Search Results for author:
Found 19 papers, 9 papers with code
Ruleformer: Context-aware Rule Mining over Knowledge Graph
Based on this idea, we propose a transformer-based rule mining approach, Ruleformer.
Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models
While Chain of Thought (CoT) prompting approaches have significantly consolidated the reasoning capabilities of large language models (LLMs), they still face limitations that require extensive human effort or have performance needs to be improved.
Self-Supervised State Space Model for Real-Time Traffic Accident Prediction Using eKAN Networks
To address these challenges, we propose SSL-eKamba, an efficient self-supervised framework for traffic accident prediction.
An Artificial Neural Network for Image Classification Inspired by Aversive Olfactory Learning Circuits in Caenorhabditis Elegans
This study introduces an artificial neural network (ANN) for image classification task, inspired by the aversive olfactory learning circuits of the nematode Caenorhabditis elegans (C. elegans).
VITA: Towards Open-Source Interactive Omni Multimodal LLM
The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas.
AccDiffusion: An Accurate Method for Higher-Resolution Image Generation
This paper attempts to address the object repetition issue in patch-wise higher-resolution image generation.
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence
Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement Learning from Human Feedback (RLHF).
Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors
Multiple-Choice Questions (MCQs) constitute a critical area of research in the study of Large Language Models (LLMs).
Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding
To address this limitation, we propose a novel Reinforcement Learning framework enhanced with Label-sensitive Reward (RLLR) to amplify the performance of LLMs in NLU tasks.
UniRQR: A Unified Model for Retrieval Decision, Query, and Response Generation in Internet-Based Knowledge Dialogue Systems
However, many of studies assumed that all conversations require external knowledge to continue, neglecting the critical step of determining when retrieval is necessary.
Rethinking Data Perturbation and Model Stabilization for Semi-supervised Medical Image Segmentation
Studies on semi-supervised medical image segmentation (SSMIS) have seen fast progress recently.
Power System Recovery Coordinated with (Non-)Black-Start Generators
The proposed model is validated on several test systems, as well as a 1393-bus representation system of the Puerto Rican electric power grid.
Deep-Learning Tool for Early Identifying Non-Traumatic Intracranial Hemorrhage Etiology based on CT Scan
Conclusions: The proposed deep learning algorithms can be an effective tool for early identification of hemorrhage etiologies based on NCCT scans.
Deep Learning Approach to Predict Hemorrhage in Moyamoya Disease
Objective: Reliable tools to predict moyamoya disease (MMD) patients at risk for hemorrhage could have significant value.
Dynamically Retrieving Knowledge via Query Generation for Informative Dialogue Generation
To solve this problem, we design a knowledge-driven dialog system named DRKQG (Dynamically Retrieving Knowledge via Query Generation for informative dialog response).
Mixture of Virtual-Kernel Experts for Multi-Objective User Profile Modeling
This paper introduces a novel multi-task model called Mixture of Virtual-Kernel Experts (MVKE) to learn user preferences on various actions and topics unitedly.
A Combination Method for Android Malware Detection Based on Control Flow Graphs and Machine Learning Algorithms
In this paper, we present a combination method for Android malware detection based on the machine learning algorithm.
Optimizing Gross Merchandise Volume via DNN-MAB Dynamic Ranking Paradigm
With the transition from people's traditional `brick-and-mortar' shopping to online mobile shopping patterns in web 2. 0 $\mathit{era}$, the recommender system plays a critical role in E-Commerce and E-Retails.
Towards a Job Title Classification System
Document classification for text, images and other applicable entities has long been a focus of research in academia and also finds application in many industrial settings.
