arxiv:2505.16297
Seongryong Jung
SeongryongJung
AI & ML interests
Post-training, Knowledge Distillation, Agentic AI
Recent Activity
upvoted a paper 3 days ago
A Survey of On-Policy Distillation for Large Language Models commentedon a paper 6 days ago
Reinforcement-aware Knowledge Distillation for LLM Reasoning updated a model 12 days ago
SeongryongJung/qwen2.5-1.5b-base-mmlu-sft-1epochOrganizations
None yet
models 6
SeongryongJung/qwen2.5-1.5b-base-mmlu-sft-1epoch
2B • Updated • 15
SeongryongJung/qwen2.5-0.5b-ifeval-mixed-kd-alpha05
Text Generation • 0.6B • Updated • 216
SeongryongJung/qwen2.5-0.5b-ifeval-pure-kd
Text Generation • 0.6B • Updated • 224
SeongryongJung/qwen2.5-1.5b-ifeval-halfepoch-sft
Text Generation • 2B • Updated • 223
SeongryongJung/qwen2.5-0.5b-ifeval-halfepoch-sft
Text Generation • 0.6B • Updated • 224
SeongryongJung/Qwen3-0.6B-DPO-adapter
Text Generation • Updated • 2