Sungmin Jo's picture

Sungmin Jo

jsm0424

·

jsm0424

AI & ML interests

RLVR, LLM Reasoning

Recent Activity

upvoted a paper 2 days ago

Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging

upvoted a paper 16 days ago

Grounding World Simulation Models in a Real-World Metropolis

upvoted a collection about 2 months ago

View all activity

Organizations

None yet

jsm0424 's datasets 12

jsm0424/deepscaler-preview-ko-hard

Viewer • Updated Feb 23 • 18k • 7

jsm0424/deepscaler-preview-ko

Viewer • Updated Feb 22 • 40.3k • 7

jsm0424/math500-deepseek-r1-distill-qwen-1.5b-constrained2

Viewer • Updated May 25, 2025 • 499 • 10

jsm0424/math500-deepseek-r1-distill-qwen-14b-constrained

Viewer • Updated May 25, 2025 • 499 • 10

jsm0424/math500-deepseek-r1-distill-qwen-1.5b-constrained

Viewer • Updated May 24, 2025 • 499 • 8

jsm0424/math500-deepseek-r1

Viewer • Updated May 22, 2025 • 496 • 10

jsm0424/gsm8k-deepseek-r1-distill-qwen-1.5b

Viewer • Updated May 21, 2025 • 1.32k • 58

jsm0424/aime2024-deepseek-r1

Viewer • Updated May 20, 2025 • 30 • 17 • 1

jsm0424/aime2024-deepseek-r1-distill-qwen-1.5b

Viewer • Updated May 20, 2025 • 30 • 6 • 1

jsm0424/math500-deepseek-r1-distill-qwen-1.5b

Viewer • Updated May 19, 2025 • 500 • 31 • 1

jsm0424/math500-deepseek-r1-distill-qwen-14b

Viewer • Updated May 19, 2025 • 500 • 32 • 1

jsm0424/korean-cipher

Viewer • Updated Feb 13, 2025 • 196 • 10 • 4