In recent years, predicting Big Five personality traits from multimodal data has received significant attention in artificial intelligence (AI). However, existing computational models often fail to achieve satisfactory performance. Psychological research has shown a strong correlation between pose and personality traits, yet previous research has largely ignored pose data in computational models. To address this gap, we develop a novel multimodal dataset that incorporates full-body pose data. The dataset includes video recordings of 287 participants completing a virtual interview with 36 questions, along with self-reported Big Five personality scores as labels. To effectively utilize this multimodal data, we introduce the Psychology-Inspired Network (PINet), which consists of three key modules: Multimodal Feature Awareness (MFA), Multimodal Feature Interaction (MFI), and Psychology-Informed Modality Correlation Loss (PIMC Loss). The MFA module leverages the Vision Mamba Block to capture comprehensive visual features related to personality, while the MFI module efficiently fuses the multimodal features. The PIMC Loss, grounded in psychological theory, guides the model to emphasize different modalities for different personality dimensions. Experimental results show that the PINet outperforms several state-of-the-art baseline models. Furthermore, the three modules of PINet contribute almost equally to the model’s overall performance. Incorporating pose data significantly enhances the model’s performance, with the pose modality ranking mid-level in importance among the five modalities. These findings address the existing gap in personality-related datasets that lack full-body pose data and provide a new approach for improving the accuracy of personality prediction models, highlighting the importance of integrating psychological insights into AI frameworks.

Human feedback is crucial in the interactions between humans and Large Language Models (LLMs). However, existing research primarily focuses on benchmarking LLMs in single-turn dialogues. Even in benchmarks designed for multi-turn dialogues, the user utterances are often independent, neglecting the nuanced and complex nature of human feedback within real-world usage scenarios. To fill this research gap, we introduce FB-Bench, a fine-grained, multi-task benchmark designed to evaluate LLMs’ responsiveness to human feedback under real-world usage scenarios in Chinese. Drawing from the two main interaction scenarios, FB-Bench comprises 591 meticulously curated samples, encompassing eight task types, five deficiency types of response, and nine feedback types. We extensively evaluate a broad array of popular LLMs, revealing significant variations in their performance across different interaction scenarios. Further analysis indicates that task, human feedback, and deficiencies of previous responses can also significantly impact LLMs’ responsiveness. Our findings underscore both the strengths and limitations of current models, providing valuable insights and directions for future research.

In recent years, the rise of Large Language Models (LLMs) has spurred a growing demand for plug-and-play AI systems. Among the various AI techniques, prompt engineering stands out as particularly significant. However, users often face challenges in writing prompts due to the steep learning curve and significant time investment, and existing automatic prompt engineering (APE) models can be difficult to use. To address this issue, we propose PAS, an LLM-based plug-and-play APE system. PAS utilizes LLMs trained on high-quality, automatically generated prompt augmentation datasets, resulting in exceptional performance. In comprehensive benchmarks, PAS achieves state-of-the-art (SOTA) results compared to previous APE models, with an average improvement of 6.09 points. Moreover, PAS is highly efficient, achieving SOTA performance with only 9000 data points. Additionally, PAS can autonomously generate prompt augmentation data without requiring additional human labor. Its flexibility also allows it to be compatible with all existing LLMs and applicable to a wide range of tasks. Moreover, we deployed PAS for Baichuan online model, and then tested PAS using internal human evaluations in Baichuan underscoring its strong performance. This combination of high performance, efficiency, and flexibility makes PAS a valuable system for enhancing the usability and effectiveness of LLMs through automatic prompt engineering. The codebase is available at https://github.com/PKU-Baichuan-MLSystemLab/PAS.

Zehui Chen, Weihua Du, Wenwei Zhang, Kuikun Liu, Jiangning Liu, Miao Zheng, Jingming Zhuo, Songyang Zhang, Dahua Lin, Kai Chen, Feng Zhao. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Based on actor-critic neural networks (NNs), an optimal controller is proposed for solving the constrained control problem of an affine nonlinear discrete-time system with disturbances. The actor NNs provide the control signals and the critic NNs work as the performance indicators of the controller. By converting the original state constraints into new input constraints and state constraints, the penalty functions are introduced into the cost function, and then the constrained optimal control problem is transformed into an unconstrained one. Further, the relationship between the optimal control input and worst-case disturbance is obtained using the Game theory. With Lyapunov stability theory, the control signals are ensured to be uniformly ultimately bounded (UUB). Finally, the effectiveness of the control algorithms is tested through a numeral simulation using a third-order dynamic system.

