Search Results for author: Xiao Ma

Found 44 papers, 15 papers with code

Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting

no code implementations25 Oct 2023 Preethi Lahoti, Nicholas Blumm, Xiao Ma, Raghavendra Kotikalapudi, Sahitya Potluri, Qijun Tan, Hansa Srinivasan, Ben Packer, Ahmad Beirami, Alex Beutel, Jilin Chen

A crucial challenge for generative large language models (LLMs) is diversity: when a user's prompt is under-specified, models may follow implicit assumptions while generating a response, which may result in homogenization of the responses, as well as certain demographic groups being under-represented or even erased from the generated responses.

Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning

no code implementations25 Oct 2023 Ananth Balashankar, Xiao Ma, Aradhana Sinha, Ahmad Beirami, Yao Qin, Jilin Chen, Alex Beutel

As large language models (LLMs) are widely adopted, new safety issues and policies emerge, to which existing safety classifiers do not generalize well.

Data Augmentation Few-Shot Learning +1

A global product of fine-scale urban building height based on spaceborne lidar

no code implementations22 Oct 2023 Xiao Ma, Guang Zheng, Chi Xu, L. Monika Moskal, Peng Gong, Qinghua Guo, Huabing Huang, Xuecao Li, Yong Pang, Cheng Wang, Huan Xie, Bailang Yu, Bo Zhao, Yuyu Zhou

Our results revealed that the estimated method of building height samples based on the GEDI data was effective with 0. 78 of Pearson's r and 3. 67 m of RMSE in comparison to the reference data.

Let's Do a Thought Experiment: Using Counterfactuals to Improve Moral Reasoning

no code implementations25 Jun 2023 Xiao Ma, Swaroop Mishra, Ahmad Beirami, Alex Beutel, Jilin Chen

Language models still struggle on moral reasoning, despite their impressive performance in many other tasks.

counterfactual Math +2

Improving and Benchmarking Offline Reinforcement Learning Algorithms

1 code implementation1 Jun 2023 Bingyi Kang, Xiao Ma, Yirui Wang, Yang Yue, Shuicheng Yan

Recently, Offline Reinforcement Learning (RL) has achieved remarkable progress with the emergence of various algorithms and datasets.

Benchmarking D4RL +3

Visualising Personal Data Flows: Insights from a Case Study of

no code implementations19 Apr 2023 Haiyue Yuan, Matthew Boakes, Xiao Ma, Dongmei Cao, Shujun Li

This case study can inform us about future research on more data flow-oriented privacy policy analysis and on the construction of a more comprehensive ontology on personal data flows in complicated business ecosystems.

Hi Sheldon! Creating Deep Personalized Characters from TV Shows

no code implementations9 Apr 2023 Meidai Xuanyuan, Yuwang Wang, Honglei Guo, Xiao Ma, Yuchen Guo, Tao Yu, Qionghai Dai

To support this novel task, we further collect a character centric multimodal dialogue dataset, named Deep Personalized Character Dataset (DPCD), from TV shows.

Imitation Learning As State Matching via Differentiable Physics

no code implementations CVPR 2023 Siwei Chen, Xiao Ma, Zhongwen Xu

With the physics prior, ILD policies can not only be transferable to unseen environment specifications but also yield higher final performance on a variety of tasks.

Continuous Control Deformable Object Manipulation +1

RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning

no code implementations18 Oct 2022 Wei Qiu, Xiao Ma, Bo An, Svetlana Obraztsova, Shuicheng Yan, Zhongwen Xu

Despite the recent advancement in multi-agent reinforcement learning (MARL), the MARL agents easily overfit the training environment and perform poorly in the evaluation scenarios where other agents behave differently.

Multi-agent Reinforcement Learning reinforcement-learning +1

A Human-ML Collaboration Framework for Improving Video Content Reviews

no code implementations18 Oct 2022 Meghana Deodhar, Xiao Ma, Yixin Cai, Alex Koes, Alex Beutel, Jilin Chen

We deal with the problem of localized in-video taxonomic human annotation in the video content moderation domain, where the goal is to identify video segments that violate granular policies, e. g., community guidelines on an online video platform.

Boosting Offline Reinforcement Learning via Data Rebalancing

no code implementations17 Oct 2022 Yang Yue, Bingyi Kang, Xiao Ma, Zhongwen Xu, Gao Huang, Shuicheng Yan

Therefore, we propose a simple yet effective method to boost offline RL algorithms based on the observation that resampling a dataset keeps the distribution support unchanged.

D4RL Offline RL +2

Imitation Learning via Differentiable Physics

1 code implementation10 Jun 2022 Siwei Chen, Xiao Ma, Zhongwen Xu

With the physics prior, ILD policies can not only be transferable to unseen environment specifications but also yield higher final performance on a variety of tasks.

