Chinmay Savadikar
3 papers · 2025–2026 · 2 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
Top co-authors
Research topics
Keywords
catastrophic forgetting
(1)
class-incremental learning
(1)
neural architecture search
(1)
linear layer
(1)
fine tuning
(1)
stability-plasticity dilemma
(1)
pretrained weight
(1)
large model
(1)
exemplar-free continual learning
(1)
low-rank formulation
(1)
multi-faceted efficiency
(1)
adversarial jacobian
(1)
iteratively learning
(1)
logit-to-image jacobian
(1)
ordered top-$k$ attack
(1)
right singular vectors
(1)
sequential quadratic programming (sqp)
(1)
Papers
CHEEM: Continual Learning by Reuse, New, Adapt and Skip - A Hierarchical Exploration-Exploitation Approach
CVPR 2026
Adversarial Perturbations Are Formed by Iteratively Learning Linear Combinations of the Right Singular Vectors of the Adversarial Jacobian
ICML 2025
WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models
ICML 2025