Search Results for author: Wenhao Yu

Found 84 papers, 35 papers with code

Retrieval-augmented Generation across Heterogeneous Knowledge

no code implementations NAACL (ACL) 2022 Wenhao Yu

Retrieval-augmented generation (RAG) methods have been receiving increasing attention from the NLP community and achieved state-of-the-art performance on many NLP downstream tasks.

Retrieval

Knowledge-Enriched Natural Language Generation

1 code implementation EMNLP (ACL) 2021 Wenhao Yu, Meng Jiang, Zhiting Hu, Qingyun Wang, Heng Ji, Nazneen Rajani

Knowledge-enriched text generation poses unique challenges in modeling and learning, driving active research in several core directions, ranging from integrated modeling of neural representations and symbolic information in the sequential/hierarchical/graphical structures, learning without direct supervisions due to the cost of structured annotation, efficient optimization and inference with massive and global constraints, to language grounding on multiple modalities, and generative reasoning with implicit commonsense knowledge and background knowledge.

Text Generation

Knowledge-Augmented Methods for Natural Language Processing

no code implementations ACL 2022 Chenguang Zhu, Yichong Xu, Xiang Ren, Bill Lin, Meng Jiang, Wenhao Yu

Knowledge in natural language processing (NLP) has been a rising trend especially after the advent of large scale pre-trained models.

Text Generation

Towards Safe and Reliable Autonomous Driving: Dynamic Occupancy Set Prediction

no code implementations29 Feb 2024 Wenbo Shao, Jiahui Xu, Wenhao Yu, Jun Li, Hong Wang

In the rapidly evolving field of autonomous driving, accurate trajectory prediction is pivotal for vehicular safety.

Autonomous Driving Trajectory Prediction

WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models

1 code implementation25 Jan 2024 Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Yong Dai, Hongming Zhang, Zhenzhong Lan, Dong Yu

The rapid advancement of large language models (LLMs) has led to a new era marked by the development of autonomous applications in real-world scenarios, which drives innovation in creating advanced web agents.

Gradient Shaping for Multi-Constraint Safe Reinforcement Learning

no code implementations23 Dec 2023 Yihang Yao, Zuxin Liu, Zhepeng Cen, Peide Huang, Tingnan Zhang, Wenhao Yu, Ding Zhao

Leveraging insights from this framework and recognizing the significance of \textit{redundant} and \textit{conflicting} constraint conditions, we introduce the Gradient Shaping (GradS) method for general Lagrangian-based safe RL algorithms to improve the training efficiency in terms of both reward and constraint satisfaction.

reinforcement-learning Reinforcement Learning (RL) +1

Dense X Retrieval: What Retrieval Granularity Should We Use?

1 code implementation11 Dec 2023 Tong Chen, Hongwei Wang, Sihao Chen, Wenhao Yu, Kaixin Ma, Xinran Zhao, Hongming Zhang, Dong Yu

We discover that the retrieval unit choice significantly impacts the performance of both retrieval and downstream tasks.

Retrieval Sentence +1

PLUG: Leveraging Pivot Language in Cross-Lingual Instruction Tuning

1 code implementation15 Nov 2023 Zhihan Zhang, Dong-Ho Lee, Yuwei Fang, Wenhao Yu, Mengzhao Jia, Meng Jiang, Francesco Barbieri

Instruction tuning has remarkably advanced large language models (LLMs) in understanding and responding to diverse human instructions.

Instruction Following

Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models

no code implementations15 Nov 2023 Wenhao Yu, Hongming Zhang, Xiaoman Pan, Kaixin Ma, Hongwei Wang, Dong Yu

In response to these challenges, we introduces Chain-of-Noting (CoN), a novel approach aimed at improving the robustness of RALMs in facing noisy, irrelevant documents and in handling unknown scenarios.

Hallucination Retrieval

Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations

1 code implementation7 Nov 2023 Sihao Chen, Hongming Zhang, Tong Chen, Ben Zhou, Wenhao Yu, Dian Yu, Baolin Peng, Hongwei Wang, Dan Roth, Dong Yu

We introduce sub-sentence encoder, a contrastively-learned contextual embedding model for fine-grained semantic representation of text.

