# Real-Time Inference for Distributed Multimodal Systems under Communication Delay Uncertainty

arXiv: https://arxiv.org/abs/2511.16225 · HTML: https://mlsanity.com/paper/2511.16225/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 20 Nov 2025.

## Builds on (most cited first, 8 of 8)

- [Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions](https://mlsanity.com/paper/2209.03430/) (2022)
- [The Challenges of Continuous Self-Supervised Learning](https://mlsanity.com/paper/2203.12710/) (2022)
- [AVE-CLIP: AudioCLIP-based Multi-window Temporal Transformer for Audio Visual Event Localization](https://mlsanity.com/paper/2210.05060/) (2022)
- [Towards Open-Vocabulary Audio-Visual Event Localization](https://mlsanity.com/paper/2411.11278/) (2024)
- [Compression Beyond Pixels: Semantic Compression with Multimodal Foundation Models](https://mlsanity.com/paper/2509.05925/) (2025)
- [Time, Simultaneity, and Causality in Wireless Networks with Sensing and Communications](https://mlsanity.com/paper/2401.08258/) (2024)
- [AdaFlow: Opportunistic Inference on Asynchronous Mobile Data with Generalized Affinity Control](https://mlsanity.com/paper/2410.24028/) (2024)
- [Statistical Characterization of Closed-Loop Latency at the Mobile Edge](https://mlsanity.com/paper/2205.05314/) (2022)

## Abstract (arXiv)

Connected cyber-physical systems perform inference based on real-time inputs from multiple data streams. Uncertain communication delays across data streams challenge the temporal flow of the inference process. State-of-the-art (SotA) non-blocking inference methods rely on a reference-modality paradigm, requiring one modality input to be fully received before processing, while depending on costly offline profiling. We propose a novel, neuro-inspired non-blocking inference paradigm that primarily employs adaptive temporal windows of integration (TWIs) to dynamically adjust to stochastic delay patterns across heterogeneous streams while relaxing the reference-modality requirement. Our communication-delay-aware framework achieves robust real-time inference with finer-grained control over the accuracy-latency tradeoff. Experiments on the audio-visual event localization (AVEL) task demonstrate superior adaptability to network dynamics compared to SotA approaches.