arxiv:2410.01748
Arian Hosseini
arianhosseini
AI & ML interests
large language models, reasoning, planning, systematic generalization
Organizations
Papers
2
models
19
arianhosseini/rebecca-hansen-cadetblue
Updated
•
1
arianhosseini/mary-snyder-paleturquoise
Updated
•
1
arianhosseini/jeffrey-pruitt-white
Updated
arianhosseini/thomas-garcia-peachpuff
Updated
arianhosseini/lisa-vance-magenta
Updated
•
2
arianhosseini/rachel-james-dds-deepskyblue
Updated
arianhosseini/courtney-rivera-darkblue
Updated
arianhosseini/jeffrey-walker-teal
Updated
•
2
arianhosseini/patricia-walters-darkmagenta
Updated
•
2
arianhosseini/patricia-johnson-yellow
Updated
datasets
14
arianhosseini/hh_sft
Viewer
•
Updated
•
169k
•
34
arianhosseini/hh_with_prompt
Viewer
•
Updated
•
169k
•
42
arianhosseini/ultrafeedback_binarized_relabel1b
Viewer
•
Updated
•
63.1k
•
37
arianhosseini/summ_dpo1b1_ngen10_max_2ndmax
Viewer
•
Updated
•
20k
•
36
arianhosseini/summ_dpo1b1_ngen10_minmax
Viewer
•
Updated
•
20k
•
36
arianhosseini/comparisons_20k_regen_labeled_dpo1b1
Viewer
•
Updated
•
20k
•
36
arianhosseini/quail_with_tree_depth
Viewer
•
Updated
•
13k
•
36
arianhosseini/summarize_dpo1b1_ngen10_20k
Viewer
•
Updated
•
20k
•
56
arianhosseini/swag_formatted_to_quail
Viewer
•
Updated
•
93.6k
•
42
arianhosseini/openai_comparisons_20k_regen_and_relabelled
Viewer
•
Updated
•
25k
•
43