Arian Hosseini
Identifiers
- name variant Arian Hosseini 0.60 · backfill
Papers (13)
- Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMs cs.CL · 2025 · author #3
- Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers cs.LG · 2025 · author #5
- Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models cs.LG · 2024 · author #4
- Not All LLM Reasoners Are Created Equal cs.LG · 2024 · author #1
- Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling cs.CL · 2024 · author #2
- Generative Verifiers: Reward Modeling as Next-Token Prediction cs.LG · 2024 · author #2
- The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization cs.LG · 2024 · author #3
- V-STaR: Training Verifiers for Self-Taught Reasoners cs.LG · 2024 · author #1
- Joint Prompt Optimization of Stacked LLMs using Variational Inference cs.CL · 2023 · author #7
- On the Compositional Generalization Gap of In-Context Learning cs.CL · 2022 · author #1
- Understanding by Understanding Not: Modeling Negation in Language Models cs.CL · 2021 · author #1
- Ordered Memory cs.LG · 2019 · author #3
- Learning to Understand Goal Specifications by Modelling Reward cs.AI · 2018 · author #5
Mentions
- 2508.10142 #3 · arxiv_oai · confidence 0.70 Arian Hosseini
- 2410.18252 #4 · arxiv_oai · confidence 0.70 Arian Hosseini
- 2408.15240 #2 · arxiv_oai · confidence 0.70 Arian Hosseini
- 2408.16737 #2 · arxiv_oai · confidence 0.70 Arian Hosseini
- 2410.01748 #1 · arxiv_oai · confidence 0.70 Arian Hosseini
- 2402.06457 #1 · arxiv_oai · confidence 0.70 Arian Hosseini
- 2403.17031 #3 · arxiv_oai · confidence 0.70 Arian Hosseini
- 2306.12509 #7 · arxiv_oai · confidence 0.70 Arian Hosseini
- 2211.08473 #1 · arxiv_oai · confidence 0.70 Arian Hosseini
- 2105.03519 #1 · arxiv_oai · confidence 0.70 Arian Hosseini
- 1806.01946 #5 · arxiv_oai · confidence 0.70 Arian Hosseini
- 1910.13466 #3 · arxiv_oai · confidence 0.70 Arian Hosseini
Frequent Coauthors
- Alessandro Sordoni 7 shared papers
- Aaron Courville 6 shared papers
- Rishabh Agarwal 6 shared papers
- Dzmitry Bahdanau 3 shared papers
- Mehran Kazemi 3 shared papers
- Hritik Bansal 2 shared papers
- Michael Noukhovitch 2 shared papers
- Shengyi Huang 2 shared papers
- Xingdi Yuan 2 shared papers
- Abhimanyu Goyal 1 shared papers
- Adam Trischler 1 shared papers
- Ankit Vani 1 shared papers
- Aviral Kumar 1 shared papers
- Bahare Fatemi 1 shared papers
- Daniel Toyama 1 shared papers
- Edward Grefenstette 1 shared papers
- Edward Hughes 1 shared papers
- Felix Hill 1 shared papers
- Friederike Niedtner 1 shared papers
- Jan Leike 1 shared papers