Picture for Jiapeng Wang

Jiapeng Wang

School of Information and Communication Engineering, Xidian University, Xi'an, China

LLMBox: A Comprehensive Library for Large Language Models

Add code
Jul 08, 2024
Viaarxiv icon

JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models

Add code
May 23, 2024
Figure 1 for JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
Figure 2 for JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
Figure 3 for JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
Figure 4 for JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
Viaarxiv icon

Fighter flight trajectory prediction based on spatio-temporal graphcial attention network

Add code
May 13, 2024
Viaarxiv icon

DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation

Add code
Mar 08, 2024
Figure 1 for DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation
Figure 2 for DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation
Figure 3 for DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation
Figure 4 for DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation
Viaarxiv icon

PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction

Add code
Jan 07, 2024
Viaarxiv icon

Revisiting Scene Text Recognition: A Data Perspective

Add code
Jul 19, 2023
Figure 1 for Revisiting Scene Text Recognition: A Data Perspective
Figure 2 for Revisiting Scene Text Recognition: A Data Perspective
Figure 3 for Revisiting Scene Text Recognition: A Data Perspective
Figure 4 for Revisiting Scene Text Recognition: A Data Perspective
Viaarxiv icon

ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval

Add code
May 28, 2023
Figure 1 for ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval
Figure 2 for ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval
Figure 3 for ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval
Figure 4 for ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval
Viaarxiv icon

CAP: instance complexity-aware network pruning

Add code
Sep 08, 2022
Figure 1 for CAP: instance complexity-aware network pruning
Figure 2 for CAP: instance complexity-aware network pruning
Figure 3 for CAP: instance complexity-aware network pruning
Figure 4 for CAP: instance complexity-aware network pruning
Viaarxiv icon

LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding

Add code
Feb 28, 2022
Figure 1 for LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
Figure 2 for LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
Figure 3 for LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
Figure 4 for LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding
Viaarxiv icon

MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction

Add code
Jun 24, 2021
Figure 1 for MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction
Figure 2 for MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction
Figure 3 for MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction
Figure 4 for MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction
Viaarxiv icon