3 citations
- Sun Yat-sen UniversityCN3 papers
- City University of Hong KongHK2 papers
- Southern University of Science and TechnologyCN2 papers
- Zhejiang UniversityCN2 papers
- Beijing Academy of Artificial IntelligenceCN1 paper
- China Telecom1 paper
- China Telecom (China)CN1 paper
- Chinese University of Hong Kong, ShenzhenCN1 paper
- Harbin Institute of TechnologyCN1 paper
- Hong Kong University of Science and TechnologyHK1 paper
- Nanjing UniversityCN1 paper
- Nanjing University of Science and TechnologyCN1 paper
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval
Zhicheng Zhang, Jiwei Tang, Kuicai Dong +9
Hard negative mining has become the dominant strategy for training retrievers, yet it faces intrinsic limitations: negatives are bounded by corpus availability, selected by retriev…
cs.LG2026★ 3 cited
TIDFormer: Exploiting Temporal and Interactive Dynamics Makes A Great Dynamic Graph Transformer
Jie Peng, Zhewei Wei, Yuhang Ye
Due to the proficiency of self-attention mechanisms (SAMs) in capturing dependencies in sequence modeling, several existing dynamic graph neural networks (DGNNs) utilize Transforme…