Arian Hosseini
8 papers · 2019–2025 · 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 ↑
π Interdisciplinary Bridge Β· Bronze π Academic Marathon Β· Sprint πΊοΈ Taxonomy Completionist (22) π£ Hot Topic Early Bird π Conference Polyglot Β· Bronze
π±
Topic Pioneer
π
Trend Setter
Venues
Top co-authors
Research topics
Artificial Intelligence
(5)
Machine Learning
(5)
Natural Language Processing
(4)
Deep Learning
(3)
Core AI
(3)
Learning Paradigms
(3)
Applications
(2)
Architectures
(2)
Core Methods
(2)
Generation
(2)
Optimization & Theory
(2)
Reinforcement Learning
(1)
Application Areas
(1)
Learning Types Β· Deep Learning
(1)
Learning Types Β· Machine Learning
(1)
Keywords
large language model
(3)
instruction following
(2)
variational inference
(1)
direct preference optimization
(1)
attention mechanism
(1)
knowledge distillation
(1)
in-context learning
(1)
language model reasoning
(1)
chain-of-thought reasoning
(1)
semantic parsing
(1)
language modeling
(1)
out-of-distribution generalization
(1)
synthetic data generation
(1)
compositional generalization
(1)
reinforcement learning from human feedback
(1)
off-policy learning
(1)
latent variable
(1)
language model
(1)
asynchronous training
(1)
reward model
(1)
Papers
Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
ICLR 2025
Generative Verifiers: Reward Modeling as Next-Token Prediction
ICLR 2025
Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling
ICLR 2025
Joint Prompt Optimization of Stacked LLMs using Variational Inference
NeurIPS 2023
On the Compositional Generalization Gap of In-Context Learning
EMNLP 2022
Understanding by Understanding Not: Modeling Negation in Language Models
NAACL 2021
Learning to Understand Goal Specifications by Modelling Reward
ICLR 2019
Ordered Memory
NeurIPS 2019