Per-neuron sigmoid gates on Qwen3 FFN neurons to disentangle factual knowledge from reasoning.
HyunseokLee
hyunseoki
AI & ML interests
None yet
Recent Activity
updated a dataset 1 day ago
hyunseoki/memory-reasoning-split-eval-sets published a dataset 1 day ago
hyunseoki/memory-reasoning-split-eval-sets updated a dataset 1 day ago
hyunseoki/qwen3-0p6b-openthoughts-self-distill-10kOrganizations
VERL Math Transfer Checkpoints
Grouped HF exports for the verl math transfer experiments.
-
hyunseoki/verl-math-transfer-7bi-to-7bi-v2
Text Generation • 8B • Updated • 425 -
hyunseoki/verl-math-transfer-7bi-to-3bi-fix03
Text Generation • 8B • Updated • 744 -
hyunseoki/verl-math-transfer-7bi-to-3bi-fix07-pool7to1
Text Generation • 8B • Updated • 821 -
hyunseoki/verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1
Text Generation • 8B • Updated • 404
Qwen3 Lambda Gates — Knowledge/Reasoning Disentanglement
Per-neuron sigmoid gates on Qwen3 FFN neurons to disentangle factual knowledge from reasoning.
VERL Math Transfer Checkpoints
Grouped HF exports for the verl math transfer experiments.
-
hyunseoki/verl-math-transfer-7bi-to-7bi-v2
Text Generation • 8B • Updated • 425 -
hyunseoki/verl-math-transfer-7bi-to-3bi-fix03
Text Generation • 8B • Updated • 744 -
hyunseoki/verl-math-transfer-7bi-to-3bi-fix07-pool7to1
Text Generation • 8B • Updated • 821 -
hyunseoki/verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1
Text Generation • 8B • Updated • 404
models 36
hyunseoki/qwen3-1.7b-lambda-gates-chat
Updated
hyunseoki/qwen3-0.6b-lambda-gates-chat
Updated
hyunseoki/qwen3-0.6b-lambda-gates-nke
Updated
hyunseoki/qwen3-0.6b-lambda-gates-baseline
Updated
hyunseoki/verl-math-transfer-7bi-to-3bi-fix05-pool7to1
Text Generation • 8B • Updated • 309
hyunseoki/verl-math-transfer-llama31-8b-to-llama32-3b-pool7to1
Text Generation • 8B • Updated • 404
hyunseoki/verl-math-transfer-7bi-to-3bi-fix07-pool7to1
Text Generation • 8B • Updated • 821
hyunseoki/verl-math-transfer-7bi-to-3bi-fix03
Text Generation • 8B • Updated • 744
hyunseoki/verl-math-transfer-7bi-to-7bi-v2
Text Generation • 8B • Updated • 425
hyunseoki/ReMoDetect-RU
0.4B • Updated • 2
datasets 14
hyunseoki/memory-reasoning-split-eval-sets
Preview • Updated • 14
hyunseoki/qwen3-0p6b-openthoughts-self-distill-10k
Preview • Updated • 15
hyunseoki/qwen3-0p6b-openthoughts-self-distill-1k
Preview • Updated • 30
hyunseoki/openthoughts3-dedup-index
Updated • 20
hyunseoki/numina-math-10k-seed13
Viewer • Updated • 11k • 27
hyunseoki/prefixgen_MATH
Viewer • Updated • 60k • 2
hyunseoki/math_train_1k
Viewer • Updated • 1k • 6
hyunseoki/gsm8k_cot_zeroshot_second
Viewer • Updated • 3.33k • 8
hyunseoki/gsm8k_cot_zeroshot_third
Viewer • Updated • 1.63k • 2
hyunseoki/gsm8k_cot_zeroshot_multiturn
Viewer • Updated • 2.64k • 13