发表机构
School of Computer and Information Engineering, Tianjin Normal University; School of Information Science and Engineering, Linyi University（天津师范大学计算机与信息工程学院; 临沂大学信息科学与工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对视觉令牌通信现有选择准则无法提升重建质量的问题，提出GCR-C方法，在不增加数据包率的情况下提升低中速率下的重建质量，且对多类变化场景有效。
AI 中文摘要
生成式视觉令牌通信通过仅发送选定的离散令牌并在接收端重建缺失内容来降低传输负载。然而，现有基于局部不确定性、重要性或多样性的令牌选择准则，无法直接确定在相同数据包预算下，更改当前选择是否能提升最终重建效果。为解决该问题，我们提出通信门控反事实优化（Gated Counterfactual Refinement for Communication, GCR-C），这是一种基于局部最小描述长度（Local-MDL）的回滚式修正层。GCR-C构建紧凑多样的候选集，通过匹配的全预算Local-MDL延续评估每个候选，且仅当获得正的基线相对重建增益时才替换基线动作。在CIFAR-10、STL-10、编码5G-LDPC链路及有限高分辨率Kodak传输上的实验表明，GCR-C在活跃的低、中速率工作点上持续提升重建质量，且不增加实际数据包率，同时在数据集、信道条件、分辨率、令牌网格及分词器变化时仍保持有效。结果还显示，由于编码器侧额外的反事实评估，存在明显的质量-计算量权衡。
英文摘要
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.
