arxiv:2601.23143
Sangwoo Park
Sangsang
AI & ML interests
I do LLM post-training research (KAIST AI)
Recent Activity
updated a model about 4 hours ago
Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen2.5-7B-Instruct_bw0p75_fw0p25_ema0p999_ep30 published a model about 4 hours ago
Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen2.5-7B-Instruct_bw0p75_fw0p25_ema0p999_ep30 updated a model about 4 hours ago
Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen2.5-7B-Instruct_bw0p25_fw0p75_ema0p999_ep30Organizations
None yet
models 218
Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen2.5-7B-Instruct_bw0p75_fw0p25_ema0p999_ep30
Text Generation • Updated
Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen2.5-7B-Instruct_bw0p25_fw0p75_ema0p999_ep30
Text Generation • Updated
Sangsang/feedback_asymmetric_kl_fixed_ema_Llama-3.1-8B-Instruct_bw0p75_fw0p25_ema0p999_ep30
Text Generation • Updated
Sangsang/feedback_asymmetric_kl_fixed_ema_Llama-3.1-8B-Instruct_bw0p25_fw0p75_ema0p999_ep30
Text Generation • Updated
Sangsang/ci-rl-Qwen2.5-7B-Instruct
Updated
Sangsang/feedback_asymmetric_kl_fixed_ema_Qwen3-14B_bw0p5_fw0p5_ema0p999_ep30
Text Generation • Updated • 13
Sangsang/grpo_Qwen3-0.6B_bs16_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30
Text Generation • Updated • 11
Sangsang/feedback_asymmetric_fixed_ema_Llama-3.1-8B-Instruct_bw0p5_fw0p5_ema0p999_ep30_v2
Text Generation • Updated • 21
Sangsang/ci-sft_Qwen3-4B
Text Generation • Updated • 18
Sangsang/ci-sft_Qwen3-4B-Instruct-2507_lr1e-6_ep30
Text Generation • Updated • 14
datasets 103
Sangsang/CI-Qwen2.5-32B-Instruct-Augmented-Responses
Viewer • Updated • 729 • 37
Sangsang/CI-Qwen3-32B-Instruct-Augmented-Responses
Viewer • Updated • 729 • 30
Sangsang/CI-Qwen3-32B-Augmented-Responses
Viewer • Updated • 729 • 56
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-32B_all
Viewer • Updated • 729 • 59
Sangsang/safepath_test_2
Viewer • Updated • 39.9k • 30
Sangsang/safepath_test
Viewer • Updated • 39.9k • 30
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-4B_all
Viewer • Updated • 729 • 87
Sangsang/ContextualIntegritySyntheticDataset_Qwen3-8B_all
Viewer • Updated • 729 • 37
Sangsang/CI-Olmo-3-32B-Think-Augmented-Responses
Viewer • Updated • 729 • 36
Sangsang/ContextualIntegritySyntheticDataset_Olmo-3-32B-Think_all
Viewer • Updated • 729 • 36