Contrastive Learning Semantic Similarity +3

FMRT: Learning Accurate Feature Matching with Reconciliatory Transformer

no code implementations20 Oct 2023 Xinyu Zhang, Li Wang, Zhiqiang Jiang, Kun Dai, Tao Xie, Lei Yang, Wenhao Yu, Yang shen, Jun Li

However, these methods only integrate long-range context information among keypoints with a fixed receptive field, which constrains the network from reconciling the importance of features with different receptive fields to realize complete image perception, hence limiting the matching accuracy.

Homography Estimation Pose Estimation +1

PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning

no code implementations20 Oct 2023 Wenhao Yu, Jie Peng, Quecheng Qiu, Hanyu Wang, Lu Zhang, Jianmin Ji

However, two roadblocks arise for training a DRL policy that outputs paths: (1) The action space for potential paths often involves higher dimensions comparing to low-level commands, which increases the difficulties of training; (2) It takes multiple time steps to track a path instead of a single time step, which requires the path to predicate the interactions of the robot w. r. t.

Collision Avoidance Robot Navigation

Creative Robot Tool Use with Large Language Models

no code implementations19 Oct 2023 Mengdi Xu, Peide Huang, Wenhao Yu, Shiqi Liu, Xilun Zhang, Yaru Niu, Tingnan Zhang, Fei Xia, Jie Tan, Ding Zhao

This paper investigates the feasibility of imbuing robots with the ability to creatively use tools in tasks that involve implicit physical constraints and long-term planning.

Motion Planning Task and Motion Planning

Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models

no code implementations19 Oct 2023 Zhihan Zhang, Shuohang Wang, Wenhao Yu, Yichong Xu, Dan Iter, Qingkai Zeng, Yang Liu, Chenguang Zhu, Meng Jiang

Large language models (LLMs) can perform a wide range of tasks by following natural language instructions, without the necessity of task-specific fine-tuning.

Toward Intelligent Emergency Control for Large-scale Power Systems: Convergence of Learning, Physics, Computing and Control

no code implementations8 Oct 2023 Qiuhua Huang, Renke Huang, Tianzhixi Yin, Sohom Datta, Xueqing Sun, Jason Hou, Jie Tan, Wenhao Yu, YuAn Liu, Xinya Li, Bruce Palmer, Ang Li, Xinda Ke, Marianna Vaiman, Song Wang, Yousu Chen

Our developed methods and platform based on the convergence framework have been applied to a large (more than 3000 buses) Texas power system, and tested with 56000 scenarios.

LASER: LLM Agent with State-Space Exploration for Web Navigation

1 code implementation15 Sep 2023 Kaixin Ma, Hongming Zhang, Hongwei Wang, Xiaoman Pan, Wenhao Yu, Dong Yu

We evaluate our proposed LLM Agent with State-Space ExploRation (LASER) on both the WebShop task and amazon. com.

Decision Making

GeoGPT: Understanding and Processing Geospatial Tasks through An Autonomous GPT

no code implementations16 Jul 2023 Yifan Zhang, Cheng Wei, Shangyou Wu, Zhengting He, Wenhao Yu

Though limited cases are presented in this paper, GeoGPT can be further extended to various tasks by equipping with more GIS tools, and we think the paradigm of "foundational plus professional" implied in GeoGPT provides an effective way to develop next-generation GIS in this era of large foundation models.

Transforming a Quadruped into a Guide Robot for the Visually Impaired: Formalizing Wayfinding, Interaction Modeling, and Safety Mechanism

no code implementations24 Jun 2023 J. Taery Kim, Wenhao Yu, Yash Kothari, Jie Tan, Greg Turk, Sehoon Ha

To build a successful guide robot, our paper explores three key topics: (1) formalizing the navigation mechanism of a guide dog and a human, (2) developing a data-driven model of their interaction, and (3) improving user safety.

