AI Agent - arXivDaily 专题

2207.00738 2022-07-05 cs.CV cs.RO 50%

Golfer: Trajectory Prediction with Masked Goal Conditioning MnM Network

Xiaocheng Tang, Soheil Sadeghi Eshkevari, Haoyu Chen, Weidan Wu, Wei Qian, Xiaoming Wang

专题命中记忆与上下文管理：agent(abstract)

Comments A preliminary version is presented at CVPR 2022 Workshop on Autonomous Driving https://cvpr2022.wad.vision

2004.11856 2022-07-05 eess.SY cs.MA cs.RO cs.SY 50%

Decentralized linear quadratic systems with major and minor agents and non-Gaussian noise

Mohammad Afshari, Aditya Mahajan

专题命中记忆与上下文管理：agent(abstract)

Comments 16 pages, submitted to the IEEE Transactions on Automatic Control

2207.00255 2022-07-04 cs.CV cs.RO 50%

Trajectory Forecasting on Temporal Graphs

Görkay Aydemir, Adil Kaan Akan, Fatma Güney

专题命中记忆与上下文管理：agent(abstract)

1906.03901 2022-06-30 math.OC 50%

Time-Optimal Control Problem With State Constraints In A Time-Periodic Flow Field

Roman Chertovskih, Nathalie T. Khalil, Fernando Lobo Pereira

专题命中记忆与上下文管理：planning(abstract)

Comments 15 pages

Journal ref In: Jaćimović, M., Khachay, M., Malkova, V., Posypkin, M. (eds) Optimization and Applications. OPTIMA 2019. Communications in Computer and Information Science, vol 1145. Springer (2020)

2112.10160 2022-06-28 physics.soc-ph 50%

Discerning media bias within a network of political allies and opponents: the idealized example of a biased coin

Nicholas Kah Yean Low, Andrew Melatos

专题命中记忆与上下文管理：agent(abstract)

Comments 38 pages, 30 figures, 8 tables. Published in Physica A

2206.11341 2022-06-24 math.OC 50%

Stagewise Newton Method for Dynamic Game Control with Imperfect State Observation

Armand Jordana, Bilal Hammoud, Justin Carpentier, Ludovic Righetti

专题命中记忆与上下文管理：planning(abstract)

Journal ref IEEE Control Systems Letters, 2022

2206.09862 2022-06-22 math.PR math-ph math.MP 50%

Propagation of chaos for a stochastic particle system modelling epidemics

Alessandro Ciallella, Mario Pulvirenti, Sergio Simonella

专题命中记忆与上下文管理：agent(abstract)

2206.09285 2022-06-22 math.OC cs.SY eess.SY 50%

Q-linear Convergence of Distributed Optimization with Barzilai-Borwein Step Sizes

Iyanuoluwa Emiola

专题命中记忆与上下文管理：agent(abstract)

2206.09089 2022-06-22 cs.CV 50%

A Dynamic Data Driven Approach for Explainable Scene Understanding

Zachary A Daniels, Dimitris Metaxas

专题命中记忆与上下文管理：agent(abstract)

Comments Unpublished draft of book chapter

2003.13947 2022-06-22 cs.CV 50%

SS-IL: Separated Softmax for Incremental Learning

Hongjoon Ahn, Jihwan Kwak, Subin Lim, Hyeonsu Bang, Hyojun Kim, Taesup Moon

专题命中记忆与上下文管理：agent(abstract)

2010.03897 2022-06-17 cs.CV 50%

BGM: Building a Dynamic Guidance Map without Visual Images for Trajectory Prediction

Beihao Xia, Conghao Wong, Heng Li, Shiming Chen, Qinmu Peng, Xinge You

专题命中记忆与上下文管理：agent(abstract)

2206.05712 2022-06-14 cs.CV 50%

Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Prediction

Lihuan Li, Maurice Pagnucco, Yang Song

专题命中记忆与上下文管理：planning(abstract)

Comments This paper has been accepted by CVPR 2022. Reference: Li, L., Pagnucco, M. and Song, Y., 2022. Graph-Based Spatial Transformer With Memory Replay for Multi-Future Pedestrian Trajectory Prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 2231-2241)

2109.11648 2022-06-14 math.OC 50%

Decentralized Control of Two Agents with Nested Accessible Information

Aditya Dave, Nishanth Venkatesh, Andreas A. Malikopoulos

专题命中记忆与上下文管理：agent(abstract)

