activity
20242026
most citedHierarchical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM

1 citations · 1 across the 5 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2026

NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction

NCP Team, Jiaqi Cao, Chiyu Chen +25

We introduce NCP-ArchPreview, a latent-space language model that pushes autoregressive pretraining beyond standard next-token prediction (NTP). Alongside NTP, the model learns thro…