Skip to content
English

Switch theme

arXiv 2610.31305 · cs.CL · 2026-10-22

Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation

Hongcan Guo, Yian Zhao, Feng Wang, Shen Nie, Guoqiang Wei, Yan Zeng, Hengshuang Zhao

ByteDance Seed

In latest · #343 Added on 2026-10-26

One-line takeaway

Cola2 is a hierarchical language-modeling framework that compresses dynamically segmented semantic spans into continuous latents and realizes text with a block-causal masked diffusion decoder, with the encoder and decoder co-adapting.

Cola2 是分层语言生成框架:把文本动态切成语义片段压缩成连续潜变量,再用块因果掩码扩散解码器生成离散文本,并让编码器与解码器协同适配。

25HF upvotes
–GitHub stars
0Citations (Semantic Scholar)
38.2Buzz score

Read on arXiv PDF Hugging Face discussion Project page

About this data

Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.

The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.

Data updated: Latest AI papers(UTC+8)