The evolution from Large Language Models (LLMs) to Multimodal Large Language Models (MLLMs) has spurred research into extending In-Context Learning (ICL) to its multimodal counterpart. Existing such studies have primarily concentrated on image-to-text ICL. However, the Text-to-Image ICL (T2I-ICL), with its unique characteristics and potential applications, remains underexplored. To address this gap, we formally define the task of T2I-ICL and present CoBSAT, the first T2I-ICL benchmark dataset, encompassing ten tasks. Utilizing our dataset to benchmark six state-of-the-art MLLMs, we uncover considerable difficulties MLLMs encounter in solving T2I-ICL. We identify the primary challenges as the inherent complexity of multimodality and image generation, and show that strategies such as fine-tuning and Chain-of-Thought prompting help to mitigate these difficulties, leading to notable improvements in performance. Our code and dataset are available at https://github.com/UW-Madison-Lee-Lab/CoBSAT.
Can Multimodal Large Language Model Think Analogically?
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Shandong Institutes of Industrial Technology（山东产业技术研究院）
Traj-MLLM: Can Multimodal Large Language Models Reform Trajectory Data Mining?
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Department of Computer Science, Aalborg University（奥胡斯大学计算机科学系）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）
The Instinctive Bias: Spurious Images lead to Illusion in MLLMs
The Hong Kong Polytechnic University（香港理工大学）；The Hong Kong University of Science and Technology（香港科技大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；NVIDIA（英伟达）
VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation
Southern University of Science and Technology（南方科技大学）；Microsoft Research Asia（微软亚洲研究院）；Shanghai University of Finance and Economics（上海财经大学）；Peking University（北京大学）
Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning
College of AI, Tsinghua University, Beijing, China（清华大学人工智能学院，北京，中国）；Shanghai Artificial Intelligence Laboratory, Shanghai, China（上海人工智能实验室，上海，中国）；The University of Tokyo, Tokyo, Japan（东京大学，东京，日本）
An Evaluation of Interleaved Instruction Tuning on Semantic Reasoning Performance in an Audio MLLM
The Graduate Center, CUNY（CUNY研究生中心）；Brooklyn College, CUNY（CUNY布鲁克林学院）；Borough of Manhattan Community College, CUNY（CUNY曼哈顿社区学院）；The City College of New York, CUNY（CUNY纽约城市学院）
Is Our Benchmark Enough? An Analysis of Continual Learning for MLLMs
School of Computer Science and Statistics, Trinity College Dublin（都柏林圣三一学院计算机科学与统计学院）；Department of Mathematics and Computer Science, Eindhoven University of Technology（埃因霍温理工大学数学与计算机科学系）
Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification
College of Computer Science, Sichuan University（四川大学计算机学院）；National Key Laboratory of Fundamental Algorithms and Models for Engineering Simulation, Sichuan University（四川大学国家工程仿真基础算法与模型重点实验室）；Sichuan National Innovation New Vision UHD Video Technology Co., Ltd（四川国家创新新视觉超高清视频技术有限公司）；Tianfu Jincheng Laboratory（天府锦城实验室）
MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering
University of Science and Technology of China（中国科学技术大学）；National University of Singapore（新加坡国立大学）；The Hong Kong Polytechnic University（香港理工大学）；Huawei（华为）