Journal ref Proceedings of 2022 American Control Conference (ACC), pp. 3423-3430, 2022

2205.14937 2022-05-31 cs.DC 50%

Gathering despite a linear number of weakly Byzantine agents

Jion Hirose, Junya Nakamura, Fukuhito Ooshita, Michiko Inoue

专题命中记忆与上下文管理：agent(abstract)

Comments 29 pages, 2 figures, 2 tables, and 6 pseudo-codes

2205.14022 2022-05-30 cs.CV 50%

Future Transformer for Long-term Action Anticipation

Dayoung Gong, Joonseok Lee, Manjin Kim, Seong Jong Ha, Minsu Cho

专题命中记忆与上下文管理：agent(abstract)

Comments Accepted to CVPR 2022

2204.02540 2022-05-18 astro-ph.EP 50%

Refinement of the convex shape model and tumbling spin state of (99942) Apophis using the 2020-2021 apparition data

H. -J. Lee, M. -J. Kim, A. Marciniak, D. -H. Kim, H. -K. Moon, Y. -J. Choi, S. Zoła, J. Chatelain, T. A. Lister, E. Gomez, S. Greenstreet, A. Pál, R. Szakáts, N. Erasmus, R. Lees, P. Janse van Rensburg, W. Ogłoza, M. Dróżdż, M. Żejmo, K. Kamiński, M. K. Kamińska, R. Duffard, D. -G. Roh, H. -S. Yim, T. Kim, S. Mottola, F. Yoshida, D. E. Reichart, E. Sonbas, D. B. Caton, M. Kaplan, O. Erece, H. Yang

专题命中记忆与上下文管理：planning(abstract)

Comments 14 pages, 5 figures; Accepted for publication on Astronomy & Astrophysics

Journal ref A&A 661, L3 (2022)

2205.07481 2022-05-17 cs.RO 50%

Bridging Sim2Real Gap Using Image Gradients for the Task of End-to-End Autonomous Driving

Unnikrishnan R Nair, Sarthak Sharma, Udit Singh Parihar, Midhun S Menon, Srikanth Vidapanakal

专题命中记忆与上下文管理：agent(abstract)

2107.07597 2022-05-17 q-bio.SC 50%

Coarse-grained Stochastic Model of Myosin-Driven Vesicles into Dendritic Spines

Youngmin Park, Prashant Singh, Thomas G. Fai

专题命中记忆与上下文管理：agent(abstract)

Comments 33 pages, 10 figures

Journal ref SIAM J. Appl. Mat., 82(3), 793-820, 2022

2205.06728 2022-05-16 physics.chem-ph cond-mat.stat-mech 50%

Sample size dependence of tagged molecule dynamics in steady-state networks with bimolecular reactions: Cycle times of a light-driven pump

Daniele Asnicar, Emanuele Penocchio, Diego Frezzato

专题命中记忆与上下文管理：agent(abstract)

Comments 13 pages, 5 figures, 2 tables

Journal ref J. Chem. Phys. 156, 184116 (2022)

2205.04347 2022-05-10 q-bio.NC 50%

A neural network model for timing control with reinforcement

Jing Wang, Yousuf El-Jayyousi, Ilker Ozden

专题命中记忆与上下文管理：agent(abstract)

Comments submitted to Frontiers in Computational Neuroscience

2205.03654 2022-05-10 cs.RO cs.CV 50%

Towards Robust 3D Object Recognition with Dense-to-Sparse Deep Domain Adaptation

Prajval Kumar Murali, Cong Wang, Ravinder Dahiya, Mohsen Kaboli

专题命中记忆与上下文管理：autonomous agent(abstract)

2104.01385 2022-05-03 eess.SY cs.SY 50%

A Specification-Guided Framework for Temporal Logic Control of Nonlinear Systems

Yinan Li, Zhibing Sun, Jun Liu

专题命中记忆与上下文管理：planning(abstract)

Comments To appear in IEEE Transactions on Automatic Control

2112.05121 2022-04-28 cs.CV 50%

Self-Supervised Keypoint Discovery in Behavioral Videos

Jennifer J. Sun, Serim Ryou, Roni Goldshmid, Brandon Weissbourd, John Dabiri, David J. Anderson, Ann Kennedy, Yisong Yue, Pietro Perona

