Jiapeng Xu

Yuliang Chen, Xi Lin, Jun Wu et al.

Federated Domain Generalization (FDG) aims to collaboratively train a global model across distributed clients that can generalize well on unseen domains. However, existing FDG methods typically struggle with cross-client data heterogeneity and incur significant communication and computation overhead. To address these challenges, this paper presents a new FDG framework, dubbed FaST-PT, which facilitates local feature augmentation and efficient unseen domain adaptation in a distributed manner. First, we propose a lightweight Multi-Modal Style Transfer (MST) method to transform image embedding under text supervision, which could expand the training data distribution and mitigate domain shift. We then design a dual-prompt module that decomposes the prompt into global and domain prompts. Specifically, global prompts capture general knowledge from augmented embedding across clients, while domain prompts capture domain-specific knowledge from local data. Besides, Domain-aware Prompt Generation (DPG) is introduced to adaptively generate suitable prompts for each sample, which facilitates unseen domain adaptation through knowledge fusion. Extensive experiments on four cross-domain benchmark datasets, e.g., PACS and DomainNet, demonstrate the superior performance of FaST-PT over SOTA FDG methods such as FedDG-GA and DiPrompt. Ablation studies further validate the effectiveness and efficiency of FaST-PT.

Haolin Yang, Yuxing Long, Zhuoyuan Yu et al.

Instruction-following navigation is a key step toward embodied intelligence. Prior benchmarks mainly focus on semantic understanding but overlook systematically evaluating navigation agents' spatial perception and reasoning capabilities. In this work, we introduce the NavSpace benchmark, which contains six task categories and 1,228 trajectory-instruction pairs designed to probe the spatial intelligence of navigation agents. On this benchmark, we comprehensively evaluate 22 navigation agents, including state-of-the-art navigation models and multimodal large language models. The evaluation results lift the veil on spatial intelligence in embodied navigation. Furthermore, we propose SNav, a new spatially intelligent navigation model. SNav outperforms existing navigation agents on NavSpace and real robot tests, establishing a strong baseline for future work.

Jiapeng Xu

Many studies have revealed that sentence comprehension relies more on semantic processing than on syntactic processing. However, previous studies have predominantly emphasized the preference for semantic processing, focusing on the semantic perspective. In contrast, this current study highlights the under-utilization of syntactic processing, from a syntactic perspective. Based on the traditional garden-path experiment, which involves locally ambiguous but globally unambiguous sentences, this study's empirical experiment innovatively crafted an adapted version featuring semantically ambiguous but syntactically unambiguous sentences to meet its specific research objective. This experiment, involving 140 subjects, demonstrates through descriptive and inferential statistical analyses using SPSS, Graph Pad Prism, and Cursor that Chinese learners of English tend to under-utilize syntactic processing when comprehending English sentences. The study identifies two types of parsing under-utilization: partial and complete. Further exploration reveals that trial and error in syntactic processing contributes to both. Consequently, this study lays a foundation for the development of a novel parsing method designed to fully integrate syntactic processing into sentence comprehension, thereby enhancing the level of English sentence comprehension for Chinese learners of English.