Metraipolis › archive › dc_02d99eb198bc

Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication — arXiv:2608.16192

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16192
License (as archived)
CC0-1.0
Archived
2026-10-18T17:44:36.206Z
SHA-256 of the archived text
c0d4effa6a8c78ca3cee5ee1d746a0e91c993bf17a55e13302859088597b5cf3
Stable URL of this page
https://metraipolis.com/documento/dc_02d99eb198bc

How to cite

Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication — arXiv:2608.16192 — arXiv (en), https://arxiv.org/abs/2608.16192 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_02d99eb198bc (Metraipolis archive dc_02d99eb198bc, sha256 c0d4effa6a8c78ca3cee5ee1d746a0e91c993bf17a55e13302859088597b5cf3)
BibTeX
@misc{dc02d99eb198bc,
  title = {Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication — arXiv:2608.16192},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16192},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_02d99eb198bc; sha256 c0d4effa6a8c78ca3cee5ee1d746a0e91c993bf17a55e13302859088597b5cf3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16192. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative visual-token communication reduces transmission load by sending only selected discrete tokens and reconstructing missing content at the receiver. However, existing token-selection criteria based on local uncertainty, importance, or diversity do not directly determine whether changing the current selection improves the final reconstruction under the same packet budget. To address this problem, we propose Gated Counterfactual Refinement for Communication (GCR-C), a rollout-style correction layer over Local-MDL. GCR-C constructs a compact diversified candidate set, evaluates each candidate through matched full-budget Local-MDL continuation, and replaces the baseline action only when a positive baseline-relative reconstruction gain is obtained. Experiments on CIFAR-10, STL-10, a coded 5G-LDPC link, and a limited high-resolution Kodak transfer show that GCR-C consistently improves reconstruction quality at active low- and medium-rate operating points without increasing the realized packet rate, while remaining effective across changes in dataset, channel condition, resolution, token grid, and tokenizer. The results also reveal a clear quality--computation tradeoff due to the additional encoder-side counterfactual evaluation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.16192 — 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 2026-10-18T16:29:13.858Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).