Zian Liu

Zian Liu, Andong Yang, Chunkai Yang et al.

Navigating a drone in unseen and cluttered environments requires reliable generalization to unseen scene layouts and understanding of environmental structure relative to the robot's capabilities. Previous methods, which assume the same environment configuration, often rely heavily on human-designed perception pipelines and predefined rules to guide the robot toward the target. This process is environment-dependent and generalizes poorly across environments. Inspired by animal navigation behavior, we design a navigation framework that navigates with a reinforcement-learning-based policy on top of a world-model-based environment understanding to overcome these issues. In addition, a sparse reward function without hand-crafted shaping terms is designed to avoid local minima traps and encourage yaw control behaviors. In simulation and on real drones, our method exhibits emergent capabilities for navigating complex, unseen environments and escaping local optima where other methods fail. In challenging maps, it achieves a 5.3% higher navigation success rate than best baseline. Furthermore, the proposed framework achieves effective sim-to-real transfer without any tuning during deployment. The code will be publicly available.

Zian Liu, Renjun Jia

Predicting financial time series presents significant challenges due to inherent low signal-to-noise ratios and intricate temporal patterns. Traditional machine learning models exhibit limitations in this forecasting task constrained by their restricted model capacity. Recent advances in large language models (LLMs), with their greatly expanded parameter spaces, demonstrate promising potential for modeling complex dependencies in temporal sequences. However, existing LLM-based approaches typically focus on fixed-length patch analysis due to the Transformer architecture, ignoring market data's multi-scale pattern characteristics. In this study, we propose $LLM4FTS$, a novel framework that enhances LLM capabilities for temporal sequence modeling through learnable patch segmentation and dynamic wavelet convolution modules. Specifically,we first employ K-means++ clustering based on DTW distance to identify scale-invariant patterns in market data. Building upon pattern recognition results, we introduce adaptive patch segmentation that partitions temporal sequences while preserving maximal pattern integrity. To accommodate time-varying frequency characteristics, we devise a dynamic wavelet convolution module that emulates discrete wavelet transformation with enhanced flexibility in capturing time-frequency features. These three modules work together to improve large language model's ability to handle scale-invariant patterns in financial time series. Extensive experiments on real-world financial datasets substantiate the framework's efficacy, demonstrating superior performance in capturing complex market patterns and achieving state-of-the-art results in stock return prediction. The successful deployment in practical trading systems confirms its real-world applicability, representing a significant advancement in LLM applications for financial forecasting.

Zian Liu

After the leaking of exploit Eternalblue, some ransomworms utilizing this exploit have been developed to sweep over the world in recent years. Ransomworm is a global growing threat as it blocks users' access to their files unless a ransom is paid by victims. Wannacry and Notpetya are two of those ransomworms which are responsible for the loss of millions of dollar, from crippling U.K. national systems to shutting down a Honda Motor Company in Japan. Many dynamic analytic papers on Wannacry were published, however, static analytic papers about Wannacry were limited. Our aim is to present readers an systematic knowledge about exploit Eternalblue, from a high\textendash leveled semantic view to the code details. Specifically, the working mechanism of Eternalblue, the reverse engineering analysis of Eternalblue in Wannacry, and the comparison with the Metasploit's Eternalblue exploit are presented. The key finding of our analysis is that the code remains almost the same when Eternalblue is transplanted into Wannacry, which indicates its potential for signatures and thus detection.