Li Shen

COMPETITION PRACTICE AND RESEARCH OF PROMOTING TEACHING BY COMPETITION: TAKE THE COURSE OF INFORMATION SYSTEM AND SECURITY COUNTERMEASURES TECHNOLOGY FOR AN EXAMPLE

Ling Zhao, Hongxia Hou, Li Shen, Rui Ma

With the explosive growth of talent demand in the field of cybersecurity, the traditional training model of "emphasizing theory over practice" in information security courses is no longer suitable for the core requirements of the industry for practical talents. Using the course …

cn (code pays fourni par la source)

Boosting backdoor attack with a learnable poisoning sample selection strategy

Zihao Zhu, Mingda Zhang, Shaokui Wei, Li Shen et autres

cn (code pays fourni par la source)

Stability and Generalization for Distributed SGDA

Miaoxi Zhu, Yan Sun, Li Shen, Bo Du et autres

Minimax optimization is gaining increasing attention in modern machine learning applications. Driven by large-scale models and massive volumes of data collected from edge devices, as well as the concern to preserve client privacy, distributed minimax optimization algorithms become popular, such as Local …

cn, au, sg (code pays fourni par la source)

Instructed Diffuser With Temporal Condition Guidance for Offline Reinforcement Learning

Jifeng Hu, Yanchao Sun, Sili Huang, Siyuan Guo et autres

Recentworks have shown the potential of diffusion models in computer vision and natural language processing. Apart from the classical supervised learning fields, diffusion models have also shown strong competitiveness in reinforcement learning (RL) by formulating decision-making as sequential generation. However, incorporating temporal …

cn, us, sg (code pays fourni par la source)

Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities

Zhiwei Hao, Jianyuan Guo, Li Shen, Yong Luo et autres

Large language models (LLMs) have achieved impressive performance across various domains. However, the substantial hardware resources required for their training present a significant barrier to efficiency and scalability. To mitigate this challenge, low-precision training techniques have been widely adopted, leading to notable …

cn, hk, sg (code pays fourni par la source)

Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing

Yuchen Wu, Liang Ding, Li Shen, Dacheng Tao

Aligning Large Language Models (LLMs) to be faithful to new knowledge in complex, multihop reasoning tasks is a critical, yet unsolved, challenge.We find that SFT-based methods, e.g., Reason-KE (Wu et al., 2025b), while stateof-the-art, suffer from a "faithfulness gap": they optimize for …

cn, au, sg (code pays fourni par la source)

FSGDR: A Cognitive Embodied Agent Based on Fuzzy Semantic-Guided Dual-Mode Reasoning

Fang Shi, Jiayin Zhang, JianKang Zeng, Shunpu Tang et autres

cn (code pays fourni par la source)

Toward Understanding Generalization and Stability Gaps Between Centralized and Decentralized Federated Learning

Yan Sun, Li Shen, Dacheng Tao

As two mainstream frameworks in federated learning (FL), both centralized and decentralized approaches have shown great application value in practical scenarios. However, existing studies do not provide sufficient evidence and clear guidance for analysis of which performs better in the FL community. …

au, cn, sg (code pays fourni par la source)

Deep Model Fusion: A Survey

Yong Peng, Miao Zhang, Liang Ding, Han Hu et autres

Deep model fusion/merging is an emerging technique that integrates parameters or predictions from multiple deep learning (DL) models into a unified framework. It combines the abilities of different models to compensate for the biases and errors of an individual model, improving overall …

cn (code pays fourni par la source)

Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging

Li Shen, Anke Tang, Enneng Yang, Guibing Guo et autres

Multi-task learning (MTL) leverages a shared model to accomplish multiple tasks and facilitate knowledge transfer. Recent research on task arithmetic-based MTL demonstrates that merging the parameters of independently fine-tuned models can effectively achieve MTL. However, existing merging methods primarily seek a static …

cn, sg (code pays fourni par la source)

Diagnostic Value of Homocysteine Metabolic Pathway in Coronary Atherosclerosis: A Study on Reference Intervals and Risk Prediction

Li Shen, Furong Zhao, Hong Mo

Purpose: To determine the reference intervals of homocysteine (Hcy) metabolic pathway in healthy adults using direct continuous sampling, and to explore their correlations with coronary atherosclerosis (CA) for improving the risk assessment and diagnostic accuracy of CA. Patients and Methods: A total …

cn (code pays fourni par la source)

Dynamic Analysis and Adaptive Discriminator for Fake News Detection

Xinqi Su, Zitong Yu, Yawen Cui, Ajian Liu et autres

In current web environment, fake news spreads rapidly across online social networks, posing serious threats to society. Existing multimodal fake news detection methods can generally be classified into knowledge-based and semantic-based approaches. However, these methods are heavily rely on human expertise and …

cn, hk (code pays fourni par la source)