Reconstructing dense geometry for dynamic scenes from a monocular video is a critical yet challenging task. Recent memory-based methods enable efficient online reconstruction, but they fundamentally suffer from a Memory Demand Dilemma: The memory representation faces an inherent conflict between the long-term stability required for static structures and the rapid, high-fidelity detail retention needed for dynamic motion. This conflict forces existing methods into a compromise, leading to either geometric drift in static structures or blurred, inaccurate reconstructions of dynamic objects. To address this dilemma, we propose Mem4D, a novel framework that decouples the modeling of static geometry and dynamic motion. Guided by this insight, we design a dual-memory architecture: 1) The Transient Dynamics Memory (TDM) focuses on capturing high-frequency motion details from recent frames, enabling accurate and fine-grained modeling of dynamic content; 2) The Persistent Structure Memory (PSM) compresses and preserves long-term spatial information, ensuring global consistency and drift-free reconstruction for static elements. By alternating queries to these specialized memories, Mem4D simultaneously maintains static geometry with global consistency and reconstructs dynamic elements with high fidelity. Experiments on challenging benchmarks demonstrate that our method achieves state-of-the-art or competitive performance while maintaining high efficiency.

ABSTRACT This paper proposes a method for constructing a knowledge graph for nuclear power equipment failures based on the CHINESE‐RoBERTa‐BiLSTM‐CRF model, whose goal is to automate the extraction and structured utilization of nuclear power equipment failure knowledge and provide decision support for nuclear power equipment debugging work. First, the method involves constructing annotated datasets for Named Entity Recognition (NER) and Relation Extraction (RE); Second, the CHINESE‐RoBERTa‐BiLSTM‐CRF model is constructed. This model employs Whole Word Masking (WWM) to capture deep contextual semantics. It also utilizes a Bidirectional Long Short‐Term Memory (BiLSTM) network to enhance sequence features and implements a Conditional Random Field (CRF) layer for optimized boundary recognition. Finally, the method classifies relationships between entity pairs. The resulting triples are stored in a Neo4j graph database to complete the knowledge graph construction. The nuclear power equipment fault knowledge graph constructed by this method is validated using model comparisons and case verification. Experimental results demonstrate that the NER model proposed in this paper achieves an F1 score of 94.9%, significantly outperforming the baseline model. Furthermore, practical verification confirms that the knowledge graph can accurately identify faults and provide decision support for on‐site anomalies.

We present VisFly, a quadrotor simulator designed to efficiently train vision-based flight policies using reinforcement learning algorithms. VisFly offers a user-friendly framework and interfaces, leveraging Habitat-Sim's rendering engines to achieve frame rates exceeding 10,000 frames per second for rendering motion and sensor data. The simulator incorporates differentiable physics and is seamlessly wrapped with the Gym environment, facilitating the straightforward implementation of various learning algorithms. It supports the directly importing open-source scene datasets compatible with Habitat-Sim, enabling training on diverse real-world environments simultaneously. To validate our simulator, we also make three reinforcement learning examples for typical flight tasks relying on visual observations. The simulator is now available at [https://github.com/SJTU-ViSYS-team/VisFly].

Dialogue-based automatic disease diagnosis has the potential to assist medical professionals in enhancing the accuracy and efficiency of diagnosis and treatment. Nonetheless, prior models grounded in reinforcement learning often exhibit a tendency to inquire about unrelated symptoms that hold limited relevance to the available symptom information within the constrained number of conversational exchanges. Consequently, these models may hastily assign a diagnosis to the patient. To address this issue, our paper draws inspiration from the diagnostic procedures employed by real-world physicians and introduces a novel two-stage training strategy termed TS-DDD for Dialogue-based Disease Diagnosis. In the initial stage, we pretrain two classifiers for symptom inquiry and disease prediction, separately. In the second stage, we devise a joint training framework that seamlessly integrates symptom inquiry, disease prediction, and decision-making processes. Extensive experiments are conducted and the results validate the effectiveness of our proposed TS-DDD model.