{"ID":6267070,"CreatedAt":"2026-07-10T01:11:38.759438437Z","UpdatedAt":"2026-07-13T01:02:08.706470581Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.08186","arxiv_id":"2607.08186","title":"Hidden Decoding at Scale: Latent Computation Scaling for Large Language Models","abstract":"Scaling Large Language Models (LLMs) has been driven mainly by enlarging the Transformer backbone, but for an already-strong model this requires another round of costly pretraining. We study whether an existing backbone can keep improving by allocating more computation to each token while leaving the Transformer backbone fixed. Depth-recurrent (looped) Transformers pursue this goal but are hard to scale, because looped computation does not fit naturally with the pipeline parallelism used to train the largest models. We add computation along the sequence-length dimension, where the extra computation is simply a longer input and stays compatible with standard large-model training. We propose Hidden Decoding, a sequence-length scaling method applied during continued pretraining (CPT). It expands each token into n streams with independent embedding tables and keeps the intermediate streams' key-value cache as context, so each token performs more internal computation without adding or widening Transformer layers. To keep this affordable at scale, we introduce Stream-Factorized Attention, in which most layers attend only within each stream and only a few layers mix across streams, reducing the attention cost from quadratic to roughly linear in n. Experiments support two scaling results. At frontier scale, we train WeLM-HD4-80B and WeLM-HD4-617B at n=4 and improve their matched non-HD baselines, making Hidden Decoding the first demonstrated sequence-length scaling method at the 100B+ MoE scale. Across expansion factors, the gains grow as n increases, showing that sequence-length expansion is a practical fixed-backbone scaling path for frontier-scale LLMs.","short_abstract":"Scaling Large Language Models (LLMs) has been driven mainly by enlarging the Transformer backbone, but for an already-strong model this requires another round of costly pretraining. We study whether an existing backbone can keep improving by allocating more computation to each token while leaving the Transformer backbo...","url_abs":"https://arxiv.org/abs/2607.08186","url_pdf":"https://arxiv.org/pdf/2607.08186v1","authors":"[\"Aiwei Liu\",\"Cheng Shi\",\"Chuhan Wu\",\"Ci Lei\",\"Di Lu\",\"Donald He\",\"Fan Zhang\",\"Fanhao Kong\",\"Feifei Zhang\",\"Guan Wang\",\"Haicheng Wang\",\"Haoyu Liu\",\"Houjin Yu\",\"Jiachen Ding\",\"Jiayi Feng\",\"Jie Zhou\",\"Jijun Chi\",\"Jindi Shi\",\"Jing Lei\",\"Junjie Zhang\",\"Laiyi Li\",\"Le Tian\",\"Linhao Zhang\",\"Miao Fan\",\"Sijun Zhang\",\"Wei Jia\",\"Weiwei Shi\",\"Wenhan Li\",\"Wentao Zhao\",\"Wenteng Liang\",\"Xiao Zhou\",\"Xiaojin Zhou\",\"Xihuai Wang\",\"Xinyu Gao\",\"Xuanliang Wang\",\"Xuyang Ao\",\"Yang Yu\",\"Yangxiu You\",\"Yinuo Zhao\",\"Yufei Kuang\",\"Yufei Wang\",\"Yuan Liu\",\"Yuan Liu\",\"Yuwen Chen\",\"Zhencong Tian\",\"Zhongyin Zhao\",\"Zilin Yu\",\"Zitao Wang\"]","published":"2026-07-09T07:37:59Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Transformer\",\"Large Language Model\",\"Language Model\"]","has_code":false}