-
PLDR-LLMs Reason At Self-Organized Criticality
Paper • 2603.23539 • Published • 3 -
Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference
Paper • 2608.10288 • Published • 7 -
fromthesky/PLDR-LLM-v51-SOC-110M-1
Text Generation • 0.1B • Updated • 267 • 1 -
fromthesky/PLDR-LLM-v51-SOC-110M-2
Text Generation • 0.1B • Updated • 17
AI & ML interests
Large Language Models, Transformers, Natural Language Processing
Recent Activity
View all activity
Papers
Training and Inference Dynamics of PLDR-LLMs: Row-Map Collapse, Renormalization, and Predictive Reduction
Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference
Pretrained PLDR-LLMs from paper titled "PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference"
-
PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference
Paper • 2502.13502 • Published • 3 -
Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference
Paper • 2608.10288 • Published • 7 -
fromthesky/PLDR-LLM-v51-104M
Text Generation • 0.1B • Updated • 24 -
fromthesky/PLDR-LLM-v51-110M-1
Text Generation • 0.1B • Updated • 22
-
PLDR-LLMs Reason At Self-Organized Criticality
Paper • 2603.23539 • Published • 3 -
Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference
Paper • 2608.10288 • Published • 7 -
fromthesky/PLDR-LLM-v51-SOC-110M-1
Text Generation • 0.1B • Updated • 267 • 1 -
fromthesky/PLDR-LLM-v51-SOC-110M-2
Text Generation • 0.1B • Updated • 17
Pretrained PLDR-LLMs from paper titled "PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference"
-
PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference
Paper • 2502.13502 • Published • 3 -
Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference
Paper • 2608.10288 • Published • 7 -
fromthesky/PLDR-LLM-v51-104M
Text Generation • 0.1B • Updated • 24 -
fromthesky/PLDR-LLM-v51-110M-1
Text Generation • 0.1B • Updated • 22
models 0
None public yet
datasets 0
None public yet