Metraipolis › archive › dc_eb5b1920e5dc

THEIA: A Multimodal Dataset and Benchmark for Vision-Language Analysis of Layout — arXiv:2609.35035

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35035
License (as archived)
CC0-1.0
Archived
2026-10-07T22:38:44.995Z
SHA-256 of the archived text
6604a9eace56bbaa04b9a3da64ded8d41cb1b3cdedffb9e1913b1e141619a02c
Stable URL of this page
https://metraipolis.com/documento/dc_eb5b1920e5dc

How to cite

THEIA: A Multimodal Dataset and Benchmark for Vision-Language Analysis of Layout — arXiv:2609.35035 — arXiv (en), https://arxiv.org/abs/2609.35035 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb5b1920e5dc (Metraipolis archive dc_eb5b1920e5dc, sha256 6604a9eace56bbaa04b9a3da64ded8d41cb1b3cdedffb9e1913b1e141619a02c)
BibTeX
@misc{dceb5b1920e5dc,
  title = {THEIA: A Multimodal Dataset and Benchmark for Vision-Language Analysis of Layout — arXiv:2609.35035},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35035},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb5b1920e5dc; sha256 6604a9eace56bbaa04b9a3da64ded8d41cb1b3cdedffb9e1913b1e141619a02c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35035. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The integration of artificial intelligence into computer-aided design frameworks has sparked a shift in the design of analog integrated circuits (ICs), transitioning the field from using manual and algorithmic-based solutions to adopting automated and intelligent paradigms. In this scenario, the GDSII file represents the industry-standard database containing the ultimate and most accurate source of information of the analog circuit, encapsulating the complex physical geometries and parasitic realities that define tape out performance. This paper proposes THEIA, a novel dataset containing thousands of layout images paired with question-answer conversations, along with a benchmark that employs a fine-tuned vision-language model (VLM) to analyze GDSII files of analog circuits, enabling designers to interact with and query physical layouts as intuitive, meaningful entities. Experimental results using thousands of analog designs across five realistic tasks demonstrate that the proposed fine-tuned VLM outperforms state-of-the-art general-purpose VLMs by a significant margin (up to 73%), highlighting a fundamental gap between general-purpose multimodal reasoning and domain-specific layout understanding.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.35035 — 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 2026-10-07T22:14:28.331Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).