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 6 hours ago
open-thoughts/OpenThinkerAgent-8B-RL updated a model about 6 hours ago
open-thoughts/OpenThinkerAgent-8B-ColdStartSFTForRL updated a dataset about 6 hours ago
open-thoughts/OpenThoughts-Agent-SFT-ColdStartForRL-10KOrganizations
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 • 14
penfever/GLM-4_6-gemini25flash-stackexchange-overflow-32ep-512k-fixeps
Text Generation • 308k • Updated • 14
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 • 10
penfever/GLM-4_6-inferredbugs-32eps-65k-fixeps
308k • Updated • 3
penfever/glm46-ling-coder-sft-sandboxes-1-maxeps-131k
Text Generation • 308k • Updated • 12 •
penfever/nl2bash_gpt-5-nano-traces-8ep-restore-hp
Text Generation • 308k • Updated • 16 •
penfever/rl__24GPU_base__exp_rpt_pymethods2test-large__qwen3base-GLM-4_7-sw-70
8B • Updated • 3
datasets 270
penfever/code-contests-noblock-qwen3.5-122b-32k-traces
Viewer • Updated • 6.93k • 7
penfever/ablation-pymethods2test-seqnorm
Viewer • Updated • 44.1k • 6
penfever/ablation-pymethods2test-seqmean-arm0
Viewer • Updated • 5.18k • 8
penfever/ablation-pymethods2test-shaped
Viewer • Updated • 40.1k • 7
penfever/nemotron-gym-agent-workplace-v2-minimax-m27-131k-traces
Viewer • Updated • 297 • 22
penfever/nemotron-gym-knowledge-web-search-mcqa-minimax-m27-131k-traces
Viewer • Updated • 2.91k • 21
penfever/exp_rpt_crosscodeeval-csharp-v4-minimax-m27-131k-traces
Viewer • Updated • 1.69k • 22
penfever/a3-rl-qwen3-8b-ablation-report
Viewer • Updated • 1 • 41
penfever/nemotron-gym-agent-calendar-minimax-m27-131k-traces
Viewer • Updated • 3.27k • 25
penfever/code-contests-noblock-qwen3.5-122b-32k-traces-r1
Viewer • Updated • 5.64k • 52