arxiv:2505.04842
Kusha Sareen
kushasareen
·
AI & ML interests
None yet
Recent Activity
updated a model 4 days ago
kushasareen/codeio-rl-only-think-8b-step950 published a model 4 days ago
kushasareen/codeio-rl-only-think-8b-step950 updated a model 4 days ago
kushasareen/codeio-rl-gepa-k8-optb-nonambig-think-8b-step950Organizations
models 28
kushasareen/codeio-rl-only-think-8b-step950
8B • Updated • 32
kushasareen/codeio-rl-gepa-k8-optb-nonambig-think-8b-step950
8B • Updated • 29
kushasareen/codeio-rl-only-think-8b-step1250
8B • Updated • 30
kushasareen/qwen35-9b-ft-m300
Reinforcement Learning • 9B • Updated • 40
kushasareen/qwen35-9b-ft-m200
Reinforcement Learning • 9B • Updated • 27
kushasareen/qwen35-9b-ft-m100
Reinforcement Learning • 9B • Updated • 30
kushasareen/qwen35-9b-ft-c400
Reinforcement Learning • 9B • Updated • 52
kushasareen/qwen35-9b-ft-c300
Reinforcement Learning • 9B • Updated • 51
kushasareen/qwen35-9b-ft-c200
Reinforcement Learning • 9B • Updated • 48
kushasareen/qwen35-9b-ft-c100
Reinforcement Learning • 9B • Updated • 53
datasets 18
kushasareen/contest-math-hard-v2
Viewer • Updated • 340 • 76
kushasareen/ttfs-hard-5
Viewer • Updated • 5 • 31
kushasareen/held-out-math-eval
Viewer • Updated • 671 • 98 • 1
kushasareen/openmath-hard-64
Viewer • Updated • 64 • 81
kushasareen/planted-3color-n48-four-groups
Viewer • Updated • 2.2k • 63
kushasareen/contest-math-intermediate
Viewer • Updated • 64 • 78
kushasareen/contest-math-hardest
Viewer • Updated • 27 • 88
kushasareen/contest-math-hard
Viewer • Updated • 341 • 93
kushasareen/recursive-rl-hard-mix
Viewer • Updated • 17.6k • 62
kushasareen/dapo-filtered
Viewer • Updated • 128 • 42