arxiv:2509.20293
Benjamin Feuer PRO
penfever
AI & ML interests
Deep learning, computer vision, large language models, large vision language models
Recent Activity
published a model about 3 hours ago
mlfoundations-dev/sft__g1_gptlong_top8_train_on_obs_fa3__40-0__Qwen3-32B updated a dataset about 11 hours ago
laion/exp_rpt_defects4j-v3-v4 published a dataset about 11 hours ago
laion/exp_rpt_defects4j-v3-v4Organizations
models 54
penfever/nl2bash-3k-traces-restore-hp
Text Generation • 308k • Updated • 27
penfever/nl2bash-1k-traces-restore-hp
Text Generation • 308k • Updated • 30
penfever/kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k
Text Generation • 308k • Updated • 45
penfever/GLM-4_6-gemini25flash-stackexchange-overflow-32ep-512k-fixeps
Text Generation • 308k • Updated • 43
penfever/GLM-4_6-taskmaster2-32eps-32k-fixeps
Text Generation • 308k • Updated • 41
penfever/nl2bash-verified-GLM-4_6-traces-32ep-32k-dft
Text Generation • 308k • Updated • 38
penfever/GLM-4_6-inferredbugs-32eps-65k-fixeps
Text Generation • 308k • Updated • 31
penfever/glm46-ling-coder-sft-sandboxes-1-maxeps-131k
Text Generation • 308k • Updated • 40
penfever/nl2bash_gpt-5-nano-traces-8ep-restore-hp
Text Generation • 308k • Updated • 36
penfever/rl__24GPU_base__exp_rpt_pymethods2test-large__qwen3base-GLM-4_7-sw-70
8B • Updated • 4
datasets 213
penfever/a2-rl-32b-exp_rpt_issue
Viewer • Updated • 29.8k • 50
penfever/a2-rl-32b-code-contests-noblock
Viewer • Updated • 18.5k • 30
penfever/rl__24GPU_base__exp_rpt_pymethods2test-large__GLM-4_7-swesmith-san__40-0
Viewer • Updated • 10.8k • 15
penfever/rl__24GPU_base__exp_rpt_pymethods2test-large__r2egym-nl2bash-stack__40-0
Viewer • Updated • 12.4k • 15
penfever/a2-rl-e2egit_large
Viewer • Updated • 24.3k • 28
penfever/a2-rl-pymethods2test_v3
Viewer • Updated • 7.33k • 29
penfever/a2-rl-2skill
Viewer • Updated • 36.1k • 595
penfever/a2-rl-proportional
Viewer • Updated • 34.5k • 236
penfever/a2-rl-adversarial
Viewer • Updated • 33.5k • 469
penfever/a2-rl-curated
Viewer • Updated • 9.88k • 149