works on
benchmark 1layout analysis 1multimodal reasoning 1pdf document understanding 1table and chart comprehension 1

From the 1 of 18 linked papers with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2025

Latent Multi-Head Attention for Small Language Models

Sushant Mehta, Raj Dandekar, Rajat Dandekar +1

We present the first comprehensive study of latent multi-head attention (MLA) for small language models, revealing interesting efficiency-quality trade-offs. Training 30M-parameter…