Search Results for author:
Found 41 papers, 16 papers with code
XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library
In this paper, we present XuanCe, a comprehensive and unified deep reinforcement learning (DRL) library designed to be compatible with PyTorch, TensorFlow, and MindSpore.
X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
Vision language pre-training aims to learn alignments between vision and language from a large amount of data.
Ranked #1 on
Cross-Modal Retrieval
on Flickr30k
(using extra training data)
Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models Memories
Pre-trained language models (PLMs) demonstrate excellent abilities to understand texts in the generic domain while struggling in a specific domain.
Write and Paint: Generative Vision-Language Models are Unified Modal Learners
In this work, we disclose the potential of symmetric generative vision-language pre-training in learning to write and paint concurrently, and propose a new unified modal model, named DaVinci, trained with prefix language modeling and prefix image modeling, a simple generative self-supervised objective on image-text pairs.
DeeP-LCC: Data-EnablEd Predictive Leading Cruise Control in Mixed Traffic Flow
For the control of connected and autonomous vehicles (CAVs), most existing methods focus on model-based strategies.
Implementation and Experimental Validation of Data-Driven Predictive Control for Dissipating Stop-and-Go Waves in Mixed Traffic
In this paper, we present the first experimental results of data-driven predictive control for connected and autonomous vehicles (CAVs) in dissipating traffic waves.
Restoring Execution Environments of Jupyter Notebooks
More than ninety percent of published Jupyter notebooks do not state dependencies on external packages.
Software Engineering
Leading Cruise Control in Mixed Traffic Flow
Numerical studies confirm the potential of LCC to strengthen the capability of CAVs in suppressing traffic instabilities and smoothing traffic flow.
Systems and Control Systems and Control Optimization and Control
Leading Cruise Control in Mixed Traffic Flow: System Modeling, Controllability, and String Stability
Most existing strategies for CAVs' longitudinal control focus on downstream traffic conditions, but neglect the impact of CAVs' behaviors on upstream traffic flow.
Recall and Learn: A Memory-augmented Solver for Math Word Problems
Specifically, given a math word problem, the model first retrieves similar questions by a memory module and then encodes the unsolved problem and each retrieved question using a representation module.
Ranked #7 on
Math Word Problem Solving
on Math23K
Multi-lane Unsignalized Intersection Cooperation with Flexible Lane Direction based on Multi-vehicle Formation Control
Unsignalized intersection cooperation of connected and automated vehicles (CAVs) is able to eliminate green time loss of signalized intersections and improve traffic efficiency.
Distributed data-driven predictive control for cooperatively smoothing mixed traffic flow
This algorithm achieves both computation and communication efficiency, as well as trajectory data privacy, through parallel calculation.
Detect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysis
Our end-to-end system achieves state-of-the-art performance on two large-scale document layout analysis datasets (PubLayNet and DocLayNet), a high-quality hierarchical document structure reconstruction dataset (HRDoc), and our Comp-HRDoc benchmark.
Formation Control for Connected and Automated Vehicles on Multi-lane Roads: Relative Motion Planning and Conflict Resolution
Multi-vehicle coordinated decision making and control can improve traffic efficiency while guaranteeing driving safety.
ArT: All-round Thinker for Unsupervised Commonsense Question-Answering
In detail, our model first focuses on key parts in the given context, and then generates highly related knowledge on such a basis in an association way like human thinking.
ArT: All-round Thinker for Unsupervised Commonsense Question Answering
ArT is totally unsupervised and KBs-free.
An Unsupervised Feature Learning Approach to Improve Automatic Incident Detection
Sophisticated automatic incident detection (AID) technology plays a key role in contemporary transportation systems.
Exploring The Contribution of Unlabeled Data in Financial Sentiment Analysis
We argue that if the bias-variance trade-off is to be better balanced by a more effective feature selection method unlabeled data is very likely to boost the classification performance.
Domain Confusion with Self Ensembling for Unsupervised Adaptation
Data collection and annotation are time-consuming in machine learning, expecially for large scale problem.
Efficient Connected and Automated Driving System with Multi-agent Graph Reinforcement Learning
Instead of learning a reliable behavior for ego automated vehicle, we focus on how to improve the outcomes of the total transportation system by allowing each automated vehicle to learn cooperation with each other and regulate human-driven traffic flow.
NeuroDiff: Scalable Differential Verification of Neural Networks using Fine-Grained Approximation
Unfortunately, existing methods either focus on verifying a single network or rely on loose approximations to prove the equivalence of two networks.
