arxiv:2606.24855
Benjamin Feuer
penfever
AI & ML interests
Deep learning, computer vision, large language models, large vision language models
Recent Activity
updated a collection about 5 hours ago
10T Mixed RLVR updated a model about 5 hours ago
open-athena/Snowball-67B-A2B-10T-Mixed-RLVR2-Async-Step146 published a model about 5 hours ago
open-athena/Snowball-67B-A2B-10T-Mixed-RLVR2-Async-Step146Organizations
models 65
penfever/qwen3coder-calendar-if-v49-lr2-step18
Text Generation • 31B • Updated • 493
penfever/qwen3coder-calendar-agent-v49-lr2-step12
Text Generation • 31B • Updated • 527
penfever/qwen3coder-calendar-agent-v49-lr4-step9
Text Generation • 31B • Updated • 523
penfever/qwen3coder-calendar-agent-v49-lr4-step6
Text Generation • 31B • Updated • 555
penfever/qwen3coder-calendar-if-v49-lr2-step3
Text Generation • 31B • Updated • 567
penfever/qwen3coder-calendar-if-v49-lr2-step6
Text Generation • 31B • Updated • 561
penfever/stageD-thinkbudget-80-8B
8B • Updated • 25
penfever/a3-rl-SankalpKJ_swesmith-oracle-filtered-40-8B
Reinforcement Learning • 8B • Updated • 36
penfever/grug-67b-a2b-sft-s1-wildchat-step257
Text Generation • 67B • Updated • 33
penfever/grug-67b-a2b-sft-s2-thinking-step630
Text Generation • 67B • Updated • 31 • 2
datasets 123
penfever/qwen3coder-iris-rl-data-sweep-artifacts
Updated • 130
penfever/jupiter-tasktrove-dapo-artifacts
Viewer • Updated • 13 • 154
penfever/passk-pass1-comparison
Preview • Updated • 28
penfever/snowball-67b-a2b-math-rl-artifacts
Updated • 132
penfever/moe-data-quality
Updated • 251
penfever/tasktrove-hparam-optimization
Updated • 442
penfever/harness-context-length-summ-ablation-artifacts
Updated • 22
penfever/snowball-5.7t-sft-eval-artifacts
Updated • 339
penfever/large-model-agentic-eval-parity-tb21-aa
Updated • 129
penfever/judgment-to-noise-data
Updated • 121