works on
annotation grounding 1cross-attention 1large language models 1parametric cad generation 1raster drawing digitization 1

From the 1 of 4 linked papers with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

PARTREP: Learning What to Repeat for Decoder-only LLMs

Andikawati P Widjaja, Yongjun Kim, Hyounghun Kim +1

While decoder-only LLMs excel at a vast array of natural language tasks, it suffers from an asymmetric information flow induced by causal attention: later tokens are richer in cont…