Datasets and Benchmarks for Offline Safe Reinforcement Learning

3 code implementations15 Jun 2023 Zuxin Liu, Zijian Guo, Haohong Lin, Yihang Yao, Jiacheng Zhu, Zhepeng Cen, Hanjiang Hu, Wenhao Yu, Tingnan Zhang, Jie Tan, Ding Zhao

This paper presents a comprehensive benchmarking suite tailored to offline safe reinforcement learning (RL) challenges, aiming to foster progress in the development and evaluation of safe learning algorithms in both the training and deployment phases.

Autonomous Driving Benchmarking +4

Language to Rewards for Robotic Skill Synthesis

no code implementations14 Jun 2023 Wenhao Yu, Nimrod Gileadi, Chuyuan Fu, Sean Kirmani, Kuang-Huei Lee, Montse Gonzalez Arenas, Hao-Tien Lewis Chiang, Tom Erez, Leonard Hasenclever, Jan Humplik, Brian Ichter, Ted Xiao, Peng Xu, Andy Zeng, Tingnan Zhang, Nicolas Heess, Dorsa Sadigh, Jie Tan, Yuval Tassa, Fei Xia

However, since low-level robot actions are hardware-dependent and underrepresented in LLM training corpora, existing efforts in applying LLMs to robotics have largely treated LLMs as semantic planners or relied on human-engineered control primitives to interface with the robot.

In-Context Learning Logical Reasoning

Exploring Contrast Consistency of Open-Domain Question Answering Systems on Minimally Edited Questions

1 code implementation23 May 2023 Zhihan Zhang, Wenhao Yu, Zheng Ning, Mingxuan Ju, Meng Jiang

Contrast consistency, the ability of a model to make consistently correct predictions in the presence of perturbations, is an essential aspect in NLP.

Data Augmentation Language Modelling +4

Pre-training Language Models for Comparative Reasoning

no code implementations23 May 2023 Mengxia Yu, Zhihan Zhang, Wenhao Yu, Meng Jiang

Comparative reasoning is a process of comparing objects, concepts, or entities to draw conclusions, which constitutes a fundamental cognitive ability.

Question Answering Question Generation +1

IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions

no code implementations23 May 2023 Wenhao Yu, Meng Jiang, Peter Clark, Ashish Sabharwal

Although counterfactual reasoning is a fundamental aspect of intelligence, the lack of large-scale counterfactual open-domain question-answering (QA) benchmarks makes it difficult to evaluate and improve models on this ability.

counterfactual Counterfactual Reasoning +2

Improving Language Models via Plug-and-Play Retrieval Feedback

no code implementations23 May 2023 Wenhao Yu, Zhihan Zhang, Zhenwen Liang, Meng Jiang, Ashish Sabharwal

ReFeed first generates initial outputs, then utilizes a retrieval model to acquire relevant information from large document collections, and finally incorporates the retrieved information into the in-context demonstration for output refinement, thereby addressing the limitations of LLMs in a more efficient and cost-effective manner.

Retrieval

Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation

no code implementations22 May 2023 Zhenwen Liang, Wenhao Yu, Tanmay Rajpurohit, Peter Clark, Xiangliang Zhang, Ashwin Kaylan

In this paper, we present a novel approach for distilling math word problem solving capabilities from large language models (LLMs) into smaller, more efficient student models.

Knowledge Tracing Math +1

Large Language Models are Built-in Autoregressive Search Engines

1 code implementation16 May 2023 Noah Ziems, Wenhao Yu, Zhihan Zhang, Meng Jiang

To overcome this limitation, recent autoregressive search engines replace the dual-encoder architecture by directly generating identifiers for relevant documents in the candidate pool.

Open-Domain Question Answering Retrieval

StarCoder: may the source be with you!

