Haozhe Zhao

NEP: Autoregressive Image Editing via Next Editing Token Prediction

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation

ML-Bench: Evaluating Large Language Models for Code Generation in Repository-Level Machine Learning Tasks

Selecting Influential Samples for Long Context Alignment via Homologous Models’ Guidance and Contextual Awareness Measurement

LongViTU: Instruction Tuning for Long-Form Video Understanding

MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning