On the Limits of Test-Time Compute for Self-Evaluation Paper • 2611.00350 • Published 14 days ago • 4
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL Paper • 2606.19162 • Published Jun 17 • 22
anirudhb11/rebase_vgs_gpt-oss-20b_rg_games_ns128_md4_bt0_1_seed42_rg_games_vgs_2gpu Viewer • Updated May 7 • 12.8k • 20
anirudhb11/rebase_vgs_gpt-oss-20b_rg_games_ns32_md4_bt0_1_seed42_rg_games_vgs_2gpu Viewer • Updated May 7 • 3.2k • 12
anirudhb11/rebase_vgs_gpt-oss-20b_rg_games_ns8_md4_bt0_1_seed42_rg_games_vgs_2gpu Viewer • Updated May 7 • 800 • 14
anirudhb11/rebase_vgs_gpt-oss-20b_rg_cognition_ns128_md4_bt0_1_seed42_rg_cognition_vgs_2gpu Viewer • Updated May 7 • 12.8k • 8
anirudhb11/rebase_vgs_gpt-oss-20b_rg_cognition_ns32_md4_bt0_1_seed42_rg_cognition_vgs_2gpu Viewer • Updated May 7 • 3.2k • 11
anirudhb11/rebase_vgs_gpt-oss-20b_rg_cognition_ns8_md4_bt0_1_seed42_rg_cognition_vgs_2gpu Viewer • Updated May 7 • 800 • 11
anirudhb11/rebase_vgs_gpt-oss-20b_lcb_v6_ns128_md4_bt0_1_seed42_lcb_v6_vgs_2gpu Viewer • Updated May 7 • 16.8k • 120
anirudhb11/rebase_vgs_gpt-oss-20b_lcb_v6_ns32_md4_bt0_1_seed42_lcb_v6_vgs_2gpu Viewer • Updated May 7 • 4.19k • 17
anirudhb11/rebase_vgs_gpt-oss-20b_lcb_v6_ns8_md4_bt0_1_seed42_lcb_v6_vgs_2gpu Viewer • Updated May 7 • 1.05k • 17
anirudhb11/rebase_vgs_gpt-oss-20b_hard_math_datasets_ns128_md4_bt0_1_seed42_hmmt_2025_vgs_2gpu Viewer • Updated May 7 • 3.84k • 5
anirudhb11/rebase_vgs_gpt-oss-20b_hard_math_datasets_ns32_md4_bt0_1_seed42_hmmt_2025_vgs_2gpu Viewer • Updated May 7 • 960 • 13
anirudhb11/rebase_vgs_gpt-oss-20b_hard_math_datasets_ns8_md4_bt0_1_seed42_hmmt_2025_vgs_2gpu Viewer • Updated May 7 • 240 • 18
anirudhb11/rebase_thinkprm_gpt-oss-20b_rg_games_ns128_md4_bt0_1_seed42_rg_games_thinkprm_2gpu Viewer • Updated May 7 • 12.8k • 4
anirudhb11/rebase_thinkprm_gpt-oss-20b_rg_games_ns32_md4_bt0_1_seed42_rg_games_thinkprm_2gpu Viewer • Updated May 7 • 3.2k • 8
anirudhb11/rebase_thinkprm_gpt-oss-20b_rg_games_ns8_md4_bt0_1_seed42_rg_games_thinkprm_2gpu Viewer • Updated May 7 • 800 • 10
anirudhb11/rebase_thinkprm_gpt-oss-20b_rg_cognition_ns128_md4_bt0_1_seed42_rg_cognition_thinkprm_2gpu Viewer • Updated May 7 • 12.8k • 14
anirudhb11/rebase_thinkprm_gpt-oss-20b_rg_cognition_ns32_md4_bt0_1_seed42_rg_cognition_thinkprm_2gpu Viewer • Updated May 7 • 3.2k • 4
anirudhb11/rebase_thinkprm_gpt-oss-20b_rg_cognition_ns8_md4_bt0_1_seed42_rg_cognition_thinkprm_2gpu Viewer • Updated May 7 • 800 • 8