AI Agent

Learning to Identify Critical States for Reinforcement Learning from Videos

Haozhe Liu, Mingchen Zhuge, Bing Li, Yuhui Wang, Francesco Faccio, Bernard Ghanem, Jürgen Schmidhuber

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Comments This paper was accepted to ICCV23

LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation

Leigang Qu, Shengqiong Wu, Hao Fei, Liqiang Nie, Tat-Seng Chua

专题命中 软件智能体 ：planning(abstract)；分类 cs.AI

Comments Accepted by ACM MM 2023

Expeditious Saliency-guided Mix-up through Random Gradient Thresholding

Minh-Long Luu, Zeyi Huang, Eric P. Xing, Yong Jae Lee, Haohan Wang

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Comments Accepted Long paper at 2nd Practical-DL Workshop at AAAI 2023

Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks

Tian Yu Liu, Yu Yang, Baharan Mirzasoleiman

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

Comments Code available at: https://github.com/tianyu139/friendly-noise

Context-Aware Timewise VAEs for Real-Time Vehicle Trajectory Prediction

Pei Xu, Jean-Bernard Hayet, Ioannis Karamouzas

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

Knowledge-Driven Robot Program Synthesis from Human VR Demonstrations

Benjamin Alt, Franklin Kenghagho Kenfack, Andrei Haidu, Darko Katic, Rainer Jäkel, Michael Beetz

专题命中 软件智能体 ：planning(abstract)；分类 cs.AI

Comments 10 pages, 11 figures, accepted at the 20th International Conference on Principles of Knowledge Representation and Reasoning (KR2023, https://kr.org/KR2023)

The Dormant Neuron Phenomenon in Deep Reinforcement Learning

Ghada Sokar, Rishabh Agarwal, Pablo Samuel Castro, Utku Evci

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

Comments Oral at ICML 2023

ScaffML: A Quantum Behavioral Interface Specification Language for Scaffold

Tiancheng Jin, Jianjun Zhao

专题命中 软件智能体 ：workflow(abstract)；分类 cs.SE

Comments This paper will be appeared in the proceedings of the 2023 IEEE International Conference on Quantum Software (QSW 2023), July 2-8, 2023

Synthesizing a Progression of Subtasks for Block-Based Visual Programming Tasks

Alperen Tercan, Ahana Ghosh, Hasan Ferit Eniser, Maria Christakis, Adish Singla

专题命中 软件智能体 ：AI agent(abstract)；分类 cs.AI

The Impact of a Continuous Integration Service on the Delivery Time of Merged Pull Requests

João Helis Bernardo, Daniel Alencar da Costa, Uirá Kulesza, Christoph Treude

专题命中 软件智能体 ：planning(abstract)；分类 cs.SE

A Network Perspective on the Influence of Code Review Bots on the Structure of Developer Collaborations

Leonore Röseler, Ingo Scholtes, Christoph Gote

专题命中 软件智能体 ：workflow(abstract)；分类 cs.SE

Comments 8 pages

Pythia: A Customizable Hardware Prefetching Framework Using Online Reinforcement Learning

Rahul Bera, Konstantinos Kanellopoulos, Anant V. Nori, Taha Shahroodi, Sreenivas Subramoney, Onur Mutlu

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

SC-ML: Self-supervised Counterfactual Metric Learning for Debiased Visual Question Answering

Xinyao Shu, Shiyang Yan, Xu Yang, Ziheng Wu, Zhongfeng Chen, Zhenyu Lu

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Yes but.. Can ChatGPT Identify Entities in Historical Documents?

