Login / Signup
InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory.
Chaojun Xiao
Pengle Zhang
Xu Han
Guangxuan Xiao
Yankai Lin
Zhengyan Zhang
Zhiyuan Liu
Song Han
Maosong Sun
Published in:
CoRR (2024)
Keyphrases
</>
long sequences
memory capacity
training set
training phase
memory space
supervised learning
test set
serious games
training algorithm
training samples
main memory
machine learning
object detection
memory usage
deeper understanding
data streams
computer software
data structure
behavioral data
case study