Hari Sundaram
8 papers · 2022–2025 · 6 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
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(24)
Top co-authors
Research topics
Artificial Intelligence
(5)
Deep Learning
(4)
Machine Learning
(4)
Natural Language Processing
(4)
Core AI
(4)
Generation
(3)
Learning Types · Machine Learning
(3)
Application Areas
(2)
Learning Types · Deep Learning
(2)
Optimization & Theory
(2)
Computer Science
(1)
Applications
(1)
Architectures
(1)
Core Methods
(1)
Learning Paradigms
(1)
Keywords
adversarial example
(2)
large language model
(2)
language model
(2)
text generation
(2)
constrained generation
(1)
batch normalization
(1)
adversarial robustness
(1)
code generation
(1)
style transfer
(1)
text style transfer
(1)
ai safety
(1)
automatic differentiation
(1)
spectral norm
(1)
black-box attack
(1)
decision boundary
(1)
toxicity detection
(1)
pairwise comparison
(1)
sparse autoencoder
(1)
ensemble learning
(1)
benchmark evaluation
(1)
Papers
Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders
EMNLP 2025
Not All Wrong is Bad: Using Adversarial Examples for Unlearning
ICML 2025
Training Robust Ensembles Requires Rethinking Lipschitz Continuity
ICLR 2025
Advancing Precise Outline-Conditioned Text Generation with Task Duality and Explicit Outline Control
EACL 2024
CEV-LM: Controlled Edit Vector Language Model for Shaping Natural Language Generations
EACL 2024
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
ACL 2024
Spectrum Extraction and Clipping for Implicitly Linear Layers
AISTATS 2024
Audience-Centric Natural Language Generation via Style Infusion
EMNLP 2022