Privileged On-Policy Exploration

classroom

AI & ML interests

None defined yet.

Recent Activity

CohenQu published a model about 8 hours ago

CMU-POPE/Qwen3-VL-4B-Instruct-rebuttal-step100

CohenQu updated a model about 8 hours ago

CMU-POPE/Qwen3-VL-4B-Instruct-rebuttal-step100

CohenQu updated a model about 2 months ago

CMU-POPE/MIRROR-glm41v-grpo-base-ckpts

View all activity

CMU-POPE 's models 20

CMU-POPE/Qwen3-VL-4B-Instruct-rebuttal-step100

Image-Text-to-Text • 5B • Updated about 8 hours ago • 12

CMU-POPE/MIRROR-glm41v-grpo-base-ckpts

CMU-POPE/MIRROR-qwen3vl-rankkl-ema-d0.99-c0p05

CMU-POPE/MIRROR-qwen3vl-rankkl-ema-d0.99-c0p001

CMU-POPE/MIRROR-qwen3vl-rankkl-ema-d0.99-c0p02

CMU-POPE/MIRROR-qwen3vl-rankkl-ema-d0.99-c0p005

CMU-POPE/MIRROR-qwen3vl-rankkl-ema-d0.99

CMU-POPE/MIRROR-qwen3vl-rankkl-noema

CMU-POPE/Qwen3.5-9B-aisci-rubric-v03.03

CMU-POPE/Qwen3.5-4B-aisci-rubric-v03.02

CMU-POPE/Qwen3.5-9B-aisci-rubric-v03.01

CMU-POPE/Qwen3.5-4B-aisci-rubric-v03.00

CMU-POPE/ODA_modality_kl_random_modkl0p01

CMU-POPE/ODA_rank_kl_rankkl0p1

CMU-POPE/ODA_rank_kl_from_privkl_rankkl0p01

CMU-POPE/ODA_always_privileged_kl_privkl0p005

CMU-POPE/ODA_rank_kl_wrefkl_rankkl0p01

CMU-POPE/ODA_modality_kl_modkl0p005_dirtext_to_image

CMU-POPE/ODA_rank_kl_wrefkl_rankkl0p001

CMU-POPE/ODA_modality_kl_modkl0p005_dirimage_to_text