Output

• RepoAwesome Any-to-Any Multimodal Generation — curated resources on any-to-any multimodal generation.
• RepoAwesome Scene Graph Generation & Application — papers and resources on scene graphs.
• RepoAwesome Multimodal Chain-of-Thought — companion to the MM-CoT survey.
• RepoAwesome Audio-Visual Intelligence — companion to the AVI survey.
• RepoNExT-GPT — the first any-to-any multimodal large language model.
• RepoVitron — a Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing.

• 2025/03Towards Semantic Equivalence of Tokenization in Multimodal LLM. NICE.
• 2024/01The Path to AGI: Achieving Modality Unification with NExT-GPT. Qingyuan Talk.
• 2023/12NExT-GPT: Any-to-Any Multimodal LLM. AI New Youth.
• 2022/12Deep Learning based Natural Language Processing: A Survey and Outlook. Jianghan University, China.
• 2021/10Comparison of Aspect-based Sentiment Analysis based on span and transition models. Wuhan University, China.
• 2021/05Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extraction with Rich Syntactic Knowledge. CIPS Youth Working Committee.

• 2024-2025 SpringMultimedia Analysis. School of Computing, NUS.
• 2024-2025 Autumn & SpringBig Data Systems for Data Science. School of Computing, NUS.
• 2023-2024 Autumn & SpringBig Data Systems for Data Science. School of Computing, NUS.
• 2021 Spring & AutumnPublic Opinion Analysis. School of CSE, WHU.

• Meng Luo
• Zongru Wu
• Baoming Yang
• Pengcheng Zhou
• Minghui Guo