Continuous Control Deformable Object Manipulation +1

Label Adversarial Learning for Skeleton-level to Pixel-level Adjustable Vessel Segmentation

no code implementations7 May 2022 Mingchao Li, Kun Huang, Zetian Zhang, Xiao Ma, Qiang Chen

This continuous process allows us to recommend high-quality vessel segmentation with clear caliber and topology.


Towards Sustainable Satellite Edge Computing

no code implementations10 Mar 2022 Qing Li, Shangguang Wang, Xiao Ma, Ao Zhou, Fangchun Yang

Recently, Low Earth Orbit (LEO) satellites experience rapid development and satellite edge computing emerges to address the limitation of bent-pipe architecture in existing satellite systems.

Edge-computing Scheduling

On Exploring Pose Estimation as an Auxiliary Learning Task for Visible-Infrared Person Re-identification

no code implementations11 Jan 2022 Yunqi Miao, Nianchang Huang, Xiao Ma, Qiang Zhang, Jungong Han

Visible-infrared person re-identification (VI-ReID) has been challenging due to the existence of large discrepancies between visible and infrared modalities.

Auxiliary Learning Knowledge Distillation +2

State-based Episodic Memory for Multi-Agent Reinforcement Learning

no code implementations19 Oct 2021 Xiao Ma, Wu-Jun Li

SEM adopts episodic memory (EM) to supervise the centralized training procedure of CTDE in MARL.

reinforcement-learning Reinforcement Learning (RL) +2

Ab Initio Particle-based Object Manipulation

no code implementations19 Jul 2021 Siwei Chen, Xiao Ma, Yunfan Lu, David Hsu

Like the model-based analytic approaches to manipulation, the particle representation enables the robot to reason about the object's geometry and dynamics in order to choose suitable manipulation actions.

Robot Manipulation

Learning Latent Graph Dynamics for Visual Manipulation of Deformable Objects

no code implementations25 Apr 2021 Xiao Ma, David Hsu, Wee Sun Lee

Manipulating deformable objects, such as ropes and clothing, is a long-standing challenge in robotics, because of their large degrees of freedom, complex non-linear dynamics, and self-occlusion in visual perception.

Contrastive Learning Deformable Object Manipulation +1

Towards Overcoming False Positives in Visual Relationship Detection

no code implementations23 Dec 2020 Daisheng Jin, Xiao Ma, Chongzhi Zhang, Yizhuo Zhou, Jiashu Tao, Mingyuan Zhang, Haiyu Zhao, Shuai Yi, Zhoujun Li, Xianglong Liu, Hongsheng Li

We observe that during training, the relationship proposal distribution is highly imbalanced: most of the negative relationship proposals are easy to identify, e. g., the inaccurate object detection, which leads to the under-fitting of low-frequency difficult proposals.

Graph Attention Human-Object Interaction Detection +4

Hierarchical Federated Learning through LAN-WAN Orchestration

no code implementations22 Oct 2020 Jinliang Yuan, Mengwei Xu, Xiao Ma, Ao Zhou, Xuanzhe Liu, Shangguang Wang

Our proposed FL can accelerate the learning process and reduce the monetary cost with frequent local aggregation in the same LAN and infrequent global aggregation on a cloud across WAN.

Federated Learning

Contrastive Variational Reinforcement Learning for Complex Observations

1 code implementation6 Aug 2020 Xiao Ma, Siwei Chen, David Hsu, Wee Sun Lee

This paper presents Contrastive Variational Reinforcement Learning (CVRL), a model-based method that tackles complex visual observations in DRL.

Atari Games Continuous Control +4

Balanced Meta-Softmax for Long-Tailed Visual Recognition

1 code implementation NeurIPS 2020 Jiawei Ren, Cunjun Yu, Shunan Sheng, Xiao Ma, Haiyu Zhao, Shuai Yi, Hongsheng Li

In our experiments, we demonstrate that Balanced Meta-Softmax outperforms state-of-the-art long-tailed classification solutions on both visual recognition and instance segmentation tasks.

General Classification Instance Segmentation +2

DinerDash Gym: A Benchmark for Policy Learning in High-Dimensional Action Space

1 code implementation13 Jul 2020 Siwei Chen, Xiao Ma, David Hsu

It has been arduous to assess the progress of a policy learning algorithm in the domain of hierarchical task with high dimensional action space due to the lack of a commonly accepted benchmark.

