Search Results for author: Tian Lan

Found 53 papers, 21 papers with code

ISTIC’s Triangular Machine Translation System for WMT2021

no code implementations WMT (EMNLP) 2021 Hangcheng Guo, wenbin liu, yanqing he, Tian Lan, Hongjiao Xu, zhenfeng wu, you pan

This paper describes the ISTIC’s submission to the Triangular Machine Translation Task of Russian-to-Chinese machine translation for WMT’ 2021.

Machine Translation Translation

MM-DAG: Multi-task DAG Learning for Multi-modal Data -- with Application for Traffic Congestion Analysis

1 code implementation5 Jun 2023 Tian Lan, Ziyue Li, Zhishuai Li, Lei Bai, Man Li, Fugee Tsung, Wolfgang Ketter, Rui Zhao, Chen Zhang

This encourages the multi-task design: with each DAG as a task, the MM-DAG tries to learn the multiple DAGs jointly so that their consensus and consistency are maximized.

Pedestrian Crossing Action Recognition and Trajectory Prediction with 3D Human Keypoints

no code implementations1 Jun 2023 Jiachen Li, Xinwei Shi, Feiyu Chen, Jonathan Stroud, Zhishuai Zhang, Tian Lan, Junhua Mao, Jeonhyung Kang, Khaled S. Refaat, Weilong Yang, Eugene Ie, CongCong Li

Accurate understanding and prediction of human behaviors are critical prerequisites for autonomous vehicles, especially in highly dynamic and interactive scenarios such as intersections in dense urban areas.

Action Recognition Autonomous Vehicles +3

FERN: Leveraging Graph Attention Networks for Failure Evaluation and Robust Network Design

no code implementations30 May 2023 Chenyi Liu, Vaneet Aggarwal, Tian Lan, Nan Geng, Yuan Yang, Mingwei Xu, Qing Li

By providing a neural network function approximation of this common kernel using graph attention networks, we develop a unified learning-based framework, FERN, for scalable Failure Evaluation and Robust Network design.

Graph Attention

Hierarchical Deep Counterfactual Regret Minimization

no code implementations27 May 2023 Jiayu Chen, Tian Lan, Vaneet Aggarwal

A notable advantage of HDCFR over previous research in this field is its ability to facilitate learning with predefined (human) expertise and foster the acquisition of transferable skills that can be applied to similar tasks.

PandaGPT: One Model To Instruction-Follow Them All

no code implementations25 May 2023 Yixuan Su, Tian Lan, Huayang Li, Jialu Xu, Yan Wang, Deng Cai

To do so, PandaGPT combines the multimodal encoders from ImageBind and the large language models from Vicuna.

Instruction Following

Multi-task Hierarchical Adversarial Inverse Reinforcement Learning

1 code implementation22 May 2023 Jiayu Chen, Dipesh Tamboli, Tian Lan, Vaneet Aggarwal

Multi-task Imitation Learning (MIL) aims to train a policy capable of performing a distribution of tasks based on multi-task expert demonstrations, which is essential for general-purpose robots.

Imitation Learning Multi-Task Learning +1

MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization

no code implementations21 Feb 2023 Yongsheng Mei, Hanhan Zhou, Tian Lan, Guru Venkataramani, Peng Wei

To this end, we propose MAC-PO, which formulates optimal prioritized experience replay for multi-agent problems as a regret minimization over the sampling weights of transitions.

Decision Making Multi-agent Reinforcement Learning +3

ReMIX: Regret Minimization for Monotonic Value Function Factorization in Multiagent Reinforcement Learning

no code implementations11 Feb 2023 Yongsheng Mei, Hanhan Zhou, Tian Lan

Such an optimization problem can be relaxed and solved using the Lagrangian multiplier method to obtain the close-form optimal projection weights.

Decision Making reinforcement-learning +2

Exploiting Partial Common Information Microstructure for Multi-Modal Brain Tumor Segmentation

no code implementations6 Feb 2023 Yongsheng Mei, Tian Lan, Guru Venkataramani

Our experimental results on the Multi-modal Brain Tumor Segmentation Challenge (BraTS) datasets consistently outperform those of state-of-the-art segmentation baselines, with validation Dice similarity coefficients of 0. 920, 0. 897, 0. 837 for the whole tumor, tumor core, and enhancing tumor on BraTS-2020.

