Arash Ahmadian
8 papers · 2023–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (5) π Renaissance Researcher (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (18)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
β‘
Prolific Year
(5)
Conferences
EMNLP (3)
ICLR (2)
ACL (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
large language model
(4)
preference optimization
(2)
cross-lingual transfer
(2)
reinforcement learning from human feedback
(2)
model alignment
(2)
policy gradient
(1)
language model alignment
(1)
responsible ai
(1)
neural network optimization
(1)
ai safety
(1)
safety alignment
(1)
off-policy learning
(1)
model fine-tuning
(1)
proximal policy optimization
(1)
red teaming
(1)
language model finetuning
(1)
multilingual language model
(1)
alignment training
(1)
sequence-level optimization
(1)
multilingual alignment
(1)
Papers
Calibrated Value-Aware Model Learning with Probabilistic Environment Models
ICML 2025
Self-Improving Robust Preference Optimization
ICLR 2025
The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm
EMNLP 2024
RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs
EMNLP 2024
Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning
ICLR 2024
Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion
EMNLP 2024
Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs
ACL 2024
Intriguing Properties of Quantization at Scale
NIPS 2023