4 code implementations9 May 2023 Raymond Li, Loubna Ben allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, Qian Liu, Evgenii Zheltonozhskii, Terry Yue Zhuo, Thomas Wang, Olivier Dehaene, Mishig Davaadorj, Joel Lamy-Poirier, João Monteiro, Oleh Shliazhko, Nicolas Gontier, Nicholas Meade, Armel Zebaze, Ming-Ho Yee, Logesh Kumar Umapathi, Jian Zhu, Benjamin Lipkin, Muhtasham Oblokulov, Zhiruo Wang, Rudra Murthy, Jason Stillerman, Siva Sankalp Patel, Dmitry Abulkhanov, Marco Zocca, Manan Dey, Zhihan Zhang, Nour Fahmy, Urvashi Bhattacharyya, Wenhao Yu, Swayam Singh, Sasha Luccioni, Paulo Villegas, Maxim Kunakov, Fedor Zhdanov, Manuel Romero, Tony Lee, Nadav Timor, Jennifer Ding, Claire Schlesinger, Hailey Schoelkopf, Jan Ebert, Tri Dao, Mayank Mishra, Alex Gu, Jennifer Robinson, Carolyn Jane Anderson, Brendan Dolan-Gavitt, Danish Contractor, Siva Reddy, Daniel Fried, Dzmitry Bahdanau, Yacine Jernite, Carlos Muñoz Ferrandis, Sean Hughes, Thomas Wolf, Arjun Guha, Leandro von Werra, Harm de Vries

The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder and StarCoderBase: 15. 5B parameter models with 8K context length, infilling capabilities and fast large-batch inference enabled by multi-query attention.

8k Code Generation

Continuous Versatile Jumping Using Learned Action Residuals

no code implementations17 Apr 2023 Yuxiang Yang, Xiangyun Meng, Wenhao Yu, Tingnan Zhang, Jie Tan, Byron Boots

Jumping is essential for legged robots to traverse through difficult terrains.

A Survey of Deep Learning for Mathematical Reasoning

1 code implementation20 Dec 2022 Pan Lu, Liang Qiu, Wenhao Yu, Sean Welleck, Kai-Wei Chang

Mathematical reasoning is a fundamental aspect of human intelligence and is applicable in various fields, including science, engineering, finance, and everyday life.

Math Mathematical Reasoning

APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning

no code implementations19 Dec 2022 Soumya Sanyal, Yichong Xu, Shuohang Wang, ZiYi Yang, Reid Pryzant, Wenhao Yu, Chenguang Zhu, Xiang Ren

Logical reasoning of text is an important ability that requires understanding the information present in the text, their interconnections, and then reasoning through them to infer new conclusions.

Data Augmentation Language Modelling +3

No driver, No Regulation? --Online Legal Driving Behavior Monitoring for Self-driving Vehicles

no code implementations8 Dec 2022 Wenhao Yu, Chengxiang Zhao, Jiaxin Liu, Yingkai Yang, Xiaohan Ma, Jun Li, Weida Wang, Hong Wang, Ding Zhao, Xiaosong Hu

To address these challenges, this paper aims to digitize traffic law comprehensively and provide an application for online monitoring of legal driving behavior for autonomous vehicles.

Autonomous Driving Decision Making

Efficient Learning of Voltage Control Strategies via Model-based Deep Reinforcement Learning

no code implementations6 Dec 2022 Ramij R. Hossain, Tianzhixi Yin, Yan Du, Renke Huang, Jie Tan, Wenhao Yu, YuAn Liu, Qiuhua Huang

We propose a novel model-based-DRL framework where a deep neural network (DNN)-based dynamic surrogate model, instead of a real-world power-grid or physics-based simulation, is utilized with the policy learning framework, making the process faster and sample efficient.

Imitation Learning reinforcement-learning +1

SOTIF Entropy: Online SOTIF Risk Quantification and Mitigation for Autonomous Driving

1 code implementation8 Nov 2022 Liang Peng, Boqi Li, Wenhao Yu, Kai Yang, Wenbo Shao, Hong Wang

Therefore, this paper proposes the "Self-Surveillance and Self-Adaption System" as a systematic approach to online minimize the SOTIF risk, which aims to provide a systematic solution for monitoring, quantification, and mitigation of inherent and external risks.

Autonomous Driving Decision Making

Retrieval Augmentation for Commonsense Reasoning: A Unified Approach

1 code implementation23 Oct 2022 Wenhao Yu, Chenguang Zhu, Zhihan Zhang, Shuohang Wang, Zhuosheng Zhang, Yuwei Fang, Meng Jiang

However, applying such methods to commonsense reasoning tasks faces two unique challenges, i. e., the lack of a general large-scale corpus for retrieval and a corresponding effective commonsense retriever.

