世界模型 - arXivDaily 专题

2407.20506 2024-07-31 cs.LG cs.AI 82%

Boosting Efficiency in Task-Agnostic Exploration through Causal Knowledge

Yupei Yang, Biwei Huang, Shikui Tu, Lei Xu

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments This paper was accepted by IJCAI'24

2406.17837 2024-06-27 cs.LG cs.AI 82%

Transformer Normalisation Layers and the Independence of Semantic Subspaces

Stephen Menary, Samuel Kaski, Andre Freitas

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

2406.15132 2024-06-24 cs.LG cs.AI 82%

Younger: The First Dataset for Artificial Intelligence-Generated Neural Network Architecture

Zhengxin Yang, Wanling Gao, Luzhou Peng, Yunyou Huang, Fei Tang, Jianfeng Zhan

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments 31 pages, 29 figures, 11 tables

2406.10429 2024-06-18 cs.CV cs.AI 82%

Consistency-diversity-realism Pareto fronts of conditional image generative models

Pietro Astolfi, Marlene Careil, Melissa Hall, Oscar Mañas, Matthew Muckley, Jakob Verbeek, Adriana Romero Soriano, Michal Drozdzal

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

2405.19334 2024-06-11 cs.AI cs.CL cs.CV cs.MM cs.SD 82%

LLMs Meet Multimodal Generation and Editing: A Survey

Yingqing He, Zhaoyang Liu, Jingye Chen, Zeyue Tian, Hongyu Liu, Xiaowei Chi, Runtao Liu, Ruibin Yuan, Yazhou Xing, Wenhai Wang, Jifeng Dai, Yong Zhang, Wei Xue, Qifeng Liu, Yike Guo, Qifeng Chen

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments 52 Pages with 16 Figures, 12 Tables, and 545 References. GitHub Repository at: https://github.com/YingqingHe/Awesome-LLMs-meet-Multimodal-Generation

2405.03878 2024-06-05 cs.LG cs.AI 82%

Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning

Aditya A. Ramesh, Kenny Young, Louis Kirsch, Jürgen Schmidhuber

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments ICML 2024 version

2402.02968 2024-05-28 cs.CV cs.LG 82%

Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives

Sheng Luo, Wei Chen, Wanxin Tian, Rui Liu, Luanxuan Hou, Xiubao Zhang, Haifeng Shen, Ruiqi Wu, Shuyi Geng, Yi Zhou, Ling Shao, Yi Yang, Bojun Gao, Qun Li, Guobin Wu

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments Accepted to IEEE Transactions on Intelligent Vehicles(T-IV). 24 pages, 9 figures, 1 table

2402.02675 2024-05-24 cs.LG cs.AI cs.CR 82%

Verifiable evaluations of machine learning models using zkSNARKs

Tobin South, Alexander Camuto, Shrey Jain, Shayla Nguyen, Robert Mahari, Christian Paquin, Jason Morton, Alex 'Sandy' Pentland

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

2401.03910 2024-01-09 cs.CL cs.AI cs.LG 82%

A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates

Raphaël Millière, Cameron Buckner

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

2309.03886 2023-12-11 cs.CL cs.AI cs.LG 82%

FIND: A Function Description Benchmark for Evaluating Interpretability Methods

Sarah Schwettmann, Tamar Rott Shaham, Joanna Materzynska, Neil Chowdhury, Shuang Li, Jacob Andreas, David Bau, Antonio Torralba

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments 28 pages, 10 figures

Journal ref NeurIPS 2023

2211.13051 2023-10-17 cs.AI cs.LG 82%

Powderworld: A Platform for Understanding Generalization via Rich Task Distributions

Kevin Frans, Phillip Isola

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

2310.05337 2023-10-10 cs.LG cs.CV 82%

What do larger image classifiers memorise?

