Vala Vakilian
5 papers · 2022–2025 · 4 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
🗺️
Taxonomy Completionist
(14)
Venues
Top co-authors
Research topics
Machine Learning
(5)
Core Methods
(4)
Deep Learning
(3)
Learning Types · Machine Learning
(3)
Optimization & Theory · Machine Learning
(2)
Optimization & Theory · Deep Learning
(2)
Artificial Intelligence
(1)
Application Areas
(1)
Core AI
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Keywords
class imbalance
(4)
neural collapse
(3)
cross-entropy loss
(2)
supervised contrastive loss
(2)
representation learning
(2)
deep learning
(1)
support vector machine
(1)
relu activation
(1)
feature geometry
(1)
classifier weight
(1)
implicit bia
(1)
parameter-efficient fine-tuning
(1)
low-rank adaptation
(1)
weight pruning
(1)
ridge regularization
(1)
label imbalance
(1)
logit-adjusted parameterization
(1)
cost-sensitive svm
(1)
optimization path
(1)
fine-tuned model
(1)
Papers
DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models
ICLR 2025
Engineering the Neural Collapse Geometry of Supervised-Contrastive Loss (Student Abstract)
AAAI 2024
Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching
ICLR 2024
On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data
AISTATS 2023
Imbalance Trouble: Revisiting Neural-Collapse Geometry
NeurIPS 2022