# Task-Oriented Candidate-Latent Feedback for Coarse-to-Fine Sensing in Distributed OFDM-ISAC Networks

arXiv: https://arxiv.org/abs/2608.03319 · HTML: https://mlsanity.com/paper/2608.03319/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [An Introduction to Deep Learning for the Physical Layer](https://mlsanity.com/paper/1702.00832/) (2017)
- [Model-Based Deep Learning](https://mlsanity.com/paper/2012.08405/) (2020)
- [Semantic Communications for Future Internet: Fundamentals, Applications, and Challenges](https://mlsanity.com/paper/2207.00427/) (2022)
- [Integrated Sensing and Communications: Towards Dual-functional Wireless Networks for 6G and Beyond](https://mlsanity.com/paper/2108.07165/) (2021)
- [Task-Oriented Multi-User Semantic Communications](https://mlsanity.com/paper/2112.10255/) (2021)
- [Less Data, More Knowledge: Building Next Generation Semantic Communication Networks](https://mlsanity.com/paper/2211.14343/) (2022)
- [Wireless Image Retrieval at the Edge](https://mlsanity.com/paper/2007.10915/) (2020)
- [Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems](https://mlsanity.com/paper/2206.14383/) (2022)
- [Rethinking Modern Communication from Semantic Coding to Semantic Communication](https://mlsanity.com/paper/2110.08496/) (2021)
- [Distributed Deep Convolutional Compression for Massive MIMO CSI Feedback](https://mlsanity.com/paper/2003.04684/) (2020)
- [A Survey on Semantic Communication Networks: Architecture, Security, and Privacy](https://mlsanity.com/paper/2405.01221/) (2024)
- [Joint Radar and Communication Design: Applications, State-of-the-art, and the Road Ahead](https://mlsanity.com/paper/1906.00789/) (2019)
- [Integrated Sensing and Communications: Recent Advances and Ten Open Challenges](https://mlsanity.com/paper/2305.00179/) (2023)
- [Radar-assisted Predictive Beamforming for Vehicular Links: Communication Served by Sensing](https://mlsanity.com/paper/2001.09306/) (2020)
- [Bayesian Predictive Beamforming for Vehicular Networks: A Low-overhead Joint Radar-Communication Approach](https://mlsanity.com/paper/2005.07698/) (2020)
- [Enabling Joint Communication and Radar Sensing in Mobile Networks -- A Survey](https://mlsanity.com/paper/2006.07559/) (2020)
- [Integration of Communication and Sensing in 6G: a Joint Industrial and Academic Perspective](https://mlsanity.com/paper/2106.13023/) (2021)
- [ISAC-NET: Model-driven Deep Learning for Integrated Passive Sensing and Communication](https://mlsanity.com/paper/2307.15074/) (2023)
- [A Novel Joint Angle-Range-Velocity Estimation Method for MIMO-OFDM ISAC Systems](https://mlsanity.com/paper/2308.03387/) (2023)
- [Joint Range-Velocity-Azimuth Estimation for OFDM-Based Integrated Sensing and Communication](https://mlsanity.com/paper/2312.13154/) (2023)
- [Integrated Sensing and Communication Channel Modeling: A Survey](https://mlsanity.com/paper/2404.17462/) (2024)
- [Networked Integrated Sensing and Communications for 6G Wireless Systems](https://mlsanity.com/paper/2405.16398/) (2024)
- [Integrated Sensing and Communications in Clutter Environment](https://mlsanity.com/paper/2311.01674/) (2023)

## Abstract (arXiv)

Future integrated sensing and communication (ISAC) architectures separate the sensing entity (SE) that acquires measurements from the sensing function (SF) that performs inference, creating a need for compact, task-oriented feedback on the SE-SF interface. Forwarding the raw channel frequency response or full per-link delay-Doppler-azimuth-elevation (DDAE) tensor is prohibitively expensive, while peak-only reporting discards target-discriminative structure under clutter. We propose a learning-based coarse-to-fine sensing pipeline with candidate-latent feedback for single-target estimation. At the SE, a lightweight convolutional scorer produces a dense delay-Doppler proposal map from pilot-based OFDM channel estimates, and a learned encoder constructs K compact C-dimensional candidate tokens by fusing per-candidate azimuth-elevation patches, normalized position, and confidence cues. The latents are uniformly quantized post-training to b bits and transmitted under a finite budget B_fb = bKC + 18K + 16 bits to the SF, which performs cross-candidate refinement, reranking, and joint four-parameter estimation. On a ray-traced urban scene with static and dynamic clutter, three operating points in the (K, C, b) design space achieve 96.33-98.88% detection at 107-806 bytes per coherent processing interval, compression ratios of 1.2-9.2 x 10^4 over the 8-bit DDAE magnitude tensor, reducing the SE-SF interface from multi-Gbit/s to sub-Mbit/s rates. Cross-scene evaluation on an independent campus-scale environment achieves 98.79-99.50% detection and at-or-better angular accuracy without retraining, indicating that the learned representation captures target-relevant structure that transports across scenes of comparable or lower clutter density.