Qi Zhang

7 papers University of Technology Sydney

• BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset
• Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning
• EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving
• Pre-Trained Policy Discriminators are General Reward Models
• Revealing Multimodal Causality with Large Language Models
• SEMPO: Lightweight Foundation Models for Time Series Forecasting
• Understanding Parametric and Contextual Knowledge Reconciliation within Large Language Models