Xinchen Zhang

Yizhen Zhang, Yang Ding, Shuoshuo Zhang et al.

Inspired by the impressive reasoning capabilities demonstrated by reinforcement learning approaches like DeepSeek-R1, recent emerging research has begun exploring the use of reinforcement learning (RL) to enhance vision-language models (VLMs) for multimodal reasoning tasks. However, most existing multimodal reinforcement learning approaches remain limited to spatial reasoning within single-image contexts, yet still struggle to generalize to more complex and real-world scenarios involving multi-image positional reasoning, where understanding the relationships across images is crucial. To address this challenge, we propose a general reinforcement learning approach PeRL tailored for interleaved multimodal tasks, and a multi-stage strategy designed to enhance the exploration-exploitation trade-off, thereby improving learning efficiency and task performance. Specifically, we introduce permutation of image sequences to simulate varied positional relationships to explore more spatial and positional diversity. Furthermore, we design a rollout filtering mechanism for resampling to focus on trajectories that contribute most to learning optimal behaviors to exploit learned policies effectively. We evaluate our model on 5 widely-used multi-image benchmarks and 3 single-image benchmarks. Our experiments confirm that PeRL trained model consistently surpasses R1-related and interleaved VLM baselines by a large margin, achieving state-of-the-art performance on multi-image benchmarks, while preserving comparable performance on single-image tasks.

Shuo Yang, Xinran Zheng, Xinchen Zhang et al.

Large Language Models (LLMs) have revolutionized various fields with their exceptional capabilities in understanding, processing, and generating human-like text. This paper investigates the potential of LLMs in advancing Network Intrusion Detection Systems (NIDS), analyzing current challenges, methodologies, and future opportunities. It begins by establishing a foundational understanding of NIDS and LLMs, exploring the enabling technologies that bridge the gap between intelligent and cognitive systems in AI-driven NIDS. While Intelligent NIDS leverage machine learning and deep learning to detect threats based on learned patterns, they often lack contextual awareness and explainability. In contrast, Cognitive NIDS integrate LLMs to process both structured and unstructured security data, enabling deeper contextual reasoning, explainable decision-making, and automated response for intrusion behaviors. Practical implementations are then detailed, highlighting LLMs as processors, detectors, and explainers within a comprehensive AI-driven NIDS pipeline. Furthermore, the concept of an LLM-centered Controller is proposed, emphasizing its potential to coordinate intrusion detection workflows, optimizing tool collaboration and system performance. Finally, this paper identifies critical challenges and opportunities, aiming to foster innovation in developing reliable, adaptive, and explainable NIDS. By presenting the transformative potential of LLMs, this paper seeks to inspire advancement in next-generation network security systems.