1 citations · 1 across the 19 of their papers we have counts for
21 papers
Breaking the Tie: A Cluster-Aware Routing Framework for Large Language Models
Yao Lu, Zhaiyuan Ji, Yaxin Gao +6
With the rapid development of artificial intelligence, the emergence of various Large Language Models (LLMs) has created a rich model ecosystem. However, this also brings a key cha…
AgentS4D: Benchmarking Runtime Risks across the Execution Lifecycle of LLM-Based Workspace Agents
Jiajun Zhou, Zhaoxuan Ke, Jihang Ye +3
Large language model (LLM)-based workspace agents execute stateful, multi-step workflows across heterogeneous resources, external tools, and persistent state. Their safety must the…
MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair
Xuanze Chen, Xukang Xie, Wentao Fu +3
Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist. A malicious instruction crafted by an attacker…
Mapping Text to Multiplex Graph: Prompt Compression as Lévy Walk-Guided Graph Pruning
Yaxin Gao, Yao Lu, Jinhong Deng +7
Existing prompt compression methods treat text as flat token sequences, failing to capture the distributed nature of important information, which is often spread across multiple lo…
ReCoG: Relational and Compact Context Graph Learning for Few-shot Molecular Property Prediction
Zeyu Wang, Xin Zheng, Yao Lu +3
Few-shot molecular property prediction (FSMPP) is essential in drug discovery and materials design, where high-quality labeled data are often scarce and expensive to obtain. Despit…
Learning How Much to Think: Difficulty-Aware Dynamic MoEs for Graph Node Classification
Jiajun Zhou, Yadong Li, Xuanze Chen +4
Mixture-of-Experts (MoE) architectures offer a scalable path for Graph Neural Networks (GNNs) in node classification tasks but typically rely on static and rigid routing strategies…
CrossHGL: A Text-Free Foundation Model for Cross-Domain Heterogeneous Graph Learning
Xuanze Chen, Jiajun Zhou, Yadong Li +2
Heterogeneous graph representation learning (HGRL) is essential for modeling complex systems with diverse node and edge types. However, most existing methods are limited to closed-…
Traffic-MoE: A Sparse Foundation Model for Network Traffic Security Analysis
Jiajun Zhou, Changhui Sun, Wentao Fu +3
As adversaries increasingly weaponize encryption and protocol obfuscation to evade traffic detection, traditional methods are rendered obsolete, necessitating deep learning to unma…
The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models
Yao Lu, Yuqi Li, Wenbin Xie +4
Although large language models (LLMs) have achieved revolutionary breakthroughs in many fields, their large model size and high computational cost pose significant challenges for p…
Few-shot Molecular Property Prediction: A Survey
Zeyu Wang, Tianyi Jiang, Huanchang Ma +6
AI-assisted molecular property prediction has become a promising technique in early-stage drug discovery and materials design in recent years. However, due to high-cost and complex…
DSPC: Dual-Stage Progressive Compression Framework for Efficient Long-Context Reasoning
Yaxin Gao, Yao Lu, Zongfei Zhang +3
Large language models (LLMs) have achieved remarkable success in many natural language processing (NLP) tasks. To achieve more accurate output, the prompts used to drive LLMs have…
LoRALib: A Standardized Benchmark for Evaluating LoRA-MoE Methods
Shaoheng Wang, Yao Lu, Yuqi Li +5
As a parameter efficient fine-tuning (PEFT) method, low-rank adaptation (LoRA) can save significant costs in storage and computing, but its strong adaptability to a single task is…
From LLM-anation to LLM-orchestrator: Coordinating Small Models for Data Labeling
Yao Lu, Zhaiyuan Ji, Jiawei Du +3
Although the annotation paradigm based on Large Language Models (LLMs) has made significant breakthroughs in recent years, its actual deployment still has two core bottlenecks: fir…
Adaptive Substructure-Aware Expert Model for Molecular Property Prediction
Tianyi Jiang, Zeyu Wang, Shanqing Yu +1
Molecular property prediction is essential for applications such as drug discovery and toxicity assessment. While Graph Neural Networks (GNNs) have shown promising results by model…
Hierarchical Local-Global Feature Learning for Few-shot Malicious Traffic Detection
Songtao Peng, Lei Wang, Wu Shuai +4
With the rapid growth of internet traffic, malicious network attacks have become increasingly frequent and sophisticated, posing significant threats to global cybersecurity. Tradit…
Unveiling Latent Information in Transaction Hashes: Hypergraph Learning for Ethereum Ponzi Scheme Detection
Junhao Wu, Yixin Yang, Chengxiang Jin +5
With the widespread adoption of Ethereum, financial frauds such as Ponzi schemes have become increasingly rampant in the blockchain ecosystem, posing significant threats to the sec…
Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
Bin Li, Dehong Gao, Yeyuan Wang +4
Despite the significant success of Large Vision-Language models(LVLMs), these models still suffer hallucinations when describing images, generating answers that include non-existen…
Mixture of Message Passing Experts with Routing Entropy Regularization for Node Classification
Xuanze Chen, Jiajun Zhou, Yadong Li +3
Graph neural networks (GNNs) have achieved significant progress in graph-based learning tasks, yet their performance often deteriorates when facing heterophilous structures where c…
Efficient Parallel Genetic Algorithm for Perturbed Substructure Optimization in Complex Network
Shanqing Yu, Meng Zhou, Jintao Zhou +5
Evolutionary computing, particularly genetic algorithm (GA), is a combinatorial optimization method inspired by natural selection and the transmission of genetic information, which…
CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models
Yeyuan Wang, Dehong Gao, Bin Li +7
The impressive performance of Large Language Model (LLM) has prompted researchers to develop Multi-modal LLM (MLLM), which has shown great potential for various multi-modal tasks.…
General2Specialized LLMs Translation for E-commerce
Kaidi Chen, Ben Chen, Dehong Gao +6
Existing Neural Machine Translation (NMT) models mainly handle translation in the general domain, while overlooking domains with special writing formulas, such as e-commerce and le…