2 citations · 2 across the 3 of their papers we have counts for
6 papers
New LoRA Skills Should Read but Never Write
Zeyan Li, Panqi Yang, Qirong Guo +5
Low-rank adapters (LoRA) make it cheap to fine-tune a large language model once per task, but combining several independently trained adapters into one model remains difficult: mer…
BridgeMem: Causal Dyadic Transition Residuals for Temporal Knowledge Graph Forecasting
Zeyan Li, Libing Chen, Shengda Zhuo +2
Temporal knowledge graph forecasting aims to infer future relational facts from the temporal structure of observed events. Existing forecasters mainly summarize history through ent…
E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems
Zelin Guan, Shengda Zhuo, Zeyan Li +4
Retrieval-Augmented Generation (RAG) equips large language models (LLMs) with external evidence by retrieving documents at inference time, but it also turns the retrieval corpusint…
Extension OL-MDISF: Online Learning from Mix-Typed, Drifted, and Incomplete Streaming Features
Shengda Zhuo, Di Wu, Yi He +2
Online learning, where feature spaces can change over time, offers a flexible learning paradigm that has attracted considerable attention. However, it still faces three significant…
From Bias to Behavior: Learning Bull-Bear Market Dynamics with Contrastive Modeling
Xiaotong Luo, Shengda Zhuo, Min Chen +5
Financial markets exhibit highly dynamic and complex behaviors shaped by both historical price trajectories and exogenous narratives, such as news, policy interpretations, and soci…
EdgeGFL: Rethinking Edge Information in Graph Feature Preference Learning
Shengda Zhuo, Jiwang Fang, Hongguang Lin +4
Graph Neural Networks (GNNs) have significant advantages in handling non-Euclidean data and have been widely applied across various areas, thus receiving increasing attention in re…