Carlos-Emiliano González-Gallardo, Emanuela Boros, Nancy Girdhar, Ahmed Hamdi, Jose G. Moreno, Antoine Doucet

专题命中 软件智能体 ：agent(abstract)；分类 cs.CL

Comments 5 pages, accepted to JCDL2023

InferFix: End-to-End Program Repair with LLMs

Matthew Jin, Syed Shahriar, Michele Tufano, Xin Shi, Shuai Lu, Neel Sundaresan, Alexey Svyatkovskiy

专题命中 软件智能体 ：workflow(abstract)；分类 cs.SE

Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward

Yanjiang Guo, Jingyue Gao, Zheng Wu, Chengming Shi, Jianyu Chen

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Comments 11 pages, 5 figures, CoRL 2022

A Multiplicative Value Function for Safe and Efficient Reinforcement Learning

Nick Bührer, Zhejun Zhang, Alexander Liniger, Fisher Yu, Luc Van Gool

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

Comments Repository available at https://github.com/nikeke19/Safe-Mult-RL

Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems

Yihao Feng, Shentao Yang, Shujian Zhang, Jianguo Zhang, Caiming Xiong, Mingyuan Zhou, Huan Wang

专题命中 软件智能体 ：agent(abstract)；分类 cs.CL

Comments Published as a conference paper at ICLR 2023

TorchFL: A Performant Library for Bootstrapping Federated Learning Experiments

Vivek Khimani, Shahin Jabbari

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

Comments 21 pages, 15 figures, 4 tables. This manuscript serves as external documentation for https://github.com/vivekkhimani/torchfl

Exploration and Incentives in Reinforcement Learning

Max Simchowitz, Aleksandrs Slivkins

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

Just-in-Time Code Duplicates Extraction

Eman Abdullah AlOmar, Anton Ivanov, Zarina Kurbatova, Yaroslav Golubev, Mohamed Wiem Mkaouer, Ali Ouni, Timofey Bryksin, Le Nguyen, Amit Kini, Aditya Thakur

专题命中 软件智能体 ：workflow(abstract)；分类 cs.SE

Comments 32 pages, 9 figures

Act for Your Duties but Maintain Your Rights

Shufang Zhu, Giuseppe De Giacomo

专题命中 软件智能体 ：agent(abstract)；分类 cs.AI

Journal ref International Conference on Principles of Knowledge Representation and Reasoning (KR), 2022

Automatic Differentiation of Programs with Discrete Randomness

Gaurav Arya, Moritz Schauer, Frank Schäfer, Chris Rackauckas

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

Comments In Proceedings of NeurIPS 2022

Toward Self-learning End-to-End Task-Oriented Dialog Systems

Xiaoying Zhang, Baolin Peng, Jianfeng Gao, Helen Meng

专题命中 软件智能体 ：agent(abstract)；分类 cs.CL

A Simple Decentralized Cross-Entropy Method

Zichen Zhang, Jun Jin, Martin Jagersand, Jun Luo, Dale Schuurmans

专题命中 软件智能体 ：planning(abstract)；分类 cs.LG

Comments NeurIPS 2022. The last two authors advised equally

The Unexplored Treasure Trove of Phabricator Code Review

Gunnar Kudrjavets, Nachiappan Nagappan, Ayushi Rastogi

专题命中 软件智能体 ：tool use(abstract)；分类 cs.SE

Comments 5 pages. To be published in Proceedings of MSR '22: Proceedings of the 19th International Conference on Mining Software Repositories (MSR 2022). ACM, New York, NY, USA

Chemoreception and chemotaxis of a three-sphere swimmer

Stevens Paz, Roberto F. Ausas, Juan P. Carbajal, Gustavo C. Buscaglia

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

Comments 20 pages, 13 figures. Submitted to "Communications in Nonlinear Science and Numerical Simulation"

Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction

Masha Itkina, Mykel J. Kochenderfer

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG

Comments Conference on Robot Learning (CoRL) 2022, 15 pages, 4 figures

Learning to Answer Multilingual and Code-Mixed Questions

Deepak Gupta

专题命中 软件智能体 ：agent(abstract)；分类 cs.CL

Comments PhD Thesis

Conformal Isometry of Lie Group Representation in Recurrent Network of Grid Cells

Dehong Xu, Ruiqi Gao, Wen-Hao Zhang, Xue-Xin Wei, Ying Nian Wu

专题命中 软件智能体 ：agent(abstract)；分类 cs.LG