Retrieval

Task Compass: Scaling Multi-task Pre-training with Task Prefix

1 code implementation12 Oct 2022 Zhuosheng Zhang, Shuohang Wang, Yichong Xu, Yuwei Fang, Wenhao Yu, Yang Liu, Hai Zhao, Chenguang Zhu, Michael Zeng

Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models.

Common Sense Reasoning Data Augmentation +4

A Unified Encoder-Decoder Framework with Entity Memory

1 code implementation7 Oct 2022 Zhihan Zhang, Wenhao Yu, Chenguang Zhu, Meng Jiang

The entity knowledge is stored in the memory as latent representations, and the memory is pre-trained on Wikipedia along with encoder-decoder parameters.

Question Answering Text Generation +1

Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering

1 code implementation6 Oct 2022 Mingxuan Ju, Wenhao Yu, Tong Zhao, Chuxu Zhang, Yanfang Ye

In light of this, we propose a novel knowledge Graph enhanced passage reader, namely Grape, to improve the reader performance for open-domain QA.

Entity Embeddings Open-Domain Question Answering

Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization

1 code implementation5 Oct 2022 Mingxuan Ju, Tong Zhao, Qianlong Wen, Wenhao Yu, Neil Shah, Yanfang Ye, Chuxu Zhang

Besides, we observe that learning from multiple philosophies enhances not only the task generalization but also the single task performances, demonstrating that PARETOGNN achieves better task generalization via the disjoint yet complementary knowledge learned from different philosophies.

Link Prediction Node Classification +4

Generate rather than Retrieve: Large Language Models are Strong Context Generators

1 code implementation21 Sep 2022 Wenhao Yu, Dan Iter, Shuohang Wang, Yichong Xu, Mingxuan Ju, Soumya Sanyal, Chenguang Zhu, Michael Zeng, Meng Jiang

We call our method generate-then-read (GenRead), which first prompts a large language model to generate contextutal documents based on a given question, and then reads the generated documents to produce the final answer.

Language Modelling Large Language Model +1

PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations

no code implementations27 Jul 2022 Kuang-Huei Lee, Ofir Nachum, Tingnan Zhang, Sergio Guadarrama, Jie Tan, Wenhao Yu

Evolution Strategy (ES) algorithms have shown promising results in training complex robotic control policies due to their massive parallelism capability, simple implementation, effective parameter-space exploration, and fast training time.

Representation Learning

Learning Semantics-Aware Locomotion Skills from Human Demonstration

no code implementations27 Jun 2022 Yuxiang Yang, Xiangyun Meng, Wenhao Yu, Tingnan Zhang, Jie Tan, Byron Boots

Using only 40 minutes of human demonstration data, our framework learns to adjust the speed and gait of the robot based on perceived terrain semantics, and enables the robot to walk over 6km without failure at close-to-optimal speed.

A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods

no code implementations7 Apr 2022 Zhihan Zhang, Wenhao Yu, Mengxia Yu, Zhichun Guo, Meng Jiang

Multi-task learning (MTL) has become increasingly popular in natural language processing (NLP) because it improves the performance of related tasks by exploiting their commonalities and differences.

Multi-Task Learning

Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions

no code implementations28 Mar 2022 Alejandro Escontrela, Xue Bin Peng, Wenhao Yu, Tingnan Zhang, Atil Iscen, Ken Goldberg, Pieter Abbeel

We also demonstrate that an effective style reward can be learned from a few seconds of motion capture data gathered from a German Shepherd and leads to energy-efficient locomotion strategies with natural gait transitions.

Safe Reinforcement Learning for Legged Locomotion

no code implementations5 Mar 2022 Tsung-Yen Yang, Tingnan Zhang, Linda Luu, Sehoon Ha, Jie Tan, Wenhao Yu

In this paper, we propose a safe reinforcement learning framework that switches between a safe recovery policy that prevents the robot from entering unsafe states, and a learner policy that is optimized to complete the task.

reinforcement-learning Reinforcement Learning (RL) +1

Physics-informed Evolutionary Strategy based Control for Mitigating Delayed Voltage Recovery

no code implementations29 Nov 2021 Yan Du, Qiuhua Huang, Renke Huang, Tianzhixi Yin, Jie Tan, Wenhao Yu, Xinya Li

Reinforcement learning methods have been developed for the same or similar challenging control problems, but they suffer from training inefficiency and lack of robustness for "corner or unseen" scenarios.

