Arash Ahmadian
8 papers · 2023–2025 · 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(25)
🐣
Hot Topic Early Bird
⚡
Prolific Year · Productive
Venues
Top co-authors
Research topics
Machine Learning
(8)
Artificial Intelligence
(5)
Optimization & Theory
(5)
Core AI
(4)
Learning Types · Machine Learning
(4)
Deep Learning
(3)
Application Areas
(3)
Natural Language Processing
(2)
Reinforcement Learning
(2)
Learning Types · Deep Learning
(2)
Methods
(2)
Resources & Methods
(2)
Interdisciplinary
(1)
Architectures
(1)
Bayesian & Probabilistic
(1)
Keywords
large language model
(4)
preference optimization
(3)
model compression
(2)
model alignment
(2)
reinforcement learning
(2)
cross-lingual transfer
(2)
reinforcement learning from human feedback
(2)
neural architecture
(1)
policy gradient
(1)
contrastive learning
(1)
neural network optimization
(1)
ai safety
(1)
responsible ai
(1)
instruction tuning
(1)
language model
(1)
language model alignment
(1)
off-policy learning
(1)
safety alignment
(1)
adversarial training
(1)
policy optimization
(1)
Papers
Calibrated Value-Aware Model Learning with Probabilistic Environment Models
ICML 2025
Self-Improving Robust Preference Optimization
ICLR 2025
Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs
ACL 2024
Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion
EMNLP 2024
Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning
ICLR 2024
RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs
EMNLP 2024
The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm
EMNLP 2024
Intriguing Properties of Quantization at Scale
NeurIPS 2023