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 2 minutes ago
laion/CoderForge-Preview-v6-1000 published a dataset 2 minutes ago
laion/CoderForge-Preview-v6-1000 updated a dataset 2 minutes ago
laion/CoderForge-Preview-v6-316Organizations
models 54
penfever/nl2bash-3k-traces-restore-hp
Text Generation • 308k • Updated • 346
penfever/nl2bash-1k-traces-restore-hp
Text Generation • 308k • Updated • 139
penfever/kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k
Text Generation • 308k • Updated • 317
penfever/GLM-4_6-gemini25flash-stackexchange-overflow-32ep-512k-fixeps
Text Generation • 308k • Updated • 302
penfever/GLM-4_6-taskmaster2-32eps-32k-fixeps
Text Generation • 308k • Updated • 282
penfever/nl2bash-verified-GLM-4_6-traces-32ep-32k-dft
Text Generation • 308k • Updated • 243
penfever/GLM-4_6-inferredbugs-32eps-65k-fixeps
Text Generation • 308k • Updated • 383
penfever/glm46-ling-coder-sft-sandboxes-1-maxeps-131k
Text Generation • 308k • Updated • 353
penfever/nl2bash_gpt-5-nano-traces-8ep-restore-hp
Text Generation • 308k • Updated • 338
penfever/rl__24GPU_base__exp_rpt_pymethods2test-large__qwen3base-GLM-4_7-sw-70
8B • Updated • 3
datasets 202
penfever/a2-rl-softwareheritage_v2
Viewer • Updated • 7.65k
penfever/a2-rl-stack_jest_v2
Viewer • Updated • 7.17k
penfever/Kimi-2.5-r2egym_sandboxes-maxeps-32k-3pct
Viewer • Updated • 129 • 23
penfever/Kimi-2.5-r2egym_sandboxes-maxeps-32k-10pct
Viewer • Updated • 432 • 27
penfever/meta-llama_Llama-3.1-70B-Instruct-jdgfct-Conciseness
Viewer • Updated • 985k • 57
penfever/nvidia_NVLM-D-72B-jdgfct-Harmlessness
Viewer • Updated • 987k • 63
penfever/Nexusflow_Athene-70B-jdgfct-Factuality
Viewer • Updated • 984k • 85
penfever/Nexusflow_Athene-70B-jdgfct-Completeness
Viewer • Updated • 984k • 64
penfever/nvidia_NVLM-D-72B-jdgfct-Completeness
Viewer • Updated • 987k • 62
penfever/meta-llama_Llama-3.1-70B-Instruct-jdgfct-Factuality
Viewer • Updated • 1M • 82