Atari Games

Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction

1 code implementation ECCV 2020 Cunjun Yu, Xiao Ma, Jiawei Ren, Haiyu Zhao, Shuai Yi

In this paper, we present STAR, a Spatio-Temporal grAph tRansformer framework, which tackles trajectory prediction by only attention mechanisms.

Autonomous Driving Pedestrian Trajectory Prediction +1

R3: A Reading Comprehension Benchmark Requiring Reasoning Processes

no code implementations2 Apr 2020 Ran Wang, Kun Tao, Dingjie Song, Zhilong Zhang, Xiao Ma, Xi'ao Su, Xin-yu Dai

Existing question answering systems can only predict answers without explicit reasoning processes, which hinder their explainability and make us overestimate their ability of understanding and reasoning over natural language.

Question Answering Reading Comprehension

Challenges in Supporting Exploratory Search through Voice Assistants

no code implementations6 Mar 2020 Xiao Ma, Ariel Liu

Compared to simple search tasks such as "How tall is the Eiffel Tower?

AI-Mediated Exchange Theory

no code implementations4 Mar 2020 Xiao Ma, Taylor W. Brown

As an extension to Social Exchange Theory (SET) in the social sciences, AI-MET views AI as influencing human-to-human relationships via a taxonomy of mediation mechanisms.

Discriminative Particle Filter Reinforcement Learning for Complex Partial Observations

1 code implementation ICLR 2020 Xiao Ma, Peter Karkus, David Hsu, Wee Sun Lee, Nan Ye

The particle filter maintains a belief using learned discriminative update, which is trained end-to-end for decision making.

Atari Games Decision Making +3

AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data

no code implementations12 Jul 2019 Zheng Gao, Lin Guo, Chi Ma, Xiao Ma, Kai Sun, Hang Xiang, Xiaoqiang Zhu, Hongsong Li, Xiaozhong Liu

Anomaly detection is facing with emerging challenges in many important industry domains, such as cyber security and online recommendation and advertising.

Anomaly Detection

Clustered Reinforcement Learning

no code implementations6 Jun 2019 Xiao Ma, Shen-Yi Zhao, Wu-Jun Li

Exploration strategy design is one of the challenging problems in reinforcement learning~(RL), especially when the environment contains a large state space or sparse rewards.

Atari Games Clustering +4

Particle Filter Recurrent Neural Networks

1 code implementation30 May 2019 Xiao Ma, Peter Karkus, David Hsu, Wee Sun Lee

Recurrent neural networks (RNNs) have been extraordinarily successful for prediction with sequential data.

General Classification Stock Price Prediction +2

Differentiable Algorithm Networks for Composable Robot Learning

no code implementations28 May 2019 Peter Karkus, Xiao Ma, David Hsu, Leslie Pack Kaelbling, Wee Sun Lee, Tomas Lozano-Perez

This paper introduces the Differentiable Algorithm Network (DAN), a composable architecture for robot learning systems.


Homogeneous Feature Transfer and Heterogeneous Location Fine-tuning for Cross-City Property Appraisal Framework

no code implementations11 Dec 2018 Yihan Guo, Shan Lin, Xiao Ma, Jay Bal, Chang-Tsun Li

Most existing real estate appraisal methods focus on building accuracy and reliable models from a given dataset but pay little attention to the extensibility of their trained model.

Understanding Image Quality and Trust in Peer-to-Peer Marketplaces

no code implementations26 Nov 2018 Xiao Ma, Lina Mezghani, Kimberly Wilber, Hui Hong, Robinson Piramuthu, Mor Naaman, Serge Belongie

In this work, we conducted a large-scale study on the quality of user-generated images in peer-to-peer marketplaces.

Dermoscopic Image Analysis for ISIC Challenge 2018

no code implementations24 Jul 2018 Jinyi Zou, Xiao Ma, Cheng Zhong, Yao Zhang

This short paper reports the algorithms we used and the evaluation performances for ISIC Challenge 2018.

Classification General Classification +3

Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate

5 code implementations21 Apr 2018 Xiao Ma, Liqin Zhao, Guan Huang, Zhi Wang, Zelin Hu, Xiaoqiang Zhu, Kun Gai

To the best of our knowledge, this is the first public dataset which contains samples with sequential dependence of click and conversion labels for CVR modeling.

Click-Through Rate Prediction Recommendation Systems +2

Deep Interest Network for Click-Through Rate Prediction

16 code implementations21 Jun 2017 Guorui Zhou, Chengru Song, Xiaoqiang Zhu, Ying Fan, Han Zhu, Xiao Ma, Yanghui Yan, Junqi Jin, Han Li, Kun Gai

In this way, user features are compressed into a fixed-length representation vector, in regardless of what candidate ads are.

Click-Through Rate Prediction

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