Aleksandar Petrov
8 papers · 2023–2025 · 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 ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (21) π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Bronze π₯ Mega-Team Β· Squad π Grand Slam
π
Triple Crown
β
The Questioner
Venues
Top co-authors
Research topics
Artificial Intelligence
(7)
Core AI
(7)
Machine Learning
(5)
Deep Learning
(4)
Natural Language Processing
(3)
Architectures
(3)
Optimization & Theory Β· Machine Learning
(3)
Resources & Methods
(3)
Application Areas
(2)
Learning Types
(2)
Optimization & Theory Β· Deep Learning
(2)
Applications
(1)
Core Methods
(1)
Learning Paradigms
(1)
Models
(1)
Keywords
large language model
(3)
in-context learning
(2)
prefix tuning
(2)
universal approximator
(2)
model evaluation
(1)
universal approximation
(1)
transformer
(1)
instruction following
(1)
theoretical analysis
(1)
safety alignment
(1)
lipschitz continuity
(1)
deep learning model
(1)
state space model
(1)
recurrent neural network
(1)
language model
(1)
foundation model
(1)
generative ai
(1)
attention head
(1)
multilingual fairness
(1)
prompt tuning
(1)
Papers
Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models
ICLR 2025
Language-Models-as-a-Service: Overview of a New Paradigm and its Challenges
AAAI 2025
Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI
ICML 2024
Prompting a Pretrained Transformer Can Be a Universal Approximator
ICML 2024
Universal In-Context Approximation By Prompting Fully Recurrent Models
NeurIPS 2024
When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
ICLR 2024
Certifying Ensembles: A General Certification Theory with S-Lipschitzness
ICML 2023
Language Model Tokenizers Introduce Unfairness Between Languages
NeurIPS 2023