Metraipolis › archive › dc_031b4b2cbe01

GALA: Generation-Aware Cross-Modal Alignment for Text-to-Time-Series Synthesis — arXiv:2608.13741

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13741
License (as archived)
CC0-1.0
Archived
2026-10-19T02:27:51.707Z
SHA-256 of the archived text
0317d9b95594212e26964ea0f6b72e9939ac48d8861c29c333dcfc77966c164f
Stable URL of this page
https://metraipolis.com/documento/dc_031b4b2cbe01

How to cite

GALA: Generation-Aware Cross-Modal Alignment for Text-to-Time-Series Synthesis — arXiv:2608.13741 — arXiv (en), https://arxiv.org/abs/2608.13741 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_031b4b2cbe01 (Metraipolis archive dc_031b4b2cbe01, sha256 0317d9b95594212e26964ea0f6b72e9939ac48d8861c29c333dcfc77966c164f)
BibTeX
@misc{dc031b4b2cbe01,
  title = {GALA: Generation-Aware Cross-Modal Alignment for Text-to-Time-Series Synthesis — arXiv:2608.13741},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13741},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_031b4b2cbe01; sha256 0317d9b95594212e26964ea0f6b72e9939ac48d8861c29c333dcfc77966c164f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13741. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Synthesizing time series from natural language is emerging as the most expressive form of controllable time series generation. However, existing text-conditioned generators either take caption embeddings frozen from off-the-shelf text encoders, or adapt the encoder end-to-end, letting the denoising loss shape the embeddings only as a by-product. In either case, the conditioning representation is never deliberately matched to the signal modality, leaving it ill-suited to guide generation. We address this by introducing GALA: Generation-Aware cross-modaL Alignment for text conditional time series generation. GALA is a two-stage approach that first contrastively couples a pretrained text encoder with a time-series foundation model into a shared embedding space with both encoders adapted to generation by an auxiliary generative loss, and then freezes the resulting caption embedding to drive a flow-matching generator. On TSFragment-600K, spanning four domains and three fragment lengths, GALA sets a new state of the art, ranking first in 30 of 36 metric columns and reaching an average rank of 1.08/1.08/1.42 at lengths 24/48/96 against 1.92/2.00/1.75 for the strongest baseline. We further find that generator-internal text encoders force a trade-off between fidelity and caption adherence, whereas conditioning on the aligned embedding breaks it: FID, CTTP, and JFTSD all improve at once. Ablating the auxiliary loss degrades FID, CTTP and JFTSD together, it indicates the generative term is a necessary component of the alignment rather than an add-on.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.13741 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T02:20:31.898Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).