Search Results for author:
Found 26 papers, 8 papers with code
InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
In this paper, we introduce InfiAgent-DABench, the first benchmark specifically designed to evaluate LLM-based agents on data analysis tasks.
CoachLM: Automatic Instruction Revisions Improve the Data Quality in LLM Instruction Tuning
Instruction tuning is crucial for enabling Language Learning Models (LLMs) in responding to human instructions.
Mental Health Diagnosis in the Digital Age: Harnessing Sentiment Analysis on Social Media Platforms upon Ultra-Sparse Feature Content
To address these issues, we propose a novel semantic feature preprocessing technique with a three-folded structure: 1) mitigating the feature sparsity with a weak classifier, 2) adaptive feature dimension with modulus loops, and 3) deep-mining and extending features among the contexts.
Dynamic Datasets and Market Environments for Financial Reinforcement Learning
The financial market is a particularly challenging playground for deep reinforcement learning due to its unique feature of dynamic datasets.
Deep Reinforcement Learning for Traffic Light Control in Intelligent Transportation Systems
In this paper, we investigate deep reinforcement learning to control traffic lights, and both theoretical analysis and numerical experiments show that the intelligent behavior ``greenwave" (i. e., a vehicle will see a progressive cascade of green lights, and not have to brake at any intersection) emerges naturally a grid road network, which is proved to be the optimal policy in an avenue with multiple cross streets.
KG-BERTScore: Incorporating Knowledge Graph into BERTScore for Reference-Free Machine Translation Evaluation
BERTScore is an effective and robust automatic metric for referencebased machine translation evaluation.
FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning
However, establishing high-quality market environments and benchmarks for financial reinforcement learning is challenging due to three major factors, namely, low signal-to-noise ratio of financial data, survivorship bias of historical data, and model overfitting in the backtesting stage.
XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence
To the best of our knowledge, it is the largest parallel dataset for source code both in terms of size and the number of languages.
StructCoder: Structure-Aware Transformer for Code Generation
This paper addresses the problem of code generation, where the goal is to generate target code given source code in a different language or a natural language description.
PointAugmenting: Cross-Modal Augmentation for 3D Object Detection
On one hand, PointAugmenting decorates point clouds with corresponding point-wise CNN features extracted by pretrained 2D detection models, and then performs 3D object detection over the decorated point clouds.
A Dataset And Benchmark Of Underwater Object Detection For Robot Picking
Towards these challenges we introduce a dataset, Detecting Underwater Objects (DUO), and a corresponding benchmark, based on the collection and re-annotation of all relevant datasets.
Extragalactic HI 21-cm absorption line observations with the Five-hundred-meter Aperture Spherical radio Telescope
Our observations successfully confirmed the existence of HI absorption lines in all these systems, including two sources that were marginally detected by ALFALFA.
Astrophysics of Galaxies
Convolutional Graph-Tensor Net for Graph Data Completion
Graph data completion is a fundamentally important issue as data generally has a graph structure, e. g., social networks, recommendation systems, and the Internet of Things.
Question Answering with Long Multiple-Span Answers
To this end, we present MASH-QA, a Multiple Answer Spans Healthcare Question Answering dataset from the consumer health domain, where answers may need to be excerpted from multiple, non-consecutive parts of text spanned across a long document.
Cross-Modality 3D Object Detection
In this paper, we focus on exploring the fusion of images and point clouds for 3D object detection in view of the complementary nature of the two modalities, i. e., images possess more semantic information while point clouds specialize in distance sensing.
LATTE: Latent Type Modeling for Biomedical Entity Linking
This is of significant importance in the biomedical domain, where it could be used to semantically annotate a large volume of clinical records and biomedical literature, to standardized concepts described in an ontology such as Unified Medical Language System (UMLS).
Low-light Image Enhancement Algorithm Based on Retinex and Generative Adversarial Network
In this work, the authors propose a novel approach for processing low-light images based on the Retinex theory and generative adversarial network (GAN), which is composed of the decomposition part for splitting the image into illumination image and reflected image, and the enhancement part for generating high-quality image.
Deep Reinforcement Learning for Unmanned Aerial Vehicle-Assisted Vehicular Networks
Unmanned aerial vehicles (UAVs) are envisioned to complement the 5G communication infrastructure in future smart cities.
Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutions
Underwater image enhancement is such an important low-level vision task with many applications that numerous algorithms have been proposed in recent years.
Background Subtraction with Real-time Semantic Segmentation
Our proposed framework consists of two components, a traditional BGS segmenter $\mathcal{B}$ and a real-time semantic segmenter $\mathcal{S}$.
A Robust Local Binary Similarity Pattern for Foreground Object Detection
First, we propose a robust texture operator named Robust Local Binary Similarity Pattern (RLBSP), which shows strong robustness to illumination variations and dynamic backgrounds.
Combining Background Subtraction Algorithms with Convolutional Neural Network
Accurate and fast extraction of foreground object is a key prerequisite for a wide range of computer vision applications such as object tracking and recognition.
An Online Ride-Sharing Path Planning Strategy for Public Vehicle Systems
As efficient traffic-management platforms, public vehicle (PV) systems are envisioned to be a promising approach to solving traffic congestions and pollutions for future smart cities.
Guided Filter based Edge-preserving Image Non-blind Deconvolution
In the denoising step, the guided filter is used with the two obtained images for efficient edge-preserving filtering.
Dual Domain Filters Based Texture and Structure Preserving Image Non-Blind Deconvolution
Image deconvolution continues to be an active research topic of recovering a sharp image, given a blurry one generated by a convolution.
Contractive De-noising Auto-encoder
Auto-encoder is a special kind of neural network based on reconstruction.
