Picture for Xiaomeng Yang

Xiaomeng Yang

IPO: Iterative Preference Optimization for Text-to-Video Generation

Add code
Feb 05, 2025
Figure 1 for IPO: Iterative Preference Optimization for Text-to-Video Generation
Figure 2 for IPO: Iterative Preference Optimization for Text-to-Video Generation
Figure 3 for IPO: Iterative Preference Optimization for Text-to-Video Generation
Figure 4 for IPO: Iterative Preference Optimization for Text-to-Video Generation
Viaarxiv icon

Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2

Add code
Feb 05, 2025
Viaarxiv icon

LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment

Add code
Dec 06, 2024
Viaarxiv icon

VidGen-1M: A Large-Scale Dataset for Text-to-video Generation

Add code
Aug 05, 2024
Viaarxiv icon

EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models

Add code
Jun 27, 2024
Viaarxiv icon

EvalAlign: Evaluating Text-to-Image Models through Precision Alignment of Multimodal Large Models with Supervised Fine-Tuning to Human Annotations

Add code
Jun 24, 2024
Viaarxiv icon

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

Add code
Apr 12, 2024
Viaarxiv icon

IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognition

Add code
Dec 19, 2023
Viaarxiv icon

End-to-end Story Plot Generator

Add code
Oct 13, 2023
Viaarxiv icon

Learning Personalized Story Evaluation

Add code
Oct 10, 2023
Viaarxiv icon