Brain Tumor Segmentation Image Segmentation +1

TWR-MCAE: A Data Augmentation Method for Through-the-Wall Radar Human Motion Recognition

no code implementations6 Jan 2023 Weicheng Gao, Xiaopeng Yang, Xiaodong Qu, Tian Lan

The data preprocessing module achieves wall clutter, human motion features, and noise subspaces separation.

Data Augmentation

Momentum Decoding: Open-ended Text Generation As Graph Exploration

1 code implementation5 Dec 2022 Tian Lan, Yixuan Su, Shuhang Liu, Heyan Huang, Xian-Ling Mao

In this study, we formulate open-ended text generation from a new perspective, i. e., we view it as an exploration process within a directed graph.

Text Generation

ODPP: A Unified Algorithm Framework for Unsupervised Option Discovery based on Determinantal Point Process

1 code implementation1 Dec 2022 Jiayu Chen, Vaneet Aggarwal, Tian Lan

Learning rich skills through temporal abstractions without supervision of external rewards is at the frontier of Reinforcement Learning research.

A Bayesian Optimization Framework for Finding Local Optima in Expensive Multi-Modal Functions

no code implementations13 Oct 2022 Yongsheng Mei, Tian Lan, Mahdi Imani, Suresh Subramaniam

This joint distribution is used in the body of the BO acquisition functions to search for local optima during the optimization process.

Bayesian Optimization

Multi-agent Deep Covering Option Discovery

no code implementations7 Oct 2022 Jiayu Chen, Marina Haliem, Tian Lan, Vaneet Aggarwal

In this case, we propose Multi-agent Deep Covering Option Discovery, which constructs the multi-agent options through minimizing the expected cover time of the multiple agents' joint state space.

Multi-agent Reinforcement Learning reinforcement-learning +1

Option-Aware Adversarial Inverse Reinforcement Learning for Robotic Control

1 code implementation5 Oct 2022 Jiayu Chen, Tian Lan, Vaneet Aggarwal

In this work, we develop a novel HIL algorithm based on Adversarial Inverse Reinforcement Learning and adapt it with the Expectation-Maximization algorithm in order to directly recover a hierarchical policy from the unannotated demonstrations.

Imitation Learning Multi-Task Learning +2

PAC: Assisted Value Factorisation with Counterfactual Predictions in Multi-Agent Reinforcement Learning

1 code implementation22 Jun 2022 Hanhan Zhou, Tian Lan, Vaneet Aggarwal

Multi-agent reinforcement learning (MARL) has witnessed significant progress with the development of value function factorization methods.

Multi-agent Reinforcement Learning reinforcement-learning +4

Language Models Can See: Plugging Visual Controls in Text Generation

1 code implementation5 May 2022 Yixuan Su, Tian Lan, Yahui Liu, Fangyu Liu, Dani Yogatama, Yan Wang, Lingpeng Kong, Nigel Collier

MAGIC is a flexible framework and is theoretically compatible with any text generation tasks that incorporate image grounding.

Image Captioning Story Generation +1

Cross-Lingual Phrase Retrieval

1 code implementation ACL 2022 Heqi Zheng, Xiao Zhang, Zewen Chi, Heyan Huang, Tan Yan, Tian Lan, Wei Wei, Xian-Ling Mao

In this paper, we propose XPR, a cross-lingual phrase retriever that extracts phrase representations from unlabeled example sentences.


SAFARI: Sparsity enabled Federated Learning with Limited and Unreliable Communications

no code implementations5 Apr 2022 Yuzhu Mao, Zihao Zhao, Meilin Yang, Le Liang, Yang Liu, Wenbo Ding, Tian Lan, Xiao-Ping Zhang

It is demonstrated that SAFARI under unreliable communications is guaranteed to converge at the same rate as the standard FedAvg with perfect communications.

Federated Learning Sparse Learning

Efficient Video Instance Segmentation via Tracklet Query and Proposal

no code implementations CVPR 2022 Jialian Wu, Sudhir Yarram, Hui Liang, Tian Lan, Junsong Yuan, Jayan Eledath, Gerard Medioni

In addition, VisTR is not fully end-to-end learnable in multiple video clips as it requires a hand-crafted data association to link instance tracklets between successive clips.

Instance Segmentation Semantic Segmentation +1

A Contrastive Framework for Neural Text Generation

2 code implementations13 Feb 2022 Yixuan Su, Tian Lan, Yan Wang, Dani Yogatama, Lingpeng Kong, Nigel Collier

Text generation is of great importance to many natural language processing applications.

