# Generative Semantic HARQ: Latent-Space Text Retransmission and Combining

arXiv: https://arxiv.org/abs/2603.15068 · HTML: https://mlsanity.com/paper/2603.15068/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 12 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 9 of 9)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Deep Learning Enabled Semantic Communication Systems](https://mlsanity.com/paper/2006.10685/) (2020)
- [Wireless Semantic Communications for Video Conferencing](https://mlsanity.com/paper/2204.07790/) (2022)
- [Deep Source-Channel Coding for Sentence Semantic Transmission with HARQ](https://mlsanity.com/paper/2106.03009/) (2021)
- [SCAN: Semantic Communication with Adaptive Channel Feedback](https://mlsanity.com/paper/2306.15534/) (2023)
- [Adaptive Bit Rate Control in Semantic Communication with Incremental Knowledge-based HARQ](https://mlsanity.com/paper/2203.06634/) (2022)
- [SemHARQ: Semantic-Aware Hybrid Automatic Repeat Request for Multi-Task Semantic Communications](https://mlsanity.com/paper/2404.08490/) (2024)
- [Spiking Semantic Communication for Feature Transmission with HARQ](https://mlsanity.com/paper/2310.08804/) (2023)
- [Semantic Communication for Cooperative Perception using HARQ](https://mlsanity.com/paper/2409.09042/) (2024)

## Built on by (most cited first, 1 of 1)

- [From Semantic to Token Communication: The Next Paradigm for Large-Model-Driven 6G Intelligent Connectivity](https://mlsanity.com/paper/2609.10714/) (2026)

## Abstract (arXiv)

Semantic communication conveys meaning rather than raw bits, but reliability at the semantic level remains an open challenge. We propose a semantic-level hybrid automatic repeat request (HARQ) framework for text communication, in which a Transformer-variational autoencoder (VAE) codec operates as a lightweight overlay on the conventional protocol stack. The stochastic encoder inherently generates diverse latent representations across retransmissions-providing incremental knowledge (IK) from a single model without dedicated protocol design. On the receiver side, a soft quality estimator triggers retransmissions and a quality-aware combiner merges the received latent vectors within a consistent latent space. We systematically benchmark six semantic quality metrics and four soft combining strategies under hybrid semantic distortion that mixes systematic bias with additive noise. The results suggest combining Weighted-Average or MRC-Inspired combining with self-consistency-based HARQ triggering for the best performance.