arxiv:2606.24855
Benjamin Feuer
penfever
AI & ML interests
Deep learning, computer vision, large language models, large vision language models
Recent Activity
updated a dataset about 2 hours ago
DCAgent2/terminal_bench_2_a3_rl_DCAgent_mix_h2_language_proportional_65_8B_20260703_180043 published a dataset about 2 hours ago
DCAgent2/terminal_bench_2_a3_rl_DCAgent_mix_h2_language_proportional_65_8B_20260703_180043 updated a dataset about 4 hours ago
DCAgent2/swebench_verified_random_100_folders_a3_rl_DCAgent_exp_rpt_curriculum_medium_10d4d1e706Organizations
models 56
penfever/stageD-thinkbudget-80-8B
8B • Updated • 32
penfever/a3-rl-SankalpKJ_swesmith-oracle-filtered-40-8B
Reinforcement Learning • 8B • Updated • 27
penfever/nl2bash-3k-traces-restore-hp
Text Generation • 308k • Updated • 4
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 • 4
penfever/GLM-4_6-gemini25flash-stackexchange-overflow-32ep-512k-fixeps
Text Generation • 308k • Updated • 3
penfever/GLM-4_6-taskmaster2-32eps-32k-fixeps
Text Generation • 308k • Updated • 7
penfever/nl2bash-verified-GLM-4_6-traces-32ep-32k-dft
Text Generation • 308k • Updated • 5
penfever/GLM-4_6-inferredbugs-32eps-65k-fixeps
308k • Updated • 4
penfever/glm46-ling-coder-sft-sandboxes-1-maxeps-131k
Text Generation • 308k • Updated • 18 •
datasets 384
penfever/VERIFY-DRYRUN
Updated
penfever/nemotron-gym-agent-workplace-v2-qwen3.5-122b-131k-opencode-traces
Viewer • Updated • 296 • 12
penfever/terminal_bench_2_exp_psu_swesmith_1K_glm_4_7_traces_jupiter__6_0__Qwen3_8B_2026cb1101a1
Viewer • Updated • 2.81k • 7 • 1
penfever/terminal_bench_2_exp_psu_swesmith_1K_glm_4_7_traces_jupiter__4_0__Qwen3_8B_20264b24e003
Viewer • Updated • 2.73k • 8 • 1
penfever/nemotron-gym-if-v2-qwen3.5-122b-32k-traces
Viewer • Updated • 25.2k • 141
penfever/swesmith-oracle-filtered-qwen3.5-122b-32k-traces
Viewer • Updated • 864 • 8
penfever/swe-rebench-patched-oracle-qwen3.5-122b-32k-traces
Viewer • Updated • 25
penfever/delphi-6279-qwen3-base-passatk-evals
Updated • 27
penfever/nemotron-gym-competitive-coding-qwen3.5-122b-32k-traces
Viewer • Updated • 11.2k • 33
penfever/nemotron-cpp-qwen3.5-122b-32k-traces
Viewer • Updated • 3.93k • 71