arxiv:2410.01748
Arian Hosseini
arianhosseini
·
AI & ML interests
large language models, reasoning, planning, systematic generalization
Recent Activity
updated
a model
4 days ago
ReasoningMila/polIter_qwen2.5_math_1.5B_inst_ppo_MATH_ckpt__iter_0047__epoch_2.00_step_1504
published
a model
4 days ago
ReasoningMila/polIter_qwen2.5_math_1.5B_inst_ppo_MATH_ckpt__iter_0047__epoch_2.00_step_1504
updated
a dataset
7 days ago
arianhosseini/aime24
Organizations
Papers
2
models
19
arianhosseini/rebecca-hansen-cadetblue
Updated
•
6
arianhosseini/mary-snyder-paleturquoise
Updated
•
8
arianhosseini/jeffrey-pruitt-white
Updated
arianhosseini/thomas-garcia-peachpuff
Updated
•
6
arianhosseini/lisa-vance-magenta
Updated
•
4
arianhosseini/rachel-james-dds-deepskyblue
Updated
arianhosseini/courtney-rivera-darkblue
Updated
arianhosseini/jeffrey-walker-teal
Updated
•
5
arianhosseini/patricia-walters-darkmagenta
Updated
•
9
arianhosseini/patricia-johnson-yellow
Updated
datasets
19
arianhosseini/aime24
Viewer
•
Updated
•
30
•
13
arianhosseini/math250_llama3p3-70B-instruct_256samples_ver32_temp0-7
Updated
•
8
arianhosseini/qwq_zeroshot_math7500_train_verification_cot
Viewer
•
Updated
•
19k
•
27
arianhosseini/llama_3.3_70B_inst_verify
Updated
•
981
arianhosseini/llama_3.3_70B_inst_generations
Updated
•
38
arianhosseini/hh_sft
Viewer
•
Updated
•
169k
•
41
arianhosseini/hh_with_prompt
Viewer
•
Updated
•
169k
•
43
arianhosseini/ultrafeedback_binarized_relabel1b
Viewer
•
Updated
•
63.1k
•
42
arianhosseini/summ_dpo1b1_ngen10_max_2ndmax
Viewer
•
Updated
•
20k
•
61
arianhosseini/summ_dpo1b1_ngen10_minmax
Viewer
•
Updated
•
20k
•
56