Metraipolis › archive › dc_609ed6812e97

Can LLMs Design Video Coding Tools? A Case Study on Planar Mode — arXiv:2609.01535

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01535
License (as archived)
CC0-1.0
Archived
2026-10-17T06:34:25.718Z
SHA-256 of the archived text
fb68af048c786f948983a2c4a2f6ecefde1901983881e5494bca5827778201d6
Stable URL of this page
https://metraipolis.com/documento/dc_609ed6812e97

How to cite

Can LLMs Design Video Coding Tools? A Case Study on Planar Mode — arXiv:2609.01535 — arXiv (en), https://arxiv.org/abs/2609.01535 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_609ed6812e97 (Metraipolis archive dc_609ed6812e97, sha256 fb68af048c786f948983a2c4a2f6ecefde1901983881e5494bca5827778201d6)
BibTeX
@misc{dc609ed6812e97,
  title = {Can LLMs Design Video Coding Tools? A Case Study on Planar Mode — arXiv:2609.01535},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01535},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_609ed6812e97; sha256 fb68af048c786f948983a2c4a2f6ecefde1901983881e5494bca5827778201d6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01535. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper explores whether large language models (LLMs) can design video coding tools, a highly challenging task due to the intricate algorithmic coupling of tool modifications. In particular, we present an empirical case study on the Planar mode, a long-standing intra prediction tool in video coding standards. Our experiments operate within a generation-and-evaluation loop, with the LLM generating new Planar predictors, encoder trials evaluating their coding performance, and the LLM re-generating refined implementations based on the evaluation feedback. We first examine directly replacing the default Planar mode in the Fraunhofer Versatile Video Encoder (VVenC) under its faster preset. Experimental results demonstrate that the LLM-generated mode can outperform the conventional Planar mode on this lightweight toolset, achieving 0.18% bitrate savings with 0.4% complexity overhead on the standard benchmark. We further extend our evaluation to the Enhanced Compression Model (ECM). Leveraging newly introduced directional Planar modes, we investigate two integration strategies: directly replacing them, and introducing the LLM-generated predictor as an additional prediction mode with new syntax elements. The empirical results suggest that both strategies can yield coding gains under a constrained low-resolution setting. Overall, this study offers preliminary evidence and practical insights, highlighting both the potential and open challenges of LLM-based coding tool design.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Multimedia (cs.MM) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.01535 — 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 2026-10-17T06:15:12.909Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).