Explanipedia

Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents Open

Yifei Zhou, Qianqian Yang, Kaixiang Lin, Min Bai, Xiong Zhou , et al. · 2024

The vision of a broadly capable and goal-directed agent, such as an Internet-browsing agent in the digital world and a household humanoid in the physical world, has rapidly advanced, thanks to the generalization capability of foundation mo…

Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk Open

Dennis Ulmer, Elman Mansimov, Kaixiang Lin, Justin Sun, Xibin Gao , et al. · 2024

Large language models (LLMs) are powerful dialogue agents, but specializing them towards fulfilling a specific function can be challenging. Instructing tuning, i.e. tuning models on instruction and sample responses generated by humans (Ouy…

A Unified Linear Speedup Analysis of Federated Averaging and Nesterov FedAvg Open

Zhaonan Qu, Kaixiang Lin, Zhaojian Li, Jiayu Zhou, Zhengyuan Zhou · 2023

Federated learning (FL) learns a model jointly from a set of participating devices without sharing each other’s privately held data. The characteristics of non-i.i.d. data across the network, low device participation, high communication co…

Transfer Learning in Deep Reinforcement Learning: A Survey Open

Zhuangdi Zhu, Kaixiang Lin, Anil K. Jain, Jiayu Zhou · 2023

Reinforcement learning is a learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in reinforcement learning upon the fast development of deep neural networks. Along with the prom…

Automated Few-shot Classification with Instruction-Finetuned Language Models Open

Rami Aly, Xingjian Shi, Kaixiang Lin, Aston Zhang, Andrew Gordon Wilson · 2023

A particularly successful class of approaches for few-shot learning combines language models with prompts -- hand-crafted task descriptions that complement data samples. However, designing prompts by hand for each task commonly requires do…

Automated Few-Shot Classification with Instruction-Finetuned Language Models Open

Rami Aly, Xingjian Shi, Kaixiang Lin, Aston Zhang, Andrew Gordon Wilson · 2023

A particularly successful class of approaches for few-shot learning combines language models with prompts - hand-crafted task descriptions that complement data samples. However, designing prompts by hand for each task commonly requires dom…

Parameter and Data Efficient Continual Pre-training for Robustness to Dialectal Variance in Arabic Open

Soumajyoti Sarkar, Kaixiang Lin, Sailik Sengupta, Leonard Lausen, Sheng Zha , et al. · 2022

The use of multilingual language models for tasks in low and high-resource languages has been a success story in deep learning. In recent times, Arabic has been receiving widespread attention on account of its dialectal variance. While pri…

CH-MARL: A Multimodal Benchmark for Cooperative, Heterogeneous Multi-Agent Reinforcement Learning Open

Vasu Sharma, Prasoon Goyal, Kaixiang Lin, Govind Thattai, Qiaozi Gao , et al. · 2022

We propose a multimodal (vision-and-language) benchmark for cooperative and heterogeneous multi-agent learning. We introduce a benchmark multimodal dataset with tasks involving collaboration between multiple simulated heterogeneous robots …

DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following Open

Xiaofeng Gao, Qiaozi Gao, Ran Gong, Kaixiang Lin, Govind Thattai , et al. · 2022

Language-guided Embodied AI benchmarks requiring an agent to navigate an environment and manipulate objects typically allow one-way communication: the human user gives a natural language command to the agent, and the agent can only follow …

Self-Adaptive Imitation Learning: Learning Tasks with Delayed Rewards from Sub-optimal Demonstrations Open

Zhuangdi Zhu, Kaixiang Lin, Bo Dai, Jiayu Zhou · 2022

Reinforcement learning (RL) has demonstrated its superiority in solving sequential decision-making problems. However, heavy dependence on immediate reward feedback impedes the wide application of RL. On the other hand, imitation learning (…

Learning to Act with Affordance-Aware Multimodal Neural SLAM Open

Zhiwei Jia, Kaixiang Lin, Yizhou Zhao, Qiaozi Gao, Govind Thattai , et al. · 2022

Recent years have witnessed an emerging paradigm shift toward embodied artificial intelligence, in which an agent must learn to solve challenging tasks by interacting with its environment. There are several challenges in solving embodied m…

Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning Open

Tongzhou Mu, Kaixiang Lin, Feiyang Niu, Govind Thattai · 2022

We present a two-step hybrid reinforcement learning (RL) policy that is designed to generate interpretable and robust hierarchical policies on the RL problem with graph-based input. Unlike prior deep reinforcement learning policies paramet…

Research on Real-Time Analysis of Combustion State of Swirl Burner Based on High-Temperature Image Acquisition Probe Open

Ting Zhang, Yuguang Niu, Dang Lu, Kaixiang Lin, Tian Qiu , et al. · 2022

DSResSol: A Sequence-Based Solubility Predictor Created with Dilated Squeeze Excitation Residual Networks Open

Mohammad Madani, Kaixiang Lin, Anna Tarakanova · 2021

Protein solubility is an important thermodynamic parameter that is critical for the characterization of a protein’s function, and a key determinant for the production yield of a protein in both the research setting and within industrial (e…

LUMINOUS: Indoor Scene Generation for Embodied AI Challenges Open

Yizhou Zhao, Kaixiang Lin, Zhiwei Jia, Qiaozi Gao, Govind Thattai , et al. · 2021

Learning-based methods for training embodied agents typically require a large number of high-quality scenes that contain realistic layouts and support meaningful interactions. However, current simulators for Embodied AI (EAI) challenges on…

DSResSol: A sequence-based solubility predictor created with dilated squeeze excitation residual networks Open

