arxiv:2510.00492
Sangwoo Park
Sangsang
AI & ML interests
I do LLM Safety & Reasoning research (KAIST AI)
Recent Activity
updated
a dataset
5 days ago
Sangsang/thinksafe_r1-distill_1.5B_debug
published
a dataset
5 days ago
Sangsang/thinksafe_r1-distill_1.5B_debug
upvoted
a
paper
5 days ago
Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for
MLLMs
Organizations
None yet
models
15
Sangsang/0923_deepseek-r1-controlTokens-20250811-GRPO-LORA-INDIVIDUAL
Updated
Sangsang/Qwen2.5-7B-Instruct-malware
Updated
Sangsang/qwen3-8B-a0-thinksafe-kl0
Text Generation
•
Updated
•
9
Sangsang/Qwen2.5-7B-Instruct-cat-preference_r16_low_temp
Updated
Sangsang/Qwen2.5-7B-Instruct-general_r16
Updated
Sangsang/0903_deepseek-r1-controlTokens-20250811-GRPO-LORA-INDIVIDUAL
Updated
Sangsang/0903_deepseek-r1-controlTokens-20250811-GRPO-LORA-INDIVIDUAL_checkpoint-500
Updated
Sangsang/0830_deepseek-r1-controlTokens-20250811-GRPO-LORA-INDIVIDUAL
Updated
Sangsang/0827_deepseek-r1-controlTokens-20250811-GRPO-LORA-INDIVIDUAL
Updated
•
4
•
1
Sangsang/Qwen2.5-7B-Instruct-penguin-preference_r16
Updated
datasets
8
Sangsang/thinksafe_r1-distill_1.5B_debug
Viewer
•
Updated
•
965
•
9
Sangsang/MobileLLM-R1-140M-base_thinksafe
Viewer
•
Updated
•
869
•
20
Sangsang/MobileLLM-R1-950M_thinksafe
Viewer
•
Updated
•
35.1k
•
19
Sangsang/MobileLLM-R1-360M_thinksafe
Viewer
•
Updated
•
29.7k
•
16
Sangsang/MobileLLM-R1-140M_thinksafe
Viewer
•
Updated
•
22.6k
•
17
Sangsang/OpenThoughts-80K-8B
Updated
•
11
Sangsang/OpenThoughts-80K-4B
Updated
•
10
Sangsang/ThinkSafe
Viewer
•
Updated
•
39k
•
9