·
AI & ML interests
None yet
Organizations
CohenQu/Instruct-POPE-arxiv-medium-WG-hard-4WG-entropy
Updated
CohenQu/Instruct-POPE-arxiv-medium-WG-hard-4WG
Updated
CohenQu/Instruct-POPE-arxiv-medium-WG-V3s
Updated
CohenQu/Instruct-POPE-arxiv-medium-WG-hard-WG-entropy
Updated
CohenQu/Instruct-POPE-arxiv-medium-WG-V2s
Updated
CohenQu/Instruct-POPE-arxiv-medium-hards
Updated
CohenQu/Instruct-POPE-arxiv-medium-WG-hard-WGs
Updated
CohenQu/Instruct-POPE-arxiv-medium-easier
Updated
CohenQu/POPE-arxiv-hard-first_guide-no_guide-mbz
4B
•
Updated
•
44
CohenQu/SFT-POPE-arxiv-medium
Updated
CohenQu/Instruct-POPE-arxiv-medium-WG-easy
Updated
CohenQu/Instruct-POPE-arxiv-medium-WG-hard
Updated
CohenQu/Instruct-POPE-arxiv-medium-easy
Updated
CohenQu/Instruct-POPE-iter1-step280-POPE-hard-first_guide-no_guide-iter2
4B
•
Updated
•
31
CohenQu/Qwen3-4B-Instruct-POPE-hard-first_guide-no_guide-v2
4B
•
Updated
•
4
CohenQu/Qwen3-4B-Instruct-POPE-hard-no_guide-v2
4B
•
Updated
•
5
CohenQu/Qwen3-4B-Instruct-POPE-hard-first_guide-no_guide_cphigh_0.26
4B
•
Updated
•
9
CohenQu/POPE-SFT-iter3-POPE-hard-no_guide
4B
•
Updated
•
5
CohenQu/Instruct-POPE-hard-first_guide-no_guide
4B
•
Updated
•
6
CohenQu/Qwen2.5-SFT-Continue_vs_Terminate.05-verl
3B
•
Updated
•
4
CohenQu/Qwen2.5-3B-Instruct_Continue_vs_Terminate.05.00
Text Generation
•
3B
•
Updated
•
6
CohenQu/sft_Qwen3-1.7B_Continue_vs_Terminate.05.00_orchard
Text Generation
•
2B
•
Updated
•
7
CohenQu/sft_Qwen3-1.7B_Continue_vs_Terminate.05.01_orchard
Text Generation
•
2B
•
Updated
•
5
CohenQu/Qwen3-4B-Base_HintGen-withSol.01.01
Text Generation
•
4B
•
Updated
•
9
CohenQu/Qwen3-4B-Base_HintGen-withSol.01.00
Text Generation
•
4B
•
Updated
•
8
CohenQu/Qwen3-4B_HintGen-withSol.01.00
Text Generation
•
4B
•
Updated
•
4
CohenQu/Qwen3-4B-Base_HintGen-withSol.00.01
Text Generation
•
4B
•
Updated
•
11
CohenQu/Qwen3-4B_HintGen-withSol.01.01
Text Generation
•
4B
•
Updated
•
11
CohenQu/Joint-Train-deepscalar_RL_hard_500_verl_0.35_0.001_0.001_32_32_20k_4_0713
2B
•
Updated
•
9
CohenQu/Qwen3-4B_HintGen-withSol.00.01
Text Generation
•
4B
•
Updated
•
7