Michal Lukasik, Vaishnavh Nagarajan, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

2211.14860 2023-08-15 cs.CV cs.AI 82%

Foiling Explanations in Deep Neural Networks

Snir Vitrack Tamam, Raz Lapid, Moshe Sipper

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments Snir Vitrack Tamam and Raz Lapid contributed equally

Journal ref Transactions on Machine Learning Research, 08/2023

2306.01157 2023-06-05 cs.LG cs.AI 82%

Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding

Alizée Pace, Hugo Yèche, Bernhard Schölkopf, Gunnar Rätsch, Guy Tennenholtz

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

2305.11358 2023-05-22 cs.LG cs.MA 82%

Understanding the World to Solve Social Dilemmas Using Multi-Agent Reinforcement Learning

Manuel Rios, Nicanor Quijano, Luis Felipe Giraldo

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments ICLR 2023 - AI4ABM workshop

2304.11104 2023-04-24 cs.AI 82%

Approximate Shielding of Atari Agents for Safe Exploration

Alexander W. Goodall, Francesco Belardinelli

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments Accepted for presentation at the ALA workshop as part of AAMAS 2023

2302.08007 2023-04-14 cs.LG cs.AI cs.AR 82%

With Shared Microexponents, A Little Shifting Goes a Long Way

Bita Rouhani, Ritchie Zhao, Venmugil Elango, Rasoul Shafipour, Mathew Hall, Maral Mesmakhosroshahi, Ankit More, Levi Melnick, Maximilian Golub, Girish Varatkar, Lei Shao, Gaurav Kolhe, Dimitry Melts, Jasmine Klar, Renee L'Heureux, Matt Perry, Doug Burger, Eric Chung, Zhaoxia Deng, Sam Naghshineh, Jongsoo Park, Maxim Naumov

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

2210.00999 2023-02-13 cs.LG cs.AI stat.ML 82%

Latent State Marginalization as a Low-cost Approach for Improving Exploration

Dinghuai Zhang, Aaron Courville, Yoshua Bengio, Qinqing Zheng, Amy Zhang, Ricky T. Q. Chen

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments Accepted by ICLR 2023

2207.12316 2022-08-05 cs.NE cs.AI cs.LG 82%

A Theoretical Framework for Inference and Learning in Predictive Coding Networks

Beren Millidge, Yuhang Song, Tommaso Salvatori, Thomas Lukasiewicz, Rafal Bogacz

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments 21/07/22 initial upload (finally); 03/08/22 revisions

2203.13880 2022-06-20 cs.CV cs.AI 82%

Reinforcement Learning with Action-Free Pre-Training from Videos

Younggyo Seo, Kimin Lee, Stephen James, Pieter Abbeel

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments International Conference on Machine Learning (ICML 2022). Project page: https://sites.google.com/view/rl-apv

2111.12594 2022-03-16 cs.CV cs.LG stat.ML 82%

Conditional Object-Centric Learning from Video

Thomas Kipf, Gamaleldin F. Elsayed, Aravindh Mahendran, Austin Stone, Sara Sabour, Georg Heigold, Rico Jonschkowski, Alexey Dosovitskiy, Klaus Greff

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments Published at ICLR 2022. Project page at https://slot-attention-video.github.io/

2009.01791 2022-02-15 cs.AI cs.IT cs.LG math.IT stat.ML 82%

Action and Perception as Divergence Minimization

Danijar Hafner, Pedro A. Ortega, Jimmy Ba, Thomas Parr, Karl Friston, Nicolas Heess

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments Website: https://danijar.com/apd

2112.06063 2021-12-14 cs.LG cs.AI cs.CR 82%

MedAttacker: Exploring Black-Box Adversarial Attacks on Risk Prediction Models in Healthcare

Muchao Ye, Junyu Luo, Guanjie Zheng, Cao Xiao, Ting Wang, Fenglong Ma

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

2106.08890 2021-06-17 cs.LG cs.AI cs.SE 82%

ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection

Yuanchun Li, Ziqi Zhang, Bingyan Liu, Ziyue Yang, Yunxin Liu

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments ISSTA 2021

1906.09088 2019-12-19 cs.LG math.DS math.OC stat.ML 82%

Meta-Model Framework for Surrogate-Based Parameter Estimation in Dynamical Systems

Žiga Lukšič, Jovan Tanevski, Sašo Džeroski, Ljupčo Todorovski

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

1903.01567 2019-03-06 cs.LG cs.AI cs.NE 82%

Model Primitive Hierarchical Lifelong Reinforcement Learning

Bohan Wu, Jayesh K. Gupta, Mykel J. Kochenderfer

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments 9 pages, 10 figures. Accepted as a full paper at AAMAS 2019

Journal ref International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2019)

