arXiv subjects

Xuejing Feng

Publications and source records attributed to Xuejing Feng.

5 recordsLinked to original sources

arXiv2024

Development and Evaluation Study of Intelligent Cockpit in the Age of Large Models

The development of Artificial Intelligence (AI) Large Models has a great impact on the application development of automotive Intelligent cockpit. The fusion development of Intelligent Cockpit and Large Models has become a new growth point of user experience in the industry, which also creates problems for related scholars, practitioners and users in terms of their understanding and evaluation of the user experience and the capability characteristics of the Intelligent Cockpit Large Models (ICLM). This paper aims to analyse the current situation of Intelligent cockpit, large model and AI Agent, to reveal the key of application research focuses on the integration of Intelligent Cockpit and Large Models, and to put forward a necessary limitation for the subsequent development of an evaluation system for the capability of automotive ICLM and user experience. The evaluation system, P-CAFE, proposed in this paper mainly proposes five dimensions of perception, cognition, action, feedback and evolution as the first-level indicators from the domains of cognitive architecture, user experience, and capability characteristics of large models, and many second-level indicators to satisfy the current status of the application and research focuses are selected. After expert evaluation, the weights of the indicators were determined, and the indicator system of P-CAFE was established. Finally, a complete evaluation method was constructed based on Fuzzy Hierarchical Analysis. It will lay a solid foundation for the application and evaluation of the automotive ICLM, and provide a reference for the development and improvement of the future ICLM.

cs.HC↗

arXiv2024

Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue

Reinforcement learning (RL) is a powerful approach to enhance task-oriented dialogue (TOD) systems. However, existing RL methods tend to mainly focus on generation tasks, such as dialogue policy learning (DPL) or response generation (RG), while neglecting dialogue state tracking (DST) for understanding. This narrow focus limits the systems to achieve globally optimal performance by overlooking the interdependence between understanding and generation. Additionally, RL methods face challenges with sparse and delayed rewards, which complicates training and optimization. To address these issues, we extend RL into both understanding and generation tasks by introducing step-by-step rewards throughout the token generation. The understanding reward increases as more slots are correctly filled in DST, while the generation reward grows with the accurate inclusion of user requests. Our approach provides a balanced optimization aligned with task completion. Experimental results demonstrate that our approach effectively enhances the performance of TOD systems and achieves new state-of-the-art results on three widely used datasets, including MultiWOZ2.0, MultiWOZ2.1, and In-Car. Our approach also shows superior few-shot ability in low-resource settings compared to current models.

cs.AI↗

arXiv2024

Towards Proactive Interactions for In-Vehicle Conversational Assistants Utilizing Large Language Models

Research demonstrates that the proactivity of in-vehicle conversational assistants (IVCAs) can help to reduce distractions and enhance driving safety, better meeting users' cognitive needs. However, existing IVCAs struggle with user intent recognition and context awareness, which leads to suboptimal proactive interactions. Large language models (LLMs) have shown potential for generalizing to various tasks with prompts, but their application in IVCAs and exploration of proactive interaction remain under-explored. These raise questions about how LLMs improve proactive interactions for IVCAs and influence user perception. To investigate these questions systematically, we establish a framework with five proactivity levels across two dimensions-assumption and autonomy-for IVCAs. According to the framework, we propose a "Rewrite + ReAct + Reflect" strategy, aiming to empower LLMs to fulfill the specific demands of each proactivity level when interacting with users. Both feasibility and subjective experiments are conducted. The LLM outperforms the state-of-the-art model in success rate and achieves satisfactory results for each proactivity level. Subjective experiments with 40 participants validate the effectiveness of our framework and show the proactive level with strong assumptions and user confirmation is most appropriate.

cs.HC↗

arXiv2023

Bright solitons in a spin-orbit-coupled dipolar Bose-Einstein condensate trapped within a double-lattice

By effectively controlling the dipole-dipole interaction, we investigate the characteristics of the ground state of bright solitons in a spin-orbit coupled dipolar Bose-Einstein condensate. The dipolar atoms are trapped within a double-lattice which consists of a linear and a nonlinear lattice. We derive the motion equations of the different spin components, taking the controlling mechanisms of the diolpe-dipole interaction into account. An analytical expression of dipole-dipole interaction is derived. By adjusting the dipole polarization angle, the dipole interaction can be adjusted from attraction to repulsion. On this basis, we study the generation and manipulation of the bright solitons using both the analytical variational method and numerical imaginary time evolution. The stability of the bright solitons is also analyzed and we map out the stability phase diagram. By adjusting the long-range dipole-dipole interaction, one can achieve manipulation of bright solitons in all aspects, including the existence, width, nodes, and stability. Considering the complexity of our system, our results will have enormous potential applications in quantum simulation of complex systems.

cond-mat.quant-gas↗

arXiv2022

Symmetry-protected higher-order exceptional points in staggered flatband rhombic lattices

Higher-order exceptional points (EPs), which appear as multifold degeneracies in the spectra of non-Hermitian systems, are garnering extensive attention in various multidisciplinary fields. However, constructing higher-order EPs still remains as a challenge due to the strict requirement of the system symmetries. Here we demonstrate that higher-order EPs can be judiciously fabricated in PT -symmetric staggered rhombic lattices by introducing not only on-site gain/loss but also nonHermitian couplings. Zero-energy flatbands persist and symmetry-protected third-order EPs (EP3) arise in these systems owing to the non-Hermitian chiral/sublattice symmetry, but distinct phase transitions and propagation dynamics occur. Specifically, the EP3 arises at the Brillouin zone (BZ) boundary in the presence of on-site gain/loss. The single-site excitations display an exponential power increase in the PT -broken phase. Meanwhile, a nearly flatband sustains when a small lattice perturbation is applied. For the lattices with non-Hermitian couplings, however, the EP3 appears at the BZ center. Quite remarkably, our analysis unveils a dynamical delocalization-localization transition for the excitation of the dispersive bands and a quartic power increase beyond the EP3. Our scheme provides a new platform towards the investigation of the higher-order EPs, and can be further extended to the study of topological phase transitions or nonlinear processes associated with higher-order EPs.

physics.optics↗