arxiv:2508.10142
Arian Hosseini
arianhosseini
·
AI & ML interests
large language models, reasoning, planning, systematic generalization
Recent Activity
authored
a paper
22 days ago
Deep Language Networks: Joint Prompt Training of Stacked LLMs using
Variational Inference
authored
a paper
22 days ago
The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR
Summarization
authored
a paper
22 days ago
Generative Verifiers: Reward Modeling as Next-Token Prediction
Organizations
models
20
arianhosseini/polIter_qwen2.5_math_1.5B_genppo_MATH_sft_0
Updated
arianhosseini/rebecca-hansen-cadetblue
3B
•
Updated
•
3
arianhosseini/mary-snyder-paleturquoise
3B
•
Updated
•
3
arianhosseini/jeffrey-pruitt-white
Updated
arianhosseini/thomas-garcia-peachpuff
Updated
•
3
arianhosseini/lisa-vance-magenta
Updated
•
4
arianhosseini/rachel-james-dds-deepskyblue
Updated
arianhosseini/courtney-rivera-darkblue
Updated
arianhosseini/jeffrey-walker-teal
3B
•
Updated
•
3
arianhosseini/patricia-walters-darkmagenta
3B
•
Updated
•
4
datasets
36
arianhosseini/mt_puzzles
Viewer
•
Updated
•
2.5k
•
324
arianhosseini/r1_1.5_dedup_fil_0to34000_thresh1_25333points
Viewer
•
Updated
•
25.3k
•
8
arianhosseini/llama70b_code_256sol_ver32_pickles
Viewer
•
Updated
•
2
•
20
arianhosseini/lcb127_llama70b_256sol
Preview
•
Updated
•
4
arianhosseini/gemma27b_it_math_128_generations
Viewer
•
Updated
•
128
•
5
arianhosseini/gemma27b_it_math_500_generations
Viewer
•
Updated
•
500
•
6
arianhosseini/verified_questions_ind_2308_to_2896
Viewer
•
Updated
•
8.63k
•
6
arianhosseini/lcb_127_llama70b_128sol
Viewer
•
Updated
•
127
•
5
arianhosseini/lcb127_llama70b_64sol_temp0_6
Updated
•
91
arianhosseini/lcb128_llama3-8B-instruct_256samples_ver32_temp0-7
Viewer
•
Updated
•
25.6k
•
4