Wheeled mobile robots (WMRs) with variable wheelbases are capable of traveling on deformable terrains and handling complex detection tasks. While the variable wheelbase length of WMR allows it to interact with the terrains adaptively, enhancing its mobility, it brings a control challenge. Inspired by the worm's movement of stretching body at different lengths under different environmental resistance, a creeping gait (CG) strategy is proposed in this work to enable the WMR to be controlled in dual modes: wheeled following mode (WFM) and specified length mode (SLM). WFM adjusts the wheelbase's length by the wheels' movements freely to minimize the internal force and torque between wheels. SLM adjusts the wheelbase's length using a proposed fuzzy logic based algorithm to stabilize the body's posture on rough terrain and overcome specific motion challenges, like escaping wheel sinking. A state-adaptive mode-switching controller is then developed using the dwell time approach to smooth the output velocities during the switching phase, and a Lyapunov analysis is performed to verify its stability. According to the results of physical experiments, three-wheeled mobile robot movements with CG enable more precise path following by 37% and faster response by 11% compared to fixed wheelbase movements, and the dwell time approach achieves smoother speed transitions between the modes than the direct switching method, especially when moving from flat to slope terrain.

In unsupervised domain adaptation (UDA), directly adapting from the source to the target domain usually suffers significant discrepancies and leads to insufficient alignment. Thus, many UDA works attempt to vanish the domain gap gradually and softly via various intermediate spaces, dubbed domain bridging (DB). However, for dense prediction tasks such as domain adaptive semantic segmentation (DASS), existing solutions have mostly relied on rough style transfer and how to elegantly bridge domains is still under-explored. In this work, we resort to data mixing to establish a deliberated domain bridging (DDB) for DASS, through which the joint distributions of source and target domains are aligned and interacted with each in the intermediate space. At the heart of DDB lies a dual-path domain bridging step for generating two intermediate domains using the coarse-wise and the fine-wise data mixing techniques, alongside a cross-path knowledge distillation step for taking two complementary models trained on generated intermediate samples as ‘teachers’ to develop a superior ‘student’ in a multi-teacher distillation manner. These two optimization steps work in an alternating way and reinforce each other to give rise to DDB with strong adaptation power. Extensive experiments on adaptive segmentation tasks with different settings demonstrate that our DDB significantly outperforms state-of-the-art methods.

This paper proposes a method for the overall optimization of smart city (SC). The proposed method is based on multi-population global-best brain storm optimization using cooperative coevolution (MP-CCGBSO). Using a SC model, energy cost, actual power loads during peak periods, and carbon dioxide emission can be minimized. For the SC problem, many researchers have proposed various evolutionary algorithms including CCGBSO, which applied cooperative coevolution to GBSO. However, there is still room to improve quality of the solution by CCGBSO. Taking Toyama city of Japan as the research object, the calculation results of original CCGBSO method and the proposed MP-CCGBSO method of 2, 4, 8 and 16 populations are compared.

With the rapidly increasing number of personal image collections on the web, it is of great importance to annotate these user-uploaded images in personalized manner. But personalized image annotation is largely ignored by the mainstream of image annotation research. In this paper, we focus on personalizing the automatic image annotation by proposing a general framework which jointly exploits the generic content-based image annotation, personal image tagging history and the content of personal history images. In our framework, two sets of candidate annotations are extracted for each image based on content-based annotation and personal image tagging history. Considering that the user's interest may not stay the same, when exploiting the personal image tagging history, we also take the content of personal history images into account to avoid the noise. To get the final annotations, we propose an unsupervised algorithm based on reinforcement learning to combine the above two candidate annotation sets. Encouraging results show that the proposed framework is effective and promising for personalizing automatic image annotation.

Sparse coding has received an increasing amount of interest in recent years. It is an unsupervised learning algorithm, which finds a basis set capturing high-level semantics in the data and learns sparse coordinates in terms of the basis set. Originally applied to modeling the human visual cortex, sparse coding has been shown useful for many applications. However, most of the existing approaches to sparse coding fail to consider the geometrical structure of the data space. In many real applications, the data is more likely to reside on a low-dimensional submanifold embedded in the high-dimensional ambient space. It has been shown that the geometrical information of the data is important for discrimination. In this paper, we propose a graph based algorithm, called graph regularized sparse coding, to learn the sparse representations that explicitly take into account the local manifold structure of the data. By using graph Laplacian as a smooth operator, the obtained sparse representations vary smoothly along the geodesics of the data manifold. The extensive experimental results on image classification and clustering have demonstrated the effectiveness of our proposed algorithm.