Daliang Li
4 papers · 2021–2024 · 3 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 · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(12)
Top co-authors
Research topics
Machine Learning
(3)
Artificial Intelligence
(2)
Deep Learning
(2)
Application Areas
(2)
Architectures
(2)
Core AI
(2)
Learning Types · Deep Learning
(2)
Computer Vision
(1)
Natural Language Processing
(1)
Analysis
(1)
Learning Paradigms
(1)
Learning Types · Machine Learning
(1)
Optimization & Theory
(1)
Resources & Methods
(1)
Keywords
transfer learning
(2)
transformer architecture
(1)
image classification
(1)
vision transformer
(1)
knowledge editing
(1)
in-context learning
(1)
convolutional neural network
(1)
adversarial perturbation
(1)
controllable generation
(1)
prompt tuning
(1)
activation sparsity
(1)
model efficiency
(1)
context grounding
(1)
large language model
(1)
prediction calibration
(1)
model compression
(1)
top-k thresholding
(1)
Papers
Two-stage LLM Fine-tuning with Less Specialization and More Generalization
ICLR 2024
Large Language Models with Controllable Working Memory
ACL 2023
The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers
ICLR 2023
Understanding Robustness of Transformers for Image Classification
ICCV 2021