# Deep Variable-Length Feedback Codes

arXiv: https://arxiv.org/abs/2602.07881 · HTML: https://mlsanity.com/paper/2602.07881/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 8 Feb 2026.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Introduction to Deep Learning for the Physical Layer](https://mlsanity.com/paper/1702.00832/) (2017)
- [Deepcode: Feedback Codes via Deep Learning](https://mlsanity.com/paper/1807.00801/) (2018)
- [Deep Extended Feedback Codes](https://mlsanity.com/paper/2105.01365/) (2021)
- [All you need is feedback: Communication with block attention feedback codes](https://mlsanity.com/paper/2206.09457/) (2022)
- [AttentionCode: Ultra-Reliable Feedback Codes for Short-Packet Communications](https://mlsanity.com/paper/2205.14955/) (2022)
- [Feedback is Good, Active Feedback is Better: Block Attention Active Feedback Codes](https://mlsanity.com/paper/2211.01730/) (2022)
- [LightCode: Light Analytical and Neural Codes for Channels with Feedback](https://mlsanity.com/paper/2403.10751/) (2024)
- [DEEP-IoT: Downlink-Enhanced Efficient-Power Internet of Things](https://mlsanity.com/paper/2403.00321/) (2024)
- [Deep Broadcast Feedback Codes](https://mlsanity.com/paper/2512.00608/) (2025)

## Abstract (arXiv)

Deep learning has enabled significant advances in feedback-based channel coding, yet existing learned schemes remain fundamentally limited: they employ fixed block lengths, suffer degraded performance at high rates, and cannot fully exploit the adaptive potential of feedback. This paper introduces Deep Variable-Length Feedback (DeepVLF) coding, a flexible coding framework that dynamically adjusts transmission length via learned feedback. We propose two complementary architectures: DeepVLF-R, where termination is receiver-driven, and DeepVLF-T, where the transmitter controls termination. Both architectures leverage bit-group partitioning and transformer-based encoder-decoder networks to enable fine-grained rate adaptation in response to feedback. Evaluations over AWGN and 5G-NR fading channels demonstrate that DeepVLF substantially outperforms state-of-the-art learned feedback codes. It achieves the same block error rate with 20%-55% fewer channel uses and lowers error floors by orders of magnitude, particularly in high-rate regimes. Encoding dynamics analysis further reveals that the models autonomously learn a two-phase strategy analogous to classical Schalkwijk-Kailath coding: an initial information-carrying phase followed by a noise-cancellation refinement phase. This emergent behavior underscores the interpretability and information-theoretic alignment of the learned codes.