LongNet: Scaling Transformers to 1,000,000,000 Tokens
Paper
•
2307.02486
•
Published
•
81
Jiayu Ding
JiayuDing
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
12 days ago
Information-Preserving Reformulation of Reasoning Traces for
Antidistillation
commented on
a paper
12 days ago
Information-Preserving Reformulation of Reasoning Traces for
Antidistillation
authored
a paper
12 days ago
LongNet: Scaling Transformers to 1,000,000,000 Tokens
Organizations
None yet
authored
2
papers
12 days ago