Namgyu Ho
itsnamgyu
AI & ML interests
LLM, Efficient NLP, Few-shot
Recent Activity
upvoted a paper 1 day ago
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation upvoted a paper 7 days ago
Language Models Can Control Their Own Attention submitted a paper 7 days ago
Language Models Can Control Their Own AttentionOrganizations
models 0
None public yet
datasets 8
itsnamgyu/dac_sft_v3_dac
Viewer • Updated • 14.8k • 10
itsnamgyu/dac_sft_v3_vanilla
Viewer • Updated • 14.8k • 9
itsnamgyu/dac_sft_v2_vanilla
Viewer • Updated • 24k • 20
itsnamgyu/dac_sft_v2_dac_v2
Viewer • Updated • 16.9k • 4
itsnamgyu/dac_sft_v2_dac
Viewer • Updated • 18.2k • 15
itsnamgyu/longbench_synthetic_v2
Viewer • Updated • 12k • 43
itsnamgyu/longbench_synthetic_v1
Viewer • Updated • 7.6k • 31
itsnamgyu/longbench_with_rubrics
Viewer • Updated • 600 • 95