semianalysisai/Qwen3.6-35B-A3B-caesar-cipher-GRPO-20260924 Reinforcement Learning • 35B • Updated Sep 25 • 28
semianalysisai/Qwen3.6-35B-A3B-simple-geometry-GRPO-20260925 Reinforcement Learning • 35B • Updated Sep 25 • 31
budget-internalization-iclr2027/gemma4-e2b-1k-grpo-reasoninggym-petbadger-s300 Any-to-Any • 5B • Updated Sep 25 • 12
budget-internalization-iclr2027/gemma4-e2b-2k-grpo-reasoninggym-smartcamel-s300 Any-to-Any • 5B • Updated Sep 25 • 14
budget-internalization-iclr2027/gemma4-e2b-4k-grpo-reasoninggym-fullcoyote-s300 Any-to-Any • 5B • Updated Sep 25 • 8
budget-internalization-iclr2027/nemotron3-nano-4b-2k-grpo-reasoninggym-coolbengal-s300 Text Generation • 4B • Updated Sep 25 • 93
budget-internalization-iclr2027/qwen3.5-4b-4k-grpo-reasoninggym-easyturkey-s300 Image-Text-to-Text • 5B • Updated Sep 25 • 17
budget-internalization-iclr2027/qwen3.5-4b-8k-grpo-reasoninggym-rapiddassie-s300 Image-Text-to-Text • 5B • Updated Sep 25 • 13
budget-internalization-iclr2027/qwen3.5-4b-16k-grpo-reasoninggym-restedmarlin-s300 Image-Text-to-Text • 5B • Updated Sep 25 • 25