arxiv:2509.20293
Benjamin Feuer PRO
penfever
AI & ML interests
Deep learning, computer vision, large language models, large vision language models
Recent Activity
updated a dataset about 19 hours ago
DCAgent/eval-terminal-bench-2.0__rl__40GPU_base_32b__ctx32k_non_it_16x_eval_ updated a dataset 1 day ago
DCAgent/eval-swebench-verified-random-100-folders__rl__40GPU_base_32b__ctx32k_non_it_16x_eval_ updated a dataset 2 days ago
DCAgent/eval-openthoughts-tblite__rl__40GPU_base_32b__ctx32k_non_it_16x_eval_Organizations
models 54
penfever/rl__24GPU_base__exp_rpt_pymethods2test-large__qwen3base-GLM-4_7-sw-70
8B • Updated • 24
penfever/rl__24GPU_base__exp_rpt_pymethods2test-large__Qwen3-8B-Base-65
8B • Updated • 25
penfever/rl__24GPU_base__exp_rpt_curriculum-hard__r2egym-nl2bash-stack-15
8B • Updated • 18
penfever/rl_rl-conf_24GP_base-yaml_mode-path_r2eg-nl2b-stac-bugs-fixt_trai-data_exp_rpt_soft-v2-45
8B • Updated • 1
penfever/rl_rl-conf_24GP_base_noth-yaml_mode-path_r2eg-nl2b-stac-bugs_trai-data_exp_rpt_stac-bash-110
8B • Updated • 1
penfever/rl_rl-conf_20GP_base-yaml_mode-path_r2eg-nl2b-stac-bugs-fixt_trai-data_exp_rpt_stac-pyte-v2-25
8B • Updated • 1
penfever/rl_rl-conf_20GP_base-yaml_mode-path_r2eg-nl2b-stac-bugs-fixt_trai-data_exp_rpt_code-v2-25
8B • Updated • 1
penfever/rl_bs128_gs16_ruby-30
8B • Updated • 2
penfever/bs64_rloo_n_noct_stri_micr_auto_tis_model_r2e-100
8B • Updated • 11
penfever/bs64_rloo_n_noct_stri_micr_auto_conv_pref_model_r2e-120
Updated
datasets 175
penfever/rl__64GPU_base_32b__nl2bash-tasks-cleaned-oracle__syh-r2eg-askl-glm_4__40-0
Updated • 17
penfever/rl__24GPU_shaped__stackexchange-overflow-sandboxes-skywork-response__exp_tas_optimal_comb__40-0
Viewer • Updated • 41.8k • 51
penfever/rl__24GPU_shaped__inferredbugs-sandboxes-verifier__exp_tas_optimal_comb__40-0
Viewer • Updated • 30.8k • 51
penfever/rl__64GPU_shaped_32b_entropy__swe_rebench_patched_oracle__syh-r2eg-askl-glm_4__40-0
Viewer • Updated • 8.51k • 35
penfever/rl__24GPU_shaped__nemotron-math-oracle-filtered__exp_tas_optimal_comb__40-0
Viewer • Updated • 22.4k • 34
penfever/Kimi-2.5-r2egym_sandboxes-maxeps-32k-reward1
Viewer • Updated • 2.82k • 26
penfever/Kimi-2.5-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-32k-reward1
Viewer • Updated • 5.24k • 30
penfever/Kimi-2.5-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-32k
Viewer • Updated • 9.36k • 42
penfever/rl__24GPU_shaped_entropy__swe_rebench_patched_oracle__100k_wd0__Qwen3-8B__20-0
Viewer • Updated • 9.97k • 36
penfever/rl__24GPU_shaped__selfinstruct-naive-sandboxes-2-verified__exp_tas_optimal_comb__40-0
Viewer • Updated • 30.2k • 38