上海大学未来技术学院
πR²团队
“科技不是一种命运,而是一种选择。”
— 查尔斯·范恩 (Charles Van Doren)
Commonsense Knowledge
常识知识推理与问答
- 常识知识驱动下的问答任务
- 视觉对话的可控回复与生成
- 多模态知识图谱构建与应用
Large Language Model
基于大语言模型的应用
- 多模态信息感知与环境交互
- 领域大语言模型构建与应用
- 基于大语言模型3D场景生成
- 基于大语言模型的任务规划
Explainable Artificial Intelligence
可解释的人工智能
- 尝试将先进的数学理论融入到AI
- 致力于为黑盒模型提供可解释性
- 期待着数学与AI更加激烈的碰撞
课题组新闻
- 2024.12.07 恭喜课题组杨建明论文《CooKie: commonsense knowledge-guided mixture-of-experts framework for fine-grained visual question answering》被Information Sciences期刊（中科院1区Top）录用！
- 2024.11.12 喜报！恭喜团队2只队伍荣获“第二十一届中国研究生数学建模竞赛”二等奖！
- 2024.10.23 课题组论文《Answering, fast and slow: Strategy enhancement of visual understanding guided by causality》被Neurocomputing期刊（中科院2区Top,中国人工智能学会B类）录用！
- 2024.07.25 课题组与华东理工大学、复旦大学等机构合作的论文A Crossword Solving System Based on Monte Carlo Tree Search被人工智能领域旗舰期刊Artificial Intelligence发表
- 2024.8.15 课题组与复旦大学、华东理工大学合作的论文Don’t Ignore the Drive of Curiosity: Rethinking Subtleties Between Universality of Commonsense Knowledge and Excellence of Large Language Models 被跨学科期刊SN Computer Science发表，研究旨在探究常识知识与大语言模型之间的微妙关系。
- 课题组与复旦大学、华东理工大学合作的文章Exploiting Duality in Aspect Sentiment Triplet Extraction with Sequential Prompting 被人工智能A类期刊 IEEE Transactions on Knowledge and Data Engineering 发表
- 课题组与复旦大学、华东理工大学合作的文章《Beyond Entities: A Large-Scale Multi-Modal Knowledge Graph with Triplet Fact Grounding》被人工智能A类顶会 AAAI2024 发表
- 恭喜课题组成员何晴论文《Selective Arguments Representation with Dual Relation-Aware Network for Video Situation Recognition》被Neural Computing and Applications 录用
- 恭喜课题组成员孙怡敏论文《Reducing Hallucinations: Enhancing VQA for Flood Disaster Damage Assessment with Visual Contexts》被CAICE 2024 录用
- 恭喜课题组成员刘成论文《IMCN: Improved modular co-attention networks for visual question answering》被Applied Intelligence录用
- 恭喜课题组成员黄铮论文《EGLR: Two-staged Explanation Generation and Language Reasoning Framework for Commonsense Question Answering》被Knowledge-Based Systems录用
- 恭喜课题组成员张元论文《Leave It to Large Language Models! Correct and Planning with Memory Integration》被Cyborg and Bionic Systems录用
- 恭喜课题组成员曹龙辉论文《Enhancing Language-Conditioned Policy Generalization with Behavioral Information》被Cyborg and Bionic Systems录用