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 model about 4 hours ago
penfever/GLM-4_6-gemini25flash-stackexchange-overflow-32ep-512k-fixeps updated a model about 17 hours ago
penfever/GLM-4_6-taskmaster2-32eps-32k-fixeps updated a model about 19 hours ago
penfever/nl2bash-verified-GLM-4_6-traces-32ep-32k-dftOrganizations
models 54
penfever/GLM-4_6-gemini25flash-stackexchange-overflow-32ep-512k-fixeps
Text Generation • 308k • Updated • 5
penfever/GLM-4_6-taskmaster2-32eps-32k-fixeps
Text Generation • 308k • Updated • 189
penfever/nl2bash-verified-GLM-4_6-traces-32ep-32k-dft
Text Generation • 308k • Updated • 192
penfever/GLM-4_6-inferredbugs-32eps-65k-fixeps
Text Generation • 308k • Updated • 351
penfever/glm46-ling-coder-sft-sandboxes-1-maxeps-131k
Text Generation • 308k • Updated • 317
penfever/nl2bash_gpt-5-nano-traces-8ep-restore-hp
Text Generation • 308k • Updated • 308
penfever/rl__24GPU_base__exp_rpt_pymethods2test-large__qwen3base-GLM-4_7-sw-70
8B • Updated • 7
penfever/rl__24GPU_base__exp_rpt_pymethods2test-large__Qwen3-8B-Base-65
8B • Updated • 9
penfever/rl__24GPU_base__exp_rpt_curriculum-hard__r2egym-nl2bash-stack-15
8B • Updated • 7
penfever/rl_rl-conf_24GP_base-yaml_mode-path_r2eg-nl2b-stac-bugs-fixt_trai-data_exp_rpt_soft-v2-45
8B • Updated • 1
datasets 198
penfever/rl__64GPU_base_32b__nl2bash-tasks-cleaned-oracle__syh-r2eg-askl-glm_4__40-0
Updated • 24
penfever/rl__24GPU_shaped__stackexchange-overflow-sandboxes-skywork-response__exp_tas_optimal_comb__40-0
Viewer • Updated • 41.8k • 57
penfever/rl__24GPU_shaped__inferredbugs-sandboxes-verifier__exp_tas_optimal_comb__40-0
Viewer • Updated • 30.8k • 53
penfever/rl__64GPU_shaped_32b_entropy__swe_rebench_patched_oracle__syh-r2eg-askl-glm_4__40-0
Viewer • Updated • 8.51k • 37
penfever/rl__24GPU_shaped__nemotron-math-oracle-filtered__exp_tas_optimal_comb__40-0
Viewer • Updated • 22.4k • 41
penfever/Kimi-2.5-r2egym_sandboxes-maxeps-32k-reward1
Viewer • Updated • 2.82k • 27
penfever/Kimi-2.5-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-32k-reward1
Viewer • Updated • 5.24k • 31
penfever/Kimi-2.5-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-32k
Viewer • Updated • 9.36k • 43
penfever/rl__24GPU_shaped_entropy__swe_rebench_patched_oracle__100k_wd0__Qwen3-8B__20-0
Viewer • Updated • 9.97k • 40
penfever/rl__24GPU_shaped__selfinstruct-naive-sandboxes-2-verified__exp_tas_optimal_comb__40-0
Viewer • Updated • 30.2k • 40