Text Generation

On the Convergence of Heterogeneous Federated Learning with Arbitrary Adaptive Online Model Pruning

1 code implementation27 Jan 2022 Hanhan Zhou, Tian Lan, Guru Venkataramani, Wenbo Ding

In this paper, we present a unifying framework for heterogeneous FL algorithms with {\em arbitrary} adaptive online model pruning and provide a general convergence analysis.

Federated Learning

Learning Multi-agent Options for Tabular Reinforcement Learning using Factor Graphs

no code implementations20 Jan 2022 Jiayu Chen, Jingdi Chen, Tian Lan, Vaneet Aggarwal

Covering option discovery has been developed to improve the exploration of reinforcement learning in single-agent scenarios with sparse reward signals, through connecting the most distant states in the embedding space provided by the Fiedler vector of the state transition graph.

reinforcement-learning Reinforcement Learning (RL)

Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy Gradients

1 code implementation4 Jan 2022 Hanhan Zhou, Tian Lan, Vaneet Aggarwal

To this end, we present LSF-SAC, a novel framework that features a variational inference-based information-sharing mechanism as extra state information to assist individual agents in the value function factorization.

Starcraft Starcraft II +1

PT-VTON: an Image-Based Virtual Try-On Network with Progressive Pose Attention Transfer

no code implementations23 Nov 2021 Hanhan Zhou, Tian Lan, Guru Venkataramani

The virtual try-on system has gained great attention due to its potential to give customers a realistic, personalized product presentation in virtualized settings.

Pose Transfer Virtual Try-on

Exploring Dense Retrieval for Dialogue Response Selection

1 code implementation13 Oct 2021 Tian Lan, Deng Cai, Yan Wang, Yixuan Su, Heyan Huang, Xian-Ling Mao

In this study, we present a solution to directly select proper responses from a large corpus or even a nonparallel corpus that only consists of unpaired sentences, using a dense retrieval model.

Conversational Response Selection Retrieval

Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering

1 code implementation13 Sep 2021 Jian Xu, Shao-Lun Huang, Linqi Song, Tian Lan

To this end, previous work either makes use of auxiliary data at parameter server to verify the received gradients (e. g., by computing validation error rate) or leverages statistic-based methods (e. g. median and Krum) to identify and remove malicious gradients from Byzantine clients.

Federated Learning Model Poisoning +2

WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU

3 code implementations31 Aug 2021 Tian Lan, Sunil Srinivasa, Huan Wang, Stephan Zheng

We present WarpDrive, a flexible, lightweight, and easy-to-use open-source RL framework that implements end-to-end deep multi-agent RL on a single GPU (Graphics Processing Unit), built on PyCUDA and PyTorch.

Decision Making Multi-agent Reinforcement Learning +2

DQ-SGD: Dynamic Quantization in SGD for Communication-Efficient Distributed Learning

no code implementations30 Jul 2021 Guangfeng Yan, Shao-Lun Huang, Tian Lan, Linqi Song

Gradient quantization is an emerging technique in reducing communication costs in distributed learning.



no code implementations1 Jan 2021 Guangfeng Yan, Shao-Lun Huang, Tian Lan, Linqi Song

This paper addresses this issue by proposing a novel dynamic quantized SGD (DQSGD) framework, which enables us to optimize the quantization strategy for each gradient descent step by exploring the trade-off between communication cost and modeling error.


Self-attention Comparison Module for Boosting Performance on Retrieval-based Open-Domain Dialog Systems

no code implementations21 Dec 2020 Tian Lan, Xian-Ling Mao, Zhipeng Zhao, Wei Wei, Heyan Huang

Since the pre-trained language models are widely used, retrieval-based open-domain dialog systems, have attracted considerable attention from researchers recently.

Open-Domain Dialog Retrieval

Ultra-Fast, Low-Storage, Highly Effective Coarse-grained Selection in Retrieval-based Chatbot by Using Deep Semantic Hashing

1 code implementation17 Dec 2020 Tian Lan, Xian-Ling Mao, Xiaoyan Gao, Wei Wei, Heyan Huang

Specifically, in our proposed DSHC model, a hashing optimizing module that consists of two autoencoder models is stacked on a trained dense representation model, and three loss functions are designed to optimize it.

