← Search

Mingchen Cai

2 accepted papers

2025

What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning

COLING 2025main

Visual instruction tuning is crucial for enhancing the zero-shot generalization capability of Multi-modal Large Language Models (MLLMs). In this paper, we aim to investigate a fundamental question: “what makes for good visual instructions”. Through a comprehensive empirical study, we find that instr…

2024

PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine

AAAI 2024technical

As an effective tool for eliciting the power of Large Language Models (LLMs), prompting has recently demonstrated unprecedented abilities across a variety of complex tasks. To further improve the performance, prompt ensemble has attracted substantial interest for tackling the hallucination and insta…