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
penfever/nemotron-gym-competitive-coding-minimax-m27-131k-traces_chunk1 published a dataset about 1 hour ago
penfever/nemotron-gym-competitive-coding-minimax-m27-131k-traces_chunk1 updated a dataset about 1 hour ago
penfever/nemotron-gym-competitive-coding-minimax-m27-131k-traces_chunk4Organizations
models 56
penfever/stageD-thinkbudget-80-8B
8B • Updated • 26
penfever/a3-rl-SankalpKJ_swesmith-oracle-filtered-40-8B
Reinforcement Learning • 8B • Updated • 24
penfever/nl2bash-3k-traces-restore-hp
Text Generation • 308k • Updated • 5
penfever/nl2bash-1k-traces-restore-hp
Text Generation • 308k • Updated • 3
penfever/kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k
Text Generation • 308k • Updated • 5
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 • 4
penfever/nl2bash-verified-GLM-4_6-traces-32ep-32k-dft
Text Generation • 308k • Updated • 2
penfever/GLM-4_6-inferredbugs-32eps-65k-fixeps
308k • Updated • 1
penfever/glm46-ling-coder-sft-sandboxes-1-maxeps-131k
Text Generation • 308k • Updated • 3 •
datasets 340
penfever/nemotron-gym-competitive-coding-minimax-m27-131k-traces_chunk1
Viewer • Updated • 237
penfever/nemotron-gym-competitive-coding-minimax-m27-131k-traces_chunk4
Viewer • Updated • 270
penfever/nemotron-gym-competitive-coding-minimax-m27-131k-traces_chunk0
Viewer • Updated • 271
penfever/nemotron-gym-competitive-coding-minimax-m27-131k-traces_chunk2
Viewer • Updated • 272
penfever/nemotron-gym-competitive-coding-minimax-m27-131k-traces_chunk3
Viewer • Updated • 271
penfever/nemotron-gym-instruction-following-calendar-minimax-m27-131k-traces
Viewer • Updated • 8.29k
penfever/lever2-pilot-glm47-swesmith-t16384-32k-traces
Viewer • Updated • 388
penfever/lever2-pilot-glm47-swesmith-t8192-32k-traces
Viewer • Updated • 200
penfever/lever2-pilot-glm47-swesmith-t16384-64k-traces
Viewer • Updated • 89
penfever/nemotron-gym-math-advanced-calculations-v3-qwen3.5-122b-32k-traces
Viewer • Updated • 5.29k • 5