1802.10546 2018-06-19 cs.AI cs.LG 82%

Computational Theories of Curiosity-Driven Learning

Pierre-Yves Oudeyer

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments To appear in "The New Science of Curiosity", ed. G. Gordon, Nova Science Publishers

1706.04721 2017-11-02 cs.AI cs.LG 82%

Target Curricula via Selection of Minimum Feature Sets: a Case Study in Boolean Networks

Shannon Fenn, Pablo Moscato

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments Accepted for publication in JMLR issue 18

1508.04159 2015-10-06 cs.PL cs.AI cs.DB cs.RO 82%

Reasoning in complex environments with the SelectScript declarative language

André Dietrich, Sebastian Zug, Luigi Nardi, Jörg Kaiser

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

Comments 15 pages, 7 figures, 6th International Workshop on Domain-Specific Languages and models for ROBotic systems (DSLRob-15)

2606.07303 2026-08-21 cs.LG 版本更新 81%

Bootstrap Theory of Representational Emergence (TBER): Explanatory Insufficiency, Transition Regimes, and the Emergence of New Representational Levels

表征涌现的自举理论：解释不充分性作为表征学习与世界模型的驱动力

Jacques Raynal, Pierre Slangen, Elsa Raynal, Jacques Margerit

机构 * Laboratory of Bioengineering and Nanosciences (LBN), University of Montpellier（生物工程与纳米科学实验室（LBN），蒙彼利埃大学）； EuroMov Digital Health in Motion, University of Montpellier, IMT Mines Alès（EuroMov数字健康运动，蒙彼利埃大学，IMT矿山阿尔勒）； Certified Sophrologist, Sensorimotor Practice, Montpellier, France（认证Sophrologist，运动觉实践，蒙彼利埃，法国）； Emeritus Professor, University of Montpellier（荣誉教授，蒙彼利埃大学）

专题命中通用世界模型：world model(abstract)；world models(abstract)；world model(abstract)；world models(abstract)

AI总结提出表征涌现自举理论（TBER），将解释不充分性视为新表征涌现的积极信号，通过五阶段递归过程驱动表征创新，应用于表征学习、世界模型和科学发现。

Comments Version 4. Major theoretical revision introducing the distinction between manifestations of explanatory insufficiency and resolution regimes (local-corrective, representationally resolutive, and structurally recurrent), together with regime-sensitive diagnosis and closure assessment. Formal mathematical boundary cases have been clarified. 28 references, no figures or tables

1. 通用世界模型 4308 篇

Boosting Efficiency in Task-Agnostic Exploration through Causal Knowledge

Transformer Normalisation Layers and the Independence of Semantic Subspaces

Younger: The First Dataset for Artificial Intelligence-Generated Neural Network Architecture

Consistency-diversity-realism Pareto fronts of conditional image generative models

LLMs Meet Multimodal Generation and Editing: A Survey

Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning

Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives

Verifiable evaluations of machine learning models using zkSNARKs

A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates

FIND: A Function Description Benchmark for Evaluating Interpretability Methods

Powderworld: A Platform for Understanding Generalization via Rich Task Distributions

What do larger image classifiers memorise?

Foiling Explanations in Deep Neural Networks

Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding

Understanding the World to Solve Social Dilemmas Using Multi-Agent Reinforcement Learning

Approximate Shielding of Atari Agents for Safe Exploration

With Shared Microexponents, A Little Shifting Goes a Long Way

Latent State Marginalization as a Low-cost Approach for Improving Exploration

A Theoretical Framework for Inference and Learning in Predictive Coding Networks

Reinforcement Learning with Action-Free Pre-Training from Videos

Conditional Object-Centric Learning from Video

Action and Perception as Divergence Minimization

MedAttacker: Exploring Black-Box Adversarial Attacks on Risk Prediction Models in Healthcare

ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection

Meta-Model Framework for Surrogate-Based Parameter Estimation in Dynamical Systems

Model Primitive Hierarchical Lifelong Reinforcement Learning

Computational Theories of Curiosity-Driven Learning

Target Curricula via Selection of Minimum Feature Sets: a Case Study in Boolean Networks

Reasoning in complex environments with the SelectScript declarative language

Bootstrap Theory of Representational Emergence (TBER): Explanatory Insufficiency, Transition Regimes, and the Emergence of New Representational Levels