arxiv:2608.30135
Byeongho Heo
bhheo
AI & ML interests
None yet
Recent Activity
upvoted a paper 2 days ago
On-Policy Distillation with Negative-Policy Rollouts upvoted a paper 30 days ago
Revisiting Complete Reasoning Traces for Post-Training upvoted a paper about 1 month ago
Eliciting Weak-to-Strong Generalization with On-Policy Reverse DistillationOrganizations
arxiv:2608.05802
arxiv:2607.15161
arxiv:2602.06393
arxiv:2510.16333
arxiv:2510.15510
arxiv:2507.06543
arxiv:2502.08167
arxiv:2411.19067
arxiv:2407.12863
arxiv:2404.01954
arxiv:2403.19588
arxiv:2403.13298
arxiv:2401.00254
arxiv:2312.10105
arxiv:2311.18540
arxiv:2310.13593
arxiv:2306.11339
arxiv:2305.00729
arxiv:2303.11114
arxiv:2212.04114
arxiv:2210.11407
arxiv:2210.08457
arxiv:2204.07962
arxiv:2202.02777
arxiv:2110.03921
arxiv:2103.16302
arxiv:2101.05022
arxiv:2012.03457
arxiv:2007.00992
arxiv:2006.08217