Mohammad Madani, Kaixiang Lin, Anna Tarakanova · 2021

Protein solubility is an important thermodynamic parameter critical for the characterization of a protein’s function, and a key determinant for the production yield of a protein in both the research setting and within industrial (e.g. phar…

RCA: A Deep Collaborative Autoencoder Approach for Anomaly Detection Open

Boyang Liu, Ding Wang, Kaixiang Lin, Pang‐Ning Tan, Jiayu Zhou · 2021

Unsupervised anomaly detection plays a crucial role in many critical applications. Driven by the success of deep learning, recent years have witnessed growing interests in applying deep neural networks (DNNs) to anomaly detection problems.…

PowerNet: Multi-Agent Deep Reinforcement Learning for Scalable Powergrid Control Open

Dong Chen, Kaian Chen, Zhaojian Li, Tianshu Chu, Rui Yao , et al. · 2021

This paper develops an efficient multi-agent deep reinforcement learning algorithm for cooperative controls in powergrids. Specifically, we consider the decentralized inverter-based secondary voltage control problem in distributed generato…

Federated Learning's Blessing: FedAvg has Linear Speedup Open

Zhaonan Qu, Kaixiang Lin, Zhaojian Li, Jiayu Zhou, Zhengyuan Zhou · 2021

Federated learning (FL) learns a model jointly from a set of participating devices without sharing each other's privately held data. The characteristics of non-\textit{i.i.d.} data across the network, low device participation, high communi…

Off-Policy Imitation Learning from Observations Open

Zhuangdi Zhu, Kaixiang Lin, Bo Dai, Jiayu Zhou · 2021

Learning from Observations (LfO) is a practical reinforcement learning scenario from which many applications can benefit through the reuse of incomplete resources. Compared to conventional imitation learning (IL), LfO is more challenging b…

PowerNet: Multi-agent Deep Reinforcement Learning for Scalable Powergrid Control Open

Chen Dong, Zhaojian Li, Tianshu Chu, Rui Yao, Feng Qiu , et al. · 2020

This paper develops an efficient multi-agent deep reinforcement learning algorithm for cooperative controls in powergrids. Specifically, we consider the decentralized inverter-based secondary voltage control problem in distributed generato…

Transfer Learning in Deep Reinforcement Learning: A Survey Open

Zhuangdi Zhu, Kaixiang Lin, Jiayu Zhou · 2020

Reinforcement learning is a learning paradigm for solving sequential decision-making problems. Recent years have witnessed remarkable progress in reinforcement learning upon the fast development of deep neural networks. Along with the prom…

A Unified Linear Speedup Analysis of Federated Averaging and Nesterov FedAvg Open

Zhaonan Qu, Kaixiang Lin, Zhaojian Li, Jiayu Zhou, Zhengyuan Zhou · 2020

Federated learning (FL) learns a model jointly from a set of participating devices without sharing each other's privately held data. The characteristics of non-i.i.d. data across the network, low device participation, high communication co…

Learning Sparse Rewarded Tasks from Sub-Optimal Demonstrations Open

Zhuangdi Zhu, Kaixiang Lin, Bo Dai, Jiayu Zhou · 2020

Model-free deep reinforcement learning (RL) has demonstrated its superiority on many complex sequential decision-making problems. However, heavy dependence on dense rewards and high sample-complexity impedes the wide adoption of these meth…

Ranking Policy Gradient Open

Kaixiang Lin, Jiayu Zhou · 2019

Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization. Tow…

Alkaline Quinone Flow Battery with Long Lifetime at pH 12 Open

David G. Kwabi, Kaixiang Lin, Yunlong Ji, Emily F. Kerr, Marc‐Antoni Goulet , et al. · 2018

(Joule 2, 1894–1906; September 19, 2018) In the originally published version of this article, the first panel of Figure 1 showing the DBEAQ synthetic route was omitted. It has now been included and appears below. Additionally, one of the r…

Efficient Large-Scale Fleet Management via Multi-Agent Deep Reinforcement Learning Open

Kaixiang Lin, Renyu Zhao, Zhe Xu, Jiayu Zhou · 2018

Large-scale online ride-sharing platforms have substantially transformed our lives by reallocating transportation resources to alleviate traffic congestion and promote transportation efficiency. An efficient fleet management strategy not o…

Differentially Private Generative Adversarial Network Open

Liyang Xie, Kaixiang Lin, Shu Wang, Fei Wang, Jiayu Zhou · 2018

Generative Adversarial Network (GAN) and its variants have recently attracted intensive research interests due to their elegant theoretical foundation and excellent empirical performance as generative models. These tools provide a promisin…

Efficient Collaborative Multi-Agent Deep Reinforcement Learning for Large-Scale Fleet Management Open

Kaixiang Lin, Renyu Zhao, Zhe Xu, Jiayu Zhou · 2018

Large-scale online ride-sharing platforms have substantially transformed our lives by reallocating transportation resources to alleviate traffic congestion and promote transportation efficiency. An efficient fleet management strategy not o…

Improving Mild Cognitive Impairment Prediction via Reinforcement Learning and Dialogue Simulation Open

Fengyi Tang, Kaixiang Lin, Ikechukwu Uchendu, Hiroko H. Dodge, Jiayu Zhou · 2018

Mild cognitive impairment (MCI) is a prodromal phase in the progression from normal aging to dementia, especially Alzheimers disease. Even though there is mild cognitive decline in MCI patients, they have normal overall cognition and thus …

Kaixiang Lin YOU? Author Swipe