Robot Learning from Randomized Simulations: A Review

no code implementations1 Nov 2021 Fabio Muratore, Fabio Ramos, Greg Turk, Wenhao Yu, Michael Gienger, Jan Peters

The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data.

Dict-BERT: Enhancing Language Model Pre-training with Dictionary

1 code implementation Findings (ACL) 2022 Wenhao Yu, Chenguang Zhu, Yuwei Fang, Donghan Yu, Shuohang Wang, Yichong Xu, Michael Zeng, Meng Jiang

In addition to training with the masked language modeling objective, we propose two novel self-supervised pre-training tasks on word and sentence-level alignment between input text sequence and rare word definitions to enhance language modeling representation with dictionary.

Language Modelling Masked Language Modeling +1

KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering

no code implementations ACL 2022 Donghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu, Shuohang Wang, Yichong Xu, Xiang Ren, Yiming Yang, Michael Zeng

The recent proposed Fusion-in-Decoder (FiD), which is built on top of the pretrained generative model T5, achieves the state-of-the-art performance in the reading module.

Answer Generation Open-Domain Question Answering +3

Universal Controllers with Differentiable Physics for Online System Identification

no code implementations29 Sep 2021 Michelle Guo, Wenhao Yu, Daniel Ho, Jiajun Wu, Yunfei Bai, Karen Liu, Wenlong Lu

In addition, we perform two studies showing that UC-DiffOSI operates well in environments with changing or unknown dynamics.

Domain Adaptation

Learning to Manipulate Amorphous Materials

no code implementations3 Mar 2021 Yunbo Zhang, Wenhao Yu, C. Karen Liu, Charles C. Kemp, Greg Turk

We produce a final animation by using inverse kinematics to guide a character's arm and hand to match the motion of the manipulation tool such as a knife or a frying pan.

Few-Shot Graph Learning for Molecular Property Prediction

1 code implementation16 Feb 2021 Zhichun Guo, Chuxu Zhang, Wenhao Yu, John Herr, Olaf Wiest, Meng Jiang, Nitesh V. Chawla

The recent success of graph neural networks has significantly boosted molecular property prediction, advancing activities such as drug discovery.

Attribute Drug Discovery +7

Protective Policy Transfer

no code implementations11 Dec 2020 Wenhao Yu, C. Karen Liu, Greg Turk

When used with a set of thresholds, the safety estimator becomes a classifier for switching between the protective policy and the task policy.

COCOI: Contact-aware Online Context Inference for Generalizable Non-planar Pushing

no code implementations23 Nov 2020 Zhuo Xu, Wenhao Yu, Alexander Herzog, Wenlong Lu, Chuyuan Fu, Masayoshi Tomizuka, Yunfei Bai, C. Karen Liu, Daniel Ho

General contact-rich manipulation problems are long-standing challenges in robotics due to the difficulty of understanding complicated contact physics.

Reinforcement Learning (RL) Robot Manipulation

Policy Transfer via Kinematic Domain Randomization and Adaptation

1 code implementation3 Nov 2020 Ioannis Exarchos, Yifeng Jiang, Wenhao Yu, C. Karen Liu

Transferring reinforcement learning policies trained in physics simulation to the real hardware remains a challenge, known as the "sim-to-real" gap.

Bayesian Optimization Domain Adaptation

Tri-Train: Automatic Pre-Fine Tuning between Pre-Training and Fine-Tuning for SciNER

no code implementations Findings of the Association for Computational Linguistics 2020 Qingkai Zeng, Wenhao Yu, Mengxia Yu, Tianwen Jiang, Tim Weninger, Meng Jiang

The training process of scientific NER models is commonly performed in two steps: i) Pre-training a language model by self-supervised tasks on huge data and ii) fine-tune training with small labelled data.

