The ChatGPT Images 2.0 model is here. Our testing shows it's better at creating more detailed images and rendering text, but it still struggles with languages other than English. OpenAI launched a new image generation AI model on Tuesday, dubbed ChatGPT Images 2.0. This model can generate more than one image from a single prompt, like an entire study booklet, as well as output text, including in non-English languages, like Chinese and Hindi. This release is available globally for ChatGPT and Codex users, with a more powerful version available for paying subscribers.

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. To overcome these challenges, we explore strategies like fine-tuning and Chain-of-Thought prompting, demonstrating notable improvements. Our code and dataset are available at \url{https://github.com/UW-Madison-Lee-Lab/CoBSAT}.

Moreover, to obtain (VTSs) have recently been developed to improve tactile a high-resolution image using a less sensitive GelSight sensor perception via high-resolution visual information [1]. VTSs (i.e., having a high thickness and stiffness gel layer), often can provide high-resolution 3D visual image reconstruction a higher interaction force is required to deform the gel layer and localization of the interacting objects by capturing tiny and obtain high-resolution images. Of note, this might not deformations of an elastic gel layer that directly interacts be feasible for several applications (e.g., high-fidelity manipulation with the objects' surface [2]. GelSight is the most wellknown of fragile objects [12] and surgical applications [13]- VTS, developed by Johnson and Adelson [3], and has [15] and may damage the sensor and reduce its durability.

Physical simulation-based optimization is a common task in science and engineering. Many such simulations produce image- or tensor-based outputs where the desired objective is a function of those outputs, and optimization is performed over a high-dimensional parameter space. We develop a Bayesian optimization method leveraging tensor-based Gaussian process surrogates and trust region Bayesian optimization to effectively model the image outputs and to efficiently optimize these types of simulations, including a radio-frequency tower configuration problem and an optical design problem.