Zexi Li
9 papers · 2023–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (27) 🐣 Hot Topic Early Bird 🏆 Grand Slam
❓
The Questioner
Venues
Top co-authors
Research topics
Machine Learning
(8)
Artificial Intelligence
(6)
Deep Learning
(4)
Application Areas
(3)
Core AI
(3)
Core Methods
(3)
Learning Paradigms · Artificial Intelligence
(3)
Learning Types · Machine Learning
(3)
Learning Types · Deep Learning
(3)
Natural Language Processing
(2)
Learning Paradigms · Machine Learning
(2)
Optimization & Theory
(2)
Resources & Methods
(2)
Computer Vision
(1)
Analysis
(1)
Keywords
federated learning
(3)
neural collapse
(2)
knowledge editing
(2)
large language model
(2)
data heterogeneity
(2)
computer vision
(1)
vision transformer
(1)
representation learning
(1)
model unlearning
(1)
loss function
(1)
factual knowledge
(1)
model merging
(1)
model editing
(1)
feature representation
(1)
catastrophic forgetting
(1)
knowledge distillation
(1)
parameter clustering
(1)
sensitivity analysis
(1)
attention mechanism
(1)
3d reconstruction
(1)
Papers
Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?
AAAI 2026
Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering
ICLR 2025
You Are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-tailed Data
ICCV 2025
Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
ICML 2024
Scalable Geometric Fracture Assembly via Co-creation Space among Assemblers
AAAI 2024
WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
NeurIPS 2024
No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier
ICCV 2023
Revisiting Weighted Aggregation in Federated Learning with Neural Networks
ICML 2023
Universal Domain Adaptation via Compressive Attention Matching
ICCV 2023