Newest papers

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 · 2026 · arXiv

DOI: 10.48550/arXiv.2610.31305 · open-access PDF

Spanish

La generación de lenguaje jerárquica separa el modelado semántico continuo de la realización de texto discreto, pero su eficacia depende de lo que comprime el espacio latente y de cómo lo utilice el generador discreto. Proponemos Cola2, un marco que estudia conjuntamente la compresión semántica continua, el equilibrio entre reconstrucción y generación, y la co-adaptación discreta continua. Cola2 segmenta dinámicamente el texto en intervalos semánticos, controla la tasa de compresión a través de retroalimentación negativa sin pérdidas auxiliares, y combina la reconstrucción y la supervisión de la generación para aprender el texto compacto, predictivo.

Machine translation (Meta M2M100); the English original follows.

Abstract

Hierarchical language generation separates continuous semantic modeling from discrete text realization, but its effectiveness depends on what the latent space compresses and how the discrete generator uses it. We propose Cola2, a framework that jointly studies continuous semantic compression, the balance between reconstruction and generation, and continuous-discrete co-adaptation. Cola2 dynamically segments text into semantic spans, controls the compression rate through auxiliary-loss-free negative feedback, and combines reconstruction and generation supervision to learn compact, predictive la

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31305, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange