Zexi Li

Venues

Frequent coauthors

Papers

1. Each Rank Could be an Expert: Single-Ranked Mixture of Experts LoRA for Multi-task Learning
   SIGKDD 2026 ·

   Ziyu Zhao

   DBLP profile ↗ORCID search ↗
2. Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?
   AAAI 2026 · Zexi Li
3. FedGuCci: Making Local Models More Connected in Landscape for Federated Learning
   SIGKDD 2025 · Zexi Li
4. FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models
   NeurIPS 2025 ·

   Yan Gao

   DBLP profile ↗ORCID search ↗
5. Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering
   ICLR 2025 ·

   Ziyu Zhao

   DBLP profile ↗ORCID search ↗
6. Photon: Federated LLM Pre-Training
   MLSys 2025 ·

   Lorenzo Sani

   DBLP profile ↗ORCID search ↗
7. Text2Weight: Bridging Natural Language and Neural Network Weight Spaces
   ACM MM 2025 ·

   Bowen Tian

   DBLP profile ↗ORCID search ↗
8. You are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-Tailed Data
   ICCV 2025 ·

   Shanshan Yan

   DBLP profile ↗ORCID search ↗
9. Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
   ICML 2024 ·

   Didi Zhu

   DBLP profile ↗ORCID search ↗
10. Neural Collapse Anchored Prompt Tuning for Generalizable Vision-Language Models
    SIGKDD 2024 ·

    Didi Zhu

    DBLP profile ↗ORCID search ↗
11. OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning
    SIGKDD 2024 ·

    Rui Ye

    DBLP profile ↗ORCID search ↗
12. Scalable Geometric Fracture Assembly via Co-creation Space among Assemblers
    AAAI 2024 ·

    Ruiyuan Zhang

    DBLP profile ↗ORCID search ↗