Minju Gwak
talzoomanzoo
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating Transfer submitted a paper 1 day ago
Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating TransferOrganizations
models 325
talzoomanzoo/nemotron-nano-4b-uid
Text Generation • Updated • 27
talzoomanzoo/nemotron-nano-4b-ttrl-sc
Text Generation • Updated • 33
talzoomanzoo/nemotron-nano-4b-ttrl-random
Text Generation • Updated • 33
talzoomanzoo/nemotron-nano-4b-ttrl
Text Generation • Updated • 28
talzoomanzoo/openreasoning-nemotron-1.5b-ttrl-random
Text Generation • Updated • 26
talzoomanzoo/openreasoning-nemotron-1.5b-ttrl-sc
Text Generation • Updated • 26
talzoomanzoo/openreasoning-nemotron-1.5b-uid
Text Generation • Updated • 27
talzoomanzoo/openreasoning-nemotron-1.5b-ttrl
Text Generation • Updated • 25
talzoomanzoo/phi-4-mini-uid
Text Generation • Updated • 13
talzoomanzoo/phi-4-mini-ttrl-sc
Text Generation • Updated • 14
datasets 151
talzoomanzoo/aime_pair_union_data
Viewer • Updated • 2.11k • 56
talzoomanzoo/sft_uid_mix
Viewer • Updated • 3.32k • 70
talzoomanzoo/sft_uid_conj
Viewer • Updated • 3.32k • 70
talzoomanzoo/sft_sc
Viewer • Updated • 3.32k • 95
talzoomanzoo/sft_uniform
Viewer • Updated • 3.32k • 59
talzoomanzoo/dpo_uid_mix
Viewer • Updated • 466 • 64
talzoomanzoo/dpo_uid_conj
Viewer • Updated • 466 • 60
talzoomanzoo/dpo_sc
Viewer • Updated • 466 • 59
talzoomanzoo/dpo_random
Viewer • Updated • 466 • 74
talzoomanzoo/qwen3-1.7b-aime-dpo-pairs
Preview • Updated • 77