Language Modelling NER

Action Sequence Augmentation for Early Graph-based Anomaly Detection

1 code implementation20 Oct 2020 Tong Zhao, Bo Ni, Wenhao Yu, Zhichun Guo, Neil Shah, Meng Jiang

With Eland, anomaly detection performance at an earlier stage is better than non-augmented methods that need significantly more observed data by up to 15% on the Area under the ROC curve.

Data Augmentation Graph Anomaly Detection

Technical Question Answering across Tasks and Domains

1 code implementation NAACL 2021 Wenhao Yu, Lingfei Wu, Yu Deng, Qingkai Zeng, Ruchi Mahindru, Sinem Guven, Meng Jiang

In this paper, we propose a novel framework of deep transfer learning to effectively address technical QA across tasks and domains.

Question Answering Reading Comprehension +2

A Survey of Knowledge-Enhanced Text Generation

3 code implementations9 Oct 2020 Wenhao Yu, Chenguang Zhu, Zaitang Li, Zhiting Hu, Qingyun Wang, Heng Ji, Meng Jiang

To address this issue, researchers have considered incorporating various forms of knowledge beyond the input text into the generation models.

Text Generation

Crossing Variational Autoencoders for Answer Retrieval

no code implementations ACL 2020 Wenhao Yu, Lingfei Wu, Qingkai Zeng, Shu Tao, Yu Deng, Meng Jiang

Existing methods learned semantic representations with dual encoders or dual variational auto-encoders.

Retrieval

Faceted Hierarchy: A New Graph Type to Organize Scientific Concepts and a Construction Method

no code implementations WS 2019 Qingkai Zeng, Mengxia Yu, Wenhao Yu, JinJun Xiong, Yiyu Shi, Meng Jiang

On a scientific concept hierarchy, a parent concept may have a few attributes, each of which has multiple values being a group of child concepts.

Face Recognition

Learning Fast Adaptation with Meta Strategy Optimization

1 code implementation28 Sep 2019 Wenhao Yu, Jie Tan, Yunfei Bai, Erwin Coumans, Sehoon Ha

The key idea behind MSO is to expose the same adaptation process, Strategy Optimization (SO), to both the training and testing phases.

Meta-Learning

Learning Novel Policies For Tasks

no code implementations13 May 2019 Yunbo Zhang, Wenhao Yu, Greg Turk

Our method does this by creating a second reward function that recognizes previously seen state sequences and rewards those by novelty, which is measured using autoencoders that have been trained on state sequences from previously discovered policies.

Policy Gradient Methods

Sim-to-Real Transfer for Biped Locomotion

no code implementations4 Mar 2019 Wenhao Yu, Visak CV Kumar, Greg Turk, C. Karen Liu

We present a new approach for transfer of dynamic robot control policies such as biped locomotion from simulation to real hardware.

Bayesian Optimization Friction

Policy Transfer with Strategy Optimization

1 code implementation ICLR 2019 Wenhao Yu, C. Karen Liu, Greg Turk

Transfer learning using domain randomization is a promising approach, but it usually assumes that the target environment is close to the distribution of the training environments, thus relying heavily on accurate system identification.

Transfer Learning

Learning Symmetric and Low-energy Locomotion

2 code implementations24 Jan 2018 Wenhao Yu, Greg Turk, C. Karen Liu

Indeed, a standard benchmark for DRL is to automatically create a running controller for a biped character from a simple reward function.

Multi-task Learning with Gradient Guided Policy Specialization

no code implementations23 Sep 2017 Wenhao Yu, C. Karen Liu, Greg Turk

Then, during the specialization training stage we selectively split the weights of the policy based on a per-weight metric that measures the disagreement among the multiple tasks.

Multi-Task Learning

Preparing for the Unknown: Learning a Universal Policy with Online System Identification

1 code implementation8 Feb 2017 Wenhao Yu, Jie Tan, C. Karen Liu, Greg Turk

Together, UP-OSI is a robust control policy that can be used across a wide range of dynamic models, and that is also responsive to sudden changes in the environment.

Friction

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