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 1 hour ago
laion/nemotron-gym-qa-abstention-v2 published a dataset about 1 hour ago
laion/nemotron-gym-qa-abstention-v2 updated a dataset about 1 hour ago
laion/nemotron-gym-math-v4Organizations
models 54
penfever/nl2bash-3k-traces-restore-hp
Text Generation • 308k • Updated • 6
penfever/nl2bash-1k-traces-restore-hp
Text Generation • 308k • Updated • 8
penfever/kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k
Text Generation • 308k • Updated • 15
penfever/GLM-4_6-gemini25flash-stackexchange-overflow-32ep-512k-fixeps
Text Generation • 308k • Updated • 15
penfever/GLM-4_6-taskmaster2-32eps-32k-fixeps
Text Generation • 308k • Updated • 12
penfever/nl2bash-verified-GLM-4_6-traces-32ep-32k-dft
Text Generation • 308k • Updated • 11
penfever/GLM-4_6-inferredbugs-32eps-65k-fixeps
308k • Updated • 3
penfever/glm46-ling-coder-sft-sandboxes-1-maxeps-131k
Text Generation • 308k • Updated • 11 •
penfever/nl2bash_gpt-5-nano-traces-8ep-restore-hp
Text Generation • 308k • Updated • 17 •
penfever/rl__24GPU_base__exp_rpt_pymethods2test-large__qwen3base-GLM-4_7-sw-70
8B • Updated • 4
datasets 257
penfever/a3-rl-DCAgent_exp_rpt_pymethods2test-large
Viewer • Updated • 47.2k
penfever/exp_rpt_pymethods2test-v3-minimax-m27-131k-traces
Viewer • Updated • 465
penfever/a3-rl-DCAgent_mix_h4_binary_easy
Viewer • Updated • 31.9k
penfever/a3-rl-DCAgent_mix_h2_language_proportional
Viewer • Updated • 45.8k
penfever/a3-rl-qwen3-8b-ablation-report
Viewer • Updated • 1
penfever/exp_rpt_nemotron-junit-minimax-m27-131k-traces
Viewer • Updated • 3.97k • 5
penfever/exp_rpt_e2egit-large-minimax-m27-131k-traces
Viewer • Updated • 4.98k • 11
penfever/a3-rl-DCAgent_selfinstruct-naive-sandboxes-2-verified
Viewer • Updated • 44.4k • 9
penfever/exp_rpt_e2egit-v2-minimax-m27-131k-traces
Viewer • Updated • 497 • 10
penfever/exp_rpt_curriculum-easy-minimax-m27-131k-traces
Viewer • Updated • 514 • 10