Hao Yu

Hao Huang, Shuaihang Yuan, Yu Hao et al.

A large-scale vision and language model that has been pretrained on massive data encodes visual and linguistic prior, which makes it easier to generate images and language that are more natural and realistic. Despite this, there is still a significant domain gap between the modalities of vision and language, especially when training data is scarce in few-shot settings, where only very limited data are available for training. In order to mitigate this issue, a multi-modal meta-learning framework has been proposed to bridge the gap between two frozen pretrained large vision and language models by introducing a tunable prompt connecting these two large models. For few-shot image captioning, the existing multi-model meta-learning framework utilizes a one-step prompting scheme to accumulate the visual features of input images to guide the language model, which struggles to generate accurate image descriptions with only a few training samples. Instead, we propose a chain-of-thought (CoT) meta-learning scheme as a multi-step image captioning procedure to better imitate how humans describe images. In addition, we further propose to learn different meta-parameters of the model corresponding to each CoT step in distinct subspaces to avoid interference. We evaluated our method on three commonly used image captioning datasets, i.e., MSCOCO, Flickr8k, and Flickr30k, under few-shot settings. The results of our experiments indicate that our chain-of-thought subspace meta-learning strategy is superior to the baselines in terms of performance across different datasets measured by different metrics.

Hao Yu

Interacting defect systems are ubiquitous in materials under realistic scenarios, yet gaining an atomic-level understanding of these systems from a computational perspective is challenging - it often demands substantial resources due to the necessity of employing supercell calculations. While machine learning techniques have shown potential in accelerating materials simulations, their application to systems involving interacting defects remains relatively rare. In this work, we present a comparative study of three different methods to predict the free energy change of systems with interacting defects. We leveraging a limited dataset from Density Functional Theory(DFT) calculations to assess the performance models using materials descriptors, graph neural networks and cluster expansion. Our findings indicate that the cluster expansion model can achieve precise energetics predictions even with this limited dataset. Furthermore, with synthetic data generate from cluster expansion model at near-DFT levels, we obtained enlarged dataset to assess the demands on data for training accurate prediction models using graph neural networks for systems featuring interacting defects. A brief discussion of the computational cost for each method is provided at the end. This research provide a preliminary evaluation of applying machine learning techniques in imperfect surface systems.

Zhenning Li, Hao Yu, Guohui Zhang et al.

Inefficient traffic control may cause numerous problems such as traffic congestion and energy waste. This paper proposes a novel multi-agent reinforcement learning method, named KS-DDPG (Knowledge Sharing Deep Deterministic Policy Gradient) to achieve optimal control by enhancing the cooperation between traffic signals. By introducing the knowledge-sharing enabled communication protocol, each agent can access to the collective representation of the traffic environment collected by all agents. The proposed method is evaluated through two experiments respectively using synthetic and real-world datasets. The comparison with state-of-the-art reinforcement learning-based and conventional transportation methods demonstrate the proposed KS-DDPG has significant efficiency in controlling large-scale transportation networks and coping with fluctuations in traffic flow. In addition, the introduced communication mechanism has also been proven to speed up the convergence of the model without significantly increasing the computational burden.