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
在最新榜 #343 本站收录于 2026-10-26
一句话要点
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。
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.
阅读 arXiv 原文 PDF Hugging Face 讨论 项目页
主题与学科
同主题:大语言模型
- Jeva: System One Models from First Principles ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions ▲273
- OmniEdu: Open Foundation Models for Learning and Teaching ▲240
- PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking ▲163
- MemT-1.0: Towards Memory-Native Evolution ▲143
同主题:高效训练与推理
- MJev-Spatial: System One Spatial Intelligence via Native Attention Matching 2026-10-15 · ▲556
- The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation 2026-09-29 · ▲511
- VideoJev: System One Model for Video Understanding and Interaction 2026-10-13 · ▲375
- LEV: Thinking Fast and Deep with Looped Decision Models 2026-10-14 · ▲337
- Scaling Properties of Same-Family On-Policy Distillation 2026-09-26 · ▲327
同机构:ByteDance Seed
数据说明
元数据来自 arXiv API(已核实);点赞来自 Hugging Face 每日论文;引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写,不转载摘要原文,请阅读原文。