Three-dimensional integration circuits (3D ICs) have become an important direction of integrated circuits, which brings in a higher integration level, higher power density, and shorter wire length. However, the heat management challenge becomes one of the key limitations for the development of 3D integration which needs desperate solutions. To address this challenge, the researchers conducted an in-depth investigation into heat transfer technologies within key structures of 3D ICs. This paper aims to review the literature on thermal management technologies, with a particular emphasis on advancements in three critical areas: thermal interface materials (TIM), through-silicon vias (TSV), and heat sink designs. Continuous research and innovation in TIM, TSV, and heat sink structures have provided diverse approaches and technical solutions for addressing thermal management issues in 3D ICs. It is expected that this review article can help researchers in academia and industry to understand the state-of-the-art of heat transfer in 3D ICs and provide better research ideas.

The emergence of ChatGPT has once again sparked research in generative artificial intelligence (GAI). While people have been amazed by the generated results, they have also noticed the reasoning potential reflected in the generated textual content. However, this current ability for causal reasoning is primarily limited to the domain of language generation, such as in models like GPT-3. In visual modality, there is currently no equivalent research. Considering causal reasoning in visual content generation is significant. This is because visual information contains infinite granularity. Particularly, images can provide more intuitive and specific demonstrations for certain reasoning tasks, especially when compared to coarse-grained text. Hence, we propose a new image generation task called visual question answering with image (VQAI) and establish a dataset of the same name based on the classic Tom and Jerry animated series. Additionally, we develop a new paradigm for image generation to tackle the challenges of this task. Finally, we perform extensive experiments and analyses, including visualizations of the generated content and discussions on the potentials and limitations. The code and data are publicly available under the license of CC BY-NC-SA 4.0 for academic and non-commercial usage at: https://github.com/IEIT-AGI/MIX-Shannon/blob/main/projects/VQAI/lgd_vqai.md.

End-to-end driving based on reinforcement learning (RL) has emerged as a promising approach in autonomous driving, with the potential to surpass human drivers. However, the exploration and exploitation dilemma of RL leads to low sample efficiency and high computational costs to train an optimal driving model, and the environment feedback-oriented learning mode limits the model's ability to handle unseen traffic scenarios, especially when dealing with the highly varied tasks of urban driving. In this paper, we proposed a context-aware meta-RL framework with two-stage constrained adaptation for challenging urban driving. Firstly, the context-aware state representation enhanced by historical behavior is construct to improve the learning efficiency and robustness, where the most efficient context encoder is selected among four different forms. Next, the end-to-end meta-driving model with high generalization ability is built through the parallel rollouts of multiple tasks and simplified meta-training procedure. Then, a two-stage constrained adaptation strategy is designed to quickly transfer the meta model to new tasks while maintaining good performance, where the meta-training data are reused through the context-based propensity estimation to constrain the optimization objective of new tasks. Extensive experiments are performed in CARLA simulator with various urban scenarios, and the results validate the superiority of our proposed models in both learning efficiency and generalization compared to state-of-the-art algorithms.