Picture for Liwei Chen

Liwei Chen

RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance

Add code
May 23, 2024
Figure 1 for RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
Figure 2 for RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
Figure 3 for RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
Figure 4 for RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
Viaarxiv icon

Harder Tasks Need More Experts: Dynamic Routing in MoE Models

Add code
Mar 12, 2024
Figure 1 for Harder Tasks Need More Experts: Dynamic Routing in MoE Models
Figure 2 for Harder Tasks Need More Experts: Dynamic Routing in MoE Models
Figure 3 for Harder Tasks Need More Experts: Dynamic Routing in MoE Models
Figure 4 for Harder Tasks Need More Experts: Dynamic Routing in MoE Models
Viaarxiv icon

Probing Multimodal Large Language Models for Global and Local Semantic Representation

Feb 27, 2024
Figure 1 for Probing Multimodal Large Language Models for Global and Local Semantic Representation
Figure 2 for Probing Multimodal Large Language Models for Global and Local Semantic Representation
Figure 3 for Probing Multimodal Large Language Models for Global and Local Semantic Representation
Figure 4 for Probing Multimodal Large Language Models for Global and Local Semantic Representation
Viaarxiv icon

Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization

Add code
Feb 06, 2024
Viaarxiv icon

A Step Closer to Comprehensive Answers: Constrained Multi-Stage Question Decomposition with Large Language Models

Add code
Nov 13, 2023
Figure 1 for A Step Closer to Comprehensive Answers: Constrained Multi-Stage Question Decomposition with Large Language Models
Figure 2 for A Step Closer to Comprehensive Answers: Constrained Multi-Stage Question Decomposition with Large Language Models
Figure 3 for A Step Closer to Comprehensive Answers: Constrained Multi-Stage Question Decomposition with Large Language Models
Figure 4 for A Step Closer to Comprehensive Answers: Constrained Multi-Stage Question Decomposition with Large Language Models
Viaarxiv icon

Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization

Add code
Sep 29, 2023
Figure 1 for Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Figure 2 for Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Figure 3 for Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Figure 4 for Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Viaarxiv icon

In-situ monitoring additive manufacturing process with AI edge computing

Jan 02, 2023
Figure 1 for In-situ monitoring additive manufacturing process with AI edge computing
Figure 2 for In-situ monitoring additive manufacturing process with AI edge computing
Figure 3 for In-situ monitoring additive manufacturing process with AI edge computing
Figure 4 for In-situ monitoring additive manufacturing process with AI edge computing
Viaarxiv icon

Encoding Implicit Relation Requirements for Relation Extraction: A Joint Inference Approach

Nov 09, 2018
Figure 1 for Encoding Implicit Relation Requirements for Relation Extraction: A Joint Inference Approach
Figure 2 for Encoding Implicit Relation Requirements for Relation Extraction: A Joint Inference Approach
Figure 3 for Encoding Implicit Relation Requirements for Relation Extraction: A Joint Inference Approach
Figure 4 for Encoding Implicit Relation Requirements for Relation Extraction: A Joint Inference Approach
Viaarxiv icon

SQL-to-Text Generation with Graph-to-Sequence Model

Add code
Sep 14, 2018
Figure 1 for SQL-to-Text Generation with Graph-to-Sequence Model
Figure 2 for SQL-to-Text Generation with Graph-to-Sequence Model
Figure 3 for SQL-to-Text Generation with Graph-to-Sequence Model
Figure 4 for SQL-to-Text Generation with Graph-to-Sequence Model
Viaarxiv icon

Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model

Add code
Aug 23, 2018
Figure 1 for Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
Figure 2 for Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
Figure 3 for Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
Figure 4 for Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
Viaarxiv icon