Cooperative Formation of Autonomous Vehicles in Mixed Traffic Flow: Beyond Platooning
In mixed traffic flow consisting of AVs and human-driven vehicles (HDVs), the prevailing platooning of multiple AVs is not the only choice for cooperative formation.
Reducing Bus Bunching with Asynchronous Multi-Agent Reinforcement Learning
However, due to the significant uncertainties in passenger demand and traffic conditions, bus operation is unstable in nature and bus bunching has become a common phenomenon that undermines the reliability and efficiency of bus services.
Decouple and Reconstruct: Mining Discriminative Features for Cross-domain Object Detection
In recent years, a great progress has been witnessed for cross-domain object detection.
Data-Driven Predictive Control for Connected and Autonomous Vehicles in Mixed Traffic
In this paper, instead of relying on a parametric car-following model, we introduce a data-driven predictive control strategy to achieve safe and optimal control for CAVs in mixed traffic.
Robust Dynamic Bus Control: A Distributional Multi-agent Reinforcement Learning Approach
However, the operation of a bus fleet is unstable in nature, and bus bunching has become a common phenomenon that undermines the efficiency and reliability of bus systems.
What If Sentence-hood is Hard to Define: A Case Study in Chinese Reading Comprehension
Machine reading comprehension (MRC) is a challenging NLP task for it requires to carefully deal with all linguistic granularities from word, sentence to passage.
Chinese Reading Comprehension
Machine Reading Comprehension
+1
Experimental Validation of Multi-lane Formation Control for Connected and Automated Vehicles in Multiple Scenarios
Formation control methods of connected and automated vehicles have been proposed to smoothly switch the structure of vehicular formations in different scenarios.
CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training
Specifically, we first extract multiple code views using compiler tools, and learn the complementary information among them under a contrastive learning framework.
Single-species population models with age structure and psychological effect in a polluted environment
The role of psychological effects makes the contact between adult and environmental toxins a functional form, while the contact between larvae and environmental toxins is linear.
TSRFormer: Table Structure Recognition with Transformers
We present a new table structure recognition (TSR) approach, called TSRFormer, to robustly recognizing the structures of complex tables with geometrical distortions from various table images.
Ranked #2 on
Table Recognition
on PubTabNet
(TEDS-Struct metric)
Robust Table Structure Recognition with Dynamic Queries Enhanced Detection Transformer
Unlike previous methods, we formulate table separation line prediction as a line regression problem instead of an image segmentation problem and propose a new two-stage dynamic queries enhanced DETR based separation line regression approach, named DQ-DETR, to predict separation lines from table images directly.
Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective
MOBA games, e. g., Dota2 and Honor of Kings, have been actively used as the testbed for the recent AI research on games, and various AI systems have been developed at the human level so far.
Information Flow Topology in Mixed Traffic: A Comparative Study between "Looking Ahead" and "Looking Behind"
In mixed traffic where human-driven vehicles (HDVs) also exist, existing research mostly focuses on "looking ahead" (i. e., the CAVs receive information from preceding vehicles) strategies for CAVs, while recent work reveals that "looking behind" (i. e., the CAVs receive information from their rear vehicles) strategies might provide more possibilities for CAV longitudinal control.
Learning Optimal Robust Control of Connected Vehicles in Mixed Traffic Flow
Connected and automated vehicles (CAVs) technologies promise to attenuate undesired traffic disturbances.
ContextSeg: Sketch Semantic Segmentation by Querying the Context with Attention
Sketch semantic segmentation is a well-explored and pivotal problem in computer vision involving the assignment of pre-defined part labels to individual strokes.
Dynamic Relation Transformer for Contextual Text Block Detection
Contextual Text Block Detection (CTBD) is the task of identifying coherent text blocks within the complexity of natural scenes.
UniVIE: A Unified Label Space Approach to Visual Information Extraction from Form-like Documents
This unified approach allows for the definition of various relation types and effectively tackles hierarchical relationships in form-like documents.
Boximator: Generating Rich and Controllable Motions for Video Synthesis
Its robust motion controllability is validated by drastic increases in the bounding box alignment metric.
Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation
The key technical contribution is a novel LLM agent framework that accounts for individual activity patterns and motivations, including a self-consistency approach to align LLMs with real-world activity data and a retrieval-augmented strategy for interpretable activity generation.
EM-TTS: Efficiently Trained Low-Resource Mongolian Lightweight Text-to-Speech
Recurrent neural networks have become a standard modeling technique for sequential data in TTS systems and are widely used.