专题命中记忆与上下文管理：agent(abstract)

Comments CVPR 2022. Code: https://github.com/neuroethology/BKinD Project page: https://sites.google.com/view/b-kind

2001.00937 2022-04-25 eess.SY cs.SY 50%

Resilient Multi-Dimensional Consensus in Adversarial Environment

Jiaqi Yan, Xiuxian Li, Yilin Mo, Changyun Wen

专题命中记忆与上下文管理：agent(abstract)

2204.07491 2022-04-18 cs.IT cs.DC cs.DM math.IT stat.ML 50%

Distributed Reconstruction of Noisy Pooled Data

Max Hahn-Klimroth, Dominik Kaaser

专题命中记忆与上下文管理：agent(abstract)

Comments Accepted at 42nd IEEE International Conference on Distributed Computing Systems (ICDCS)

2204.07315 2022-04-18 cs.MA 50%

Machine Learning Approaches to Automated Mechanism Design for Public Project Problem

Guanhua Wang

专题命中记忆与上下文管理：agent(abstract)

Comments Phd Thesis

1911.07314 2022-04-18 math.OC 50%

Dynamic Programming Principles for Mean-Field Controls with Learning

Haotian Gu, Xin Guo, Xiaoli Wei, Renyuan Xu

专题命中记忆与上下文管理：agent(abstract)

2204.05517 2022-04-13 eess.SY cs.MA cs.SY 50%

A Finite-State Fixed-Corridor Model for UAS Traffic Management

Hamid Emadi, Ella Atkins, Hossein Rastgoftar

专题命中记忆与上下文管理：planning(abstract)

2204.00656 2022-04-05 cs.CV 50%

Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes

Samrudhdhi B. Rangrej, Chetan L. Srinidhi, James J. Clark

专题命中记忆与上下文管理：agent(abstract)

Comments Accepted to CVPR 2022

2104.14539 2022-03-31 quant-ph 50%

Model-Free Quantum Control with Reinforcement Learning

V. V. Sivak, A. Eickbusch, H. Liu, B. Royer, I. Tsioutsios, M. H. Devoret

专题命中记忆与上下文管理：agent(abstract)

Journal ref Phys. Rev. X 12, 011059 (2022)

1. 记忆与上下文管理 4758 篇

Golfer: Trajectory Prediction with Masked Goal Conditioning MnM Network

Decentralized linear quadratic systems with major and minor agents and non-Gaussian noise

Trajectory Forecasting on Temporal Graphs

Time-Optimal Control Problem With State Constraints In A Time-Periodic Flow Field

Discerning media bias within a network of political allies and opponents: the idealized example of a biased coin

Stagewise Newton Method for Dynamic Game Control with Imperfect State Observation

Propagation of chaos for a stochastic particle system modelling epidemics

Q-linear Convergence of Distributed Optimization with Barzilai-Borwein Step Sizes

A Dynamic Data Driven Approach for Explainable Scene Understanding

SS-IL: Separated Softmax for Incremental Learning

BGM: Building a Dynamic Guidance Map without Visual Images for Trajectory Prediction

Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Prediction

Decentralized Control of Two Agents with Nested Accessible Information

Gathering despite a linear number of weakly Byzantine agents

Future Transformer for Long-term Action Anticipation

Refinement of the convex shape model and tumbling spin state of (99942) Apophis using the 2020-2021 apparition data

Bridging Sim2Real Gap Using Image Gradients for the Task of End-to-End Autonomous Driving

Coarse-grained Stochastic Model of Myosin-Driven Vesicles into Dendritic Spines

Sample size dependence of tagged molecule dynamics in steady-state networks with bimolecular reactions: Cycle times of a light-driven pump

A neural network model for timing control with reinforcement

Towards Robust 3D Object Recognition with Dense-to-Sparse Deep Domain Adaptation

A Specification-Guided Framework for Temporal Logic Control of Nonlinear Systems

Self-Supervised Keypoint Discovery in Behavioral Videos

Resilient Multi-Dimensional Consensus in Adversarial Environment

Distributed Reconstruction of Noisy Pooled Data

Machine Learning Approaches to Automated Mechanism Design for Public Project Problem

Dynamic Programming Principles for Mean-Field Controls with Learning

A Finite-State Fixed-Corridor Model for UAS Traffic Management

Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes

Model-Free Quantum Control with Reinforcement Learning