Picture for Zhendong Mao

Zhendong Mao

LIRE: listwise reward enhancement for preference alignment

Add code
May 22, 2024
Figure 1 for LIRE: listwise reward enhancement for preference alignment
Figure 2 for LIRE: listwise reward enhancement for preference alignment
Figure 3 for LIRE: listwise reward enhancement for preference alignment
Figure 4 for LIRE: listwise reward enhancement for preference alignment
Viaarxiv icon

Feature-Adaptive and Data-Scalable In-Context Learning

Add code
May 17, 2024
Viaarxiv icon

Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting

Add code
Apr 19, 2024
Figure 1 for Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting
Figure 2 for Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting
Figure 3 for Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting
Figure 4 for Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting
Viaarxiv icon

Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation

Add code
Apr 05, 2024
Figure 1 for Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
Figure 2 for Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
Figure 3 for Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
Figure 4 for Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
Viaarxiv icon

RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization

Add code
Mar 01, 2024
Figure 1 for RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
Figure 2 for RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
Figure 3 for RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
Figure 4 for RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
Viaarxiv icon

Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing

Add code
Feb 22, 2024
Viaarxiv icon

Benchmarking Large Language Models on Controllable Generation under Diversified Instructions

Add code
Jan 01, 2024
Figure 1 for Benchmarking Large Language Models on Controllable Generation under Diversified Instructions
Figure 2 for Benchmarking Large Language Models on Controllable Generation under Diversified Instructions
Figure 3 for Benchmarking Large Language Models on Controllable Generation under Diversified Instructions
Figure 4 for Benchmarking Large Language Models on Controllable Generation under Diversified Instructions
Viaarxiv icon

Improving Image Captioning via Predicting Structured Concepts

Add code
Nov 28, 2023
Viaarxiv icon

E-CORE: Emotion Correlation Enhanced Empathetic Dialogue Generation

Add code
Nov 25, 2023
Viaarxiv icon

Grammatical Error Correction via Mixed-Grained Weighted Training

Add code
Nov 23, 2023
Viaarxiv icon