Mehul Damani's picture

1 2

Mehul Damani PRO

mehuldamani

·

https://damanimehul.github.io

AI & ML interests

Reinforcement Learning, Large Language Models

Recent Activity

published a model about 19 hours ago

mehuldamani/rlcr_single_from_rlvr_chkpt480

updated a dataset about 22 hours ago

mehuldamani/big-math-tough

published a dataset about 22 hours ago

mehuldamani/big-math-tough

View all activity

Organizations

None yet

mehuldamani 's models 196

mehuldamani/rlcr_single_from_rlvr_chkpt480

Updated about 19 hours ago

mehuldamani/rlvr-base-trainRlcr-ConfMoreOne_fracAcc_entroRew_pt5Brier_pt9Temp_reasonInPrompt

Updated 1 day ago

mehuldamani/qwen3_8b_medical_rlvr_multi_k_2

Updated 2 days ago

mehuldamani/qwen3_8b_medical_rlvr_multi_k_4

Updated 2 days ago

mehuldamani/rlvr-base-train-with-rlcr-sumConfMoreOne_fractAcc_pt5Brier_pt9Temp_reasonUncertInPrompt

Updated 2 days ago

mehuldamani/rlcr-multi-from-rlvr-base-sumConfMoreThanOne_pt5Brier-pt9Temp-specifyConf_reasonUncertInPrompt

Updated 2 days ago

mehuldamani/rlcr-multi-from-rlvr-base-train-1pointBrier-point9Temp-specifyConf_reasonUncertInPrompt

Updated 3 days ago

mehuldamani/rlcr-multi-from-rlvr-base-train-point5Brier-1point4Temp-specifyConfSumLessThan1

Updated 3 days ago

mehuldamani/rlcr-multi-from-rlvr-base-train-1pointBrier-point9Temp-specifyConfSumLessThan1

Updated 3 days ago

mehuldamani/rlcr-multi-from-rlvr-base-train-point5Brier-point9Temp-specifyConfSumLessThan1

Updated 3 days ago

mehuldamani/rlcr-multi-from-rlvr-base-train-point5Brier-specifyConfSumLessThan1

Updated 4 days ago

mehuldamani/rlcr-multi-from-rlvr-base-train-point2Brier-specifyConfSumLessThan1

Updated 4 days ago

mehuldamani/rlcr-multi-from-rlvr-base-train-point2Brier

Updated 5 days ago

mehuldamani/rlcr-multi-from-rlvr-base-train-1Brier

Updated 5 days ago

mehuldamani/rlcr-multi-from-rlvr-base-train-point5Brier

Updated 5 days ago

mehuldamani/qwen3_8b_medical_rlcr_multi_separate_uniqueness_reward

Updated 6 days ago

mehuldamani/qwen3_8b_medical_rlcr_multi_without_uniquenessEnforcedInAccReward

Updated 6 days ago

mehuldamani/qwen3_8b_medical_rlvr_multi_with_uniquenessEnforcedInAccReward

Updated 6 days ago

mehuldamani/rlvr_multi_rlCrPrompt_longerLength

Updated 6 days ago

mehuldamani/rlcr_multi_standard

Updated 7 days ago

mehuldamani/rlcr_multi_0_brier

Updated 7 days ago

mehuldamani/qwen3_8b_medical_rlvr_multi_fractionalCorrectness_rlvrPromptOriginal

Updated 7 days ago

mehuldamani/rlvr_multi_rlvrPromptModified

Updated 7 days ago

mehuldamani/rlvr_multi_rlCrPrompt

Updated 7 days ago

mehuldamani/qwen3_8b_medical_rlcr_multiple_scalingBrier_adaptiveKL

Updated 8 days ago

mehuldamani/qwen3_8b_medical_rlcr_multiple_adaptiveBrierWeight

Updated 9 days ago

mehuldamani/qwen3_8b_medical_rlcr_multiple_normalized_moreThanOneCorrectnessPoint

Updated 9 days ago

mehuldamani/qwen3_8b_medical_rlcr_multiple_moreThanOneCorrectnessPoint

Updated 9 days ago

mehuldamani/qwen3_8b_medical_rlcr_multiple_originalSettings_new_prompt

Updated 9 days ago

mehuldamani/qwen3_8b_medical_rlcr_multiple_original_old_prompt

Updated 9 days ago