Suraj Srinivas
13 papers · 2018–2026 · 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 ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (35)
π
Keyword Champion
(2)
ποΈ
Keyword Collector
(71)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
β
The Questioner
(3)
Venues
Top co-authors
Research topics
Machine Learning
(12)
Artificial Intelligence
(11)
Core AI
(10)
Deep Learning
(6)
Optimization & Theory Β· Machine Learning
(6)
Optimization & Theory Β· Deep Learning
(4)
Application Areas
(3)
Core Methods
(3)
Learning Types
(3)
Architectures
(2)
Learning Paradigms
(2)
Models
(2)
Techniques
(2)
Computer Vision
(1)
Mathematics & Optimization
(1)
Keywords
adversarial robustness
(3)
post-hoc explanation
(2)
neural network
(2)
model interpretability
(2)
weight decay
(2)
input gradient
(2)
domain adaptation
(1)
transfer learning
(1)
representation learning
(1)
knowledge distillation
(1)
batch normalization
(1)
multimodal learning
(1)
model architecture
(1)
explainable ai
(1)
feature disentanglement
(1)
model robustness
(1)
model editing
(1)
feature attribution
(1)
embedding learning
(1)
concept representation
(1)
Papers
Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders
EACL 2026
How Much Can We Forget about Data Contamination?
ICML 2025
Characterizing Data Point Vulnerability as Average-Case Robustness
UAI 2024
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
NeurIPS 2024
Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability
NeurIPS 2023
On Minimizing the Impact of Dataset Shifts on Actionable Explanations
UAI 2023
Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness
NeurIPS 2023
Data-Efficient Structured Pruning via Submodular Optimization
NeurIPS 2022
Efficient Training of Low-Curvature Neural Networks
NeurIPS 2022
Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations
NeurIPS 2022
Rethinking the Role of Gradient-based Attribution Methods for Model Interpretability
ICLR 2021
Full-Gradient Representation for Neural Network Visualization
NeurIPS 2019
Knowledge Transfer with Jacobian Matching
ICML 2018