Endeshaw Bogale, Xianbin Wang, Long Bao Le

专题命中规划推理：reasoning(abstract)；planning(abstract)

Comments ITU Special Issue N.1 The impact of Artificial Intelligence (AI) on communication networks and services, (To appear)

1704.03084 2017-07-25 cs.CL cs.AI cs.LG 67%

Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning

Baolin Peng, Xiujun Li, Lihong Li, Jianfeng Gao, Asli Celikyilmaz, Sungjin Lee, Kam-Fai Wong

专题命中规划推理：planning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 12 pages, 8 figures

1. 规划推理 11088 篇

Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors

AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn

Spatio-temporal Storytelling? Leveraging Generative Models for Semantic Trajectory Analysis

Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting

Interpretable Medical Diagnostics with Structured Data Extraction by Large Language Models

InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language

RARR: Researching and Revising What Language Models Say, Using Language Models

Reflective Linguistic Programming (RLP): A Stepping Stone in Socially-Aware AGI (SocialAGI)

LIMA: Less Is More for Alignment

Query Expansion by Prompting Large Language Models

StructDiffusion: Language-Guided Creation of Physically-Valid Structures using Unseen Objects

A Picture is Worth a Thousand Words: Language Models Plan from Pixels

Extracting Victim Counts from Text

Using cognitive psychology to understand GPT-3

Learning What and Where: Disentangling Location and Identity Tracking Without Supervision

BusyBot: Learning to Interact, Reason, and Plan in a BusyBoard Environment

ProgPrompt: Generating Situated Robot Task Plans using Large Language Models

Free-Space Ellipsoid Graphs for Multi-Agent Target Monitoring

Stochastic Assignment for Deploying Multiple Marsupial Robots

TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting

Intelligent Agent-Based Stimulation for Testing Robotic Software in Human-Robot Interactions

Model-free conventions in multi-agent reinforcement learning with heterogeneous preferences

Artificial Intelligence Decision Support for Medical Triage

Bootleg: Chasing the Tail with Self-Supervised Named Entity Disambiguation

Debate Dynamics for Human-comprehensible Fact-checking on Knowledge Graphs

Proceedings of the AI-HRI Symposium at AAAI-FSS 2019

Grounding Language for Transfer in Deep Reinforcement Learning

Subgoal Discovery for Hierarchical Dialogue Policy Learning

Machine Intelligence Techniques for Next-Generation Context-Aware Wireless Networks

Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning