Search Results for author: Shilong Wang

Found 18 papers, 4 papers with code

Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuning

no code implementations6 Jun 2025 Yujia Huo, Jianchun Liu, Hongli Xu, Zhenguo Ma, Shilong Wang, Liusheng Huang

Moreover, the challenge is further exacerbated by significant variation in data distributions and device capabilities across clients, which leads to intensified forgetting and degraded model generalization.

parameter-efficient fine-tuning

Efficient Federated Fine-Tuning of Large Language Models with Layer Dropout

no code implementations13 Mar 2025 Shilong Wang, Jianchun Liu, Hongli Xu, Jiaming Yan, Xianjun Gao

This work proposes DropPEFT, an innovative federated PEFT framework that employs a novel stochastic transformer layer dropout method, enabling devices to deactivate a considerable fraction of LLMs layers during training, thereby eliminating the associated computational load and memory footprint.

parameter-efficient fine-tuning

G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems

no code implementations16 Feb 2025 Shilong Wang, Guibin Zhang, Miao Yu, Guancheng Wan, Fanci Meng, Chongye Guo, Kun Wang, Yang Wang

Large Language Model (LLM)-based Multi-agent Systems (MAS) have demonstrated remarkable capabilities in various complex tasks, ranging from collaborative problem-solving to autonomous decision-making.

Decision Making Language Modeling +3

Enhancing Federated Graph Learning via Adaptive Fusion of Structural and Node Characteristics

no code implementations25 Dec 2024 Xianjun Gao, Jianchun Liu, Hongli Xu, Shilong Wang, Liusheng Huang

By combining these two models with a proper ratio, FedGCF can achieve a comprehensive understanding of the graph data and deliver better performance, even under non-IID distributions.

Graph Learning Graph Neural Network

NetSafe: Exploring the Topological Safety of Multi-agent Networks

no code implementations21 Oct 2024 Miao Yu, Shilong Wang, Guibin Zhang, Junyuan Mao, Chenlong Yin, Qijiong Liu, Qingsong Wen, Kun Wang, Yang Wang

Large language models (LLMs) have empowered nodes within multi-agent networks with intelligence, showing growing applications in both academia and industry.

Hallucination Misinformation

Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model

no code implementations29 Sep 2024 Yifan Duan, Jian Zhao, Pengcheng, Junyuan Mao, Hao Wu, Jingyu Xu, Shilong Wang, Caoyuan Ma, Kai Wang, Kun Wang, Xuelong Li

To this end, we establish a causal framework for ST predictions, termed CaPaint, which targets to identify causal regions in data and endow model with causal reasoning ability in a two-stage process.

Causal Discovery Image Inpainting

Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey

no code implementations12 Jun 2024 Hao Yang, Yanyan Zhao, Yang Wu, Shilong Wang, Tian Zheng, Hongbo Zhang, Zongyang Ma, Wanxiang Che, Bing Qin

Compared to traditional sentiment analysis, which only considers text, multimodal sentiment analysis needs to consider emotional signals from multimodal sources simultaneously and is therefore more consistent with the way how humans process sentiment in real-world scenarios.

Multimodal Sentiment Analysis

Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence

1 code implementation15 Feb 2024 Weixiang Zhao, Zhuojun Li, Shilong Wang, Yang Wang, Yulin Hu, Yanyan Zhao, Chen Wei, Bing Qin

Emotional Intelligence (EI), consisting of emotion perception, emotion cognition and emotion expression, plays the critical roles in improving user interaction experience for the current large language model (LLM) based conversational general AI assistants.

Emotional Intelligence Language Modeling +2

SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models

no code implementations16 Jan 2024 Weixiang Zhao, Shilong Wang, Yulin Hu, Yanyan Zhao, Bing Qin, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che

Existing methods devise the learning module to acquire task-specific knowledge with parameter-efficient tuning (PET) block and the selection module to pick out the corresponding one for the testing input, aiming at handling the challenges of catastrophic forgetting and knowledge transfer in CL.

Continual Learning Transfer Learning

Earthfarseer: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model

2 code implementations13 Dec 2023 Hao Wu, Yuxuan Liang, Wei Xiong, Zhengyang Zhou, Wei Huang, Shilong Wang, Kun Wang

Efficiently modeling spatio-temporal (ST) physical processes and observations presents a challenging problem for the deep learning community.

An Early Evaluation of GPT-4V(ision)

1 code implementation25 Oct 2023 Yang Wu, Shilong Wang, Hao Yang, Tian Zheng, Hongbo Zhang, Yanyan Zhao, Bing Qin

In this paper, we evaluate different abilities of GPT-4V including visual understanding, language understanding, visual puzzle solving, and understanding of other modalities such as depth, thermal, video, and audio.

Math

The Snowflake Hypothesis: Training Deep GNN with One Node One Receptive field

no code implementations19 Aug 2023 Kun Wang, Guohao Li, Shilong Wang, Guibin Zhang, Kai Wang, Yang You, Xiaojiang Peng, Yuxuan Liang, Yang Wang

Despite Graph Neural Networks demonstrating considerable promise in graph representation learning tasks, GNNs predominantly face significant issues with over-fitting and over-smoothing as they go deeper as models of computer vision realm.

Graph Representation Learning

TransESC: Smoothing Emotional Support Conversation via Turn-Level State Transition

1 code implementation5 May 2023 Weixiang Zhao, Yanyan Zhao, Shilong Wang, Bing Qin

Specifically, we construct the state transition graph with a two-step way, named transit-then-interact, to grasp such three types of turn-level transition information.

Decoder

Is ChatGPT Equipped with Emotional Dialogue Capabilities?

no code implementations19 Apr 2023 Weixiang Zhao, Yanyan Zhao, Xin Lu, Shilong Wang, Yanpeng Tong, Bing Qin

This report presents a study on the emotional dialogue capability of ChatGPT, an advanced language model developed by OpenAI.

Dialogue Understanding Language Modeling +1

EZLDA: Efficient and Scalable LDA on GPUs

no code implementations17 Jul 2020 Shilong Wang, Hang Liu, Anil Gaihre, Hengyong Yu

LDA is a statistical approach for topic modeling with a wide range of applications.

Cannot find the paper you are looking for? You can Submit a new open access paper.