tangyunbo

tangyunbo

AI & ML interests

None yet

Recent Activity

upvoted a paper 6 days ago

ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents

updated a model 7 days ago

tangyunbo/Qwen3-4B-Instruct-2507-hint-sft-ckpt775

published a model 7 days ago

tangyunbo/Qwen3-4B-Instruct-2507-hint-sft-ckpt775

View all activity

Organizations

None yet

Papers 2

arxiv:2607.01071

arxiv:2605.29796

models 2

tangyunbo/Qwen3-4B-Instruct-2507-hint-sft-ckpt775

Text Generation • 4B • Updated 7 days ago • 21

tangyunbo/Qwen3-4B-RL-multiscope-fromscratch-iter297

Text Generation • 4B • Updated 20 days ago • 218

datasets 0

None public yet