PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference
Paper
•
2502.13502
•
Published
•
1
•
2
Burc Gokden
fromthesky
AI & ML interests
Large Language Models, Transformers
Recent Activity
upvoted
a
paper
1 day ago
CoulGAT: An Experiment on Interpretability of Graph Attention Networks
upvoted
a
paper
1 day ago
Power Law Graph Transformer for Machine Translation and Representation
Learning
upvoted
a
paper
1 day ago
PLDR-LLM: Large Language Model from Power Law Decoder Representations
Organizations
fromthesky's activity
commented
a
paper
1 day ago