Sangdoo Yun

oodgnas

·

AI & ML interests

None yet

Recent Activity

authored a paper about 10 hours ago

On-Policy Delta Distillation

upvoted a paper 1 day ago

On-Policy Delta Distillation

upvoted a paper about 1 month ago

Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time

View all activity

Organizations

Papers 49

arxiv:2607.15161

arxiv:2603.15583

arxiv:2507.06543

arxiv:2506.15674

models 33

oodgnas/Qwen3-1.7B-SFT-100k-MTP-s2-w005

2B • Updated Mar 30 • 5

oodgnas/Qwen3-1.7B-SFT-100k

2B • Updated Mar 30 • 113

oodgnas/Qwen3-1.7B-Base

2B • Updated Mar 30 • 1

oodgnas/Qwen2.5-1.5B-Instruct-SFT-30k-NTP-MTP-w001

2B • Updated Mar 28 • 2

oodgnas/Qwen2.5-1.5B-Instruct-SFT-30k-MTP-s3-w001

2B • Updated Mar 27 • 5

oodgnas/Qwen2.5-1.5B-Instruct-SFT-30k-NTP-s1-w001

2B • Updated Mar 27 • 3

oodgnas/Qwen2.5-1.5B-Instruct-SFT-30k-MTP-w001

2B • Updated Mar 27 • 2

oodgnas/Qwen2.5-1.5B-Instruct-SFT-30k-MTP-w005

2B • Updated Mar 27 • 5

oodgnas/Qwen2.5-1.5B-Instruct-SFT-30k

2B • Updated Mar 27 • 2

oodgnas/Qwen3-1.7B-OLMo3-midtrain-mtp-pos21

2B • Updated Mar 26

datasets 0

None public yet