This repository organizes academic and practical resources focused on hallucination in multimodal large language models (MLLM) or large vision-language models (LVLM). Hallucination here refers to generated text that is nonsensical or unfaithful to the source content, including factual errors or instruction violations. The collection includes a comprehensive 40-page survey with 228 references covering root causes, training-free mitigations, contrastive decoding, and RL-based solutions.