Chatbot Retrieval

Which Kind Is Better in Open-domain Multi-turn Dialog,Hierarchical or Non-hierarchical Models? An Empirical Study

no code implementations7 Aug 2020 Tian Lan, Xian-Ling Mao, Wei Wei, He-Yan Huang

Thus, in this paper, we will measure systematically nearly all representative hierarchical and non-hierarchical models over the same experimental settings to check which kind is better.

PONE: A Novel Automatic Evaluation Metric for Open-Domain Generative Dialogue Systems

1 code implementation6 Apr 2020 Tian Lan, Xian-Ling Mao, Wei Wei, Xiaoyan Gao, He-Yan Huang

Through extensive experiments, the learning-based metrics are demonstrated that they are the most effective evaluation metrics for open-domain generative dialogue systems.

Dialogue Evaluation

MILA: Multi-Task Learning from Videos via Efficient Inter-Frame Attention

no code implementations18 Feb 2020 Donghyun Kim, Tian Lan, Chuhang Zou, Ning Xu, Bryan A. Plummer, Stan Sclaroff, Jayan Eledath, Gerard Medioni

We embed the attention module in a ``slow-fast'' architecture, where the slower network runs on sparsely sampled keyframes and the light-weight shallow network runs on non-keyframes at a high frame rate.

Multi-Task Learning

When to Talk: Chatbot Controls the Timing of Talking during Multi-turn Open-domain Dialogue Generation

no code implementations20 Dec 2019 Tian Lan, Xian-Ling Mao, He-Yan Huang, Wei Wei

Intuitively, a dialogue model that can control the timing of talking autonomously based on the conversation context can chat with humans more naturally.

Dialogue Generation

Generative Dialog Policy for Task-oriented Dialog Systems

no code implementations17 Sep 2019 Tian Lan, Xian-Ling Mao, He-Yan Huang

As far as we know, the existing task-oriented dialogue systems obtain the dialogue policy through classification, which can assign either a dialogue act and its corresponding parameters or multiple dialogue acts without their corresponding parameters for a dialogue action.

General Classification Task-Oriented Dialogue Systems

Multi-task Learning for Low-resource Second Language Acquisition Modeling

1 code implementation25 Aug 2019 Yong Hu, He-Yan Huang, Tian Lan, Xiaochi Wei, Yuxiang Nie, Jiarui Qi, Liner Yang, Xian-Ling Mao

Second language acquisition (SLA) modeling is to predict whether second language learners could correctly answer the questions according to what they have learned.

Language Acquisition Multi-Task Learning

Large-scale 3D point cloud representations via graph inception networks with applications to autonomous driving

no code implementations26 Jun 2019 Siheng Chen, Sufeng. Niu, Tian Lan, Baoan Liu

We present a novel graph-neural-network-based system to effectively represent large-scale 3D point clouds with the applications to autonomous driving.

Autonomous Driving Self-Driving Cars

RUN:Residual U-Net for Computer-Aided Detection of Pulmonary Nodules without Candidate Selection

no code implementations30 May 2018 Tian Lan, Yuanyuan Li, Jonah Kimani Murugi, Yi Ding, Zhiguang Qin

The early detection and early diagnosis of lung cancer are crucial to improve the survival rate of lung cancer patients.

Spatio-temporal Aware Non-negative Component Representation for Action Recognition

no code implementations27 Aug 2016 Jianhong Wang, Tian Lan, Xu Zhang, Limin Luo

This paper presents a novel mid-level representation for action recognition, named spatio-temporal aware non-negative component representation (STANNCR).

Action Recognition Temporal Action Localization

Action Recognition by Hierarchical Mid-level Action Elements

no code implementations ICCV 2015 Tian Lan, Yuke Zhu, Amir Roshan Zamir, Silvio Savarese

Realistic videos of human actions exhibit rich spatiotemporal structures at multiple levels of granularity: an action can always be decomposed into multiple finer-grained elements in both space and time.

Action Parsing Action Recognition +1

Latent Maximum Margin Clustering

no code implementations NeurIPS 2013 Guang-Tong Zhou, Tian Lan, Arash Vahdat, Greg Mori

We present a maximum margin framework that clusters data using latent variables.


A Max-Margin Riffled Independence Model for Image Tag Ranking

no code implementations CVPR 2013 Tian Lan, Greg Mori

We propose Max-Margin Riffled Independence Model (MMRIM), a new method for image tag ranking modeling the structured preferences among tags.

Retrieval TAG

Cannot find the paper you are looking for? You can Submit a new open access paper.