Aojun Lu
5 papers · 2024–2026 · 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 ↓
🌍
Conference Polyglot · Silver
🗺️
Taxonomy Completionist
(12)
❓
The Questioner
Venues
Top co-authors
Research topics
Deep Learning
(3)
Machine Learning
(3)
Learning Types · Machine Learning
(3)
Architectures
(2)
Artificial Intelligence
(1)
Application Areas
(1)
Core Methods
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Optimization & Theory · Deep Learning
(1)
Optimization & Theory · Machine Learning
(1)
Techniques
(1)
Keywords
continual learning
(3)
catastrophic forgetting
(3)
stability-plasticity trade-off
(2)
sharpness-aware minimization
(1)
loss landscape
(1)
out-of-distribution generalization
(1)
pre-trained model
(1)
vision-language model
(1)
supervised fine-tuning
(1)
generalization gap
(1)
flat minima
(1)
network depth
(1)
network width
(1)
class prototype
(1)
architecture design
(1)
parameter constraint
(1)
data difficulty
(1)
architectural perspective
(1)
dual-arch framework
(1)
plasticity network
(1)
Papers
Adapt Before Continual Learning
AAAI 2026
Why Does RL Generalize Better Than SFT? A Data-Centric Perspective on VLM Post-Training
CVPR 2026
Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective
ICML 2025
Make Continual Learning Stronger via C-Flat
NeurIPS 2024
Revisiting Neural Networks for Continual Learning: An Architectural Perspective
IJCAI 2024