# AI Flow at the Network Edge

arXiv: https://arxiv.org/abs/2411.12469 · HTML: https://mlsanity.com/paper/2411.12469/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 19 Nov 2024.

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model](https://mlsanity.com/paper/2310.01412/) (2023)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach](https://mlsanity.com/paper/2102.04170/) (2021)
- [Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications](https://mlsanity.com/paper/2111.12444/) (2021)
- [Communication-Computation Trade-Off in Resource-Constrained Edge Inference](https://mlsanity.com/paper/2006.02166/) (2020)
- [Compressing Neural Networks using the Variational Information Bottleneck](https://mlsanity.com/paper/1802.10399/) (2018)
- [Large Language Models Empowered Autonomous Edge AI for Connected Intelligence](https://mlsanity.com/paper/2307.02779/) (2023)

## Built on by (most cited first, 30 of 46)

- [Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference](https://mlsanity.com/paper/2503.12926/) (2025)
- [Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model](https://mlsanity.com/paper/2503.04543/) (2025)
- [NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering](https://mlsanity.com/paper/2503.07076/) (2025)
- [VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers](https://mlsanity.com/paper/2503.09387/) (2025)
- [Generative Video Compression: Towards 0.01% Compression Rate for Video Transmission](https://mlsanity.com/paper/2512.24300/) (2025)
- [GUI-Eyes: Tool-Augmented Perception for Visual Grounding in GUI Agents](https://mlsanity.com/paper/2601.09770/) (2026)
- [SalQ-VLM: Fine-Grained Saliency-Guided Quantization for Vision-Language Models](https://mlsanity.com/paper/2508.03351/) (2025)
- [Information Capacity: Evaluating the Efficiency of Large Language Models via Text Compression](https://mlsanity.com/paper/2511.08066/) (2025)
- [Mitigating Spurious Correlations Between Question and Answer via Chain-of-Thought Correctness Perception Distillation](https://mlsanity.com/paper/2509.05602/) (2025)
- [MR-UIE: Multi-Perspective Reasoning with Reinforcement Learning for Universal Information Extraction](https://mlsanity.com/paper/2509.09082/) (2025)
- [T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables](https://mlsanity.com/paper/2508.19813/) (2025)
- [Towards Pervasive Distributed Agentic Generative AI -- A State of The Art](https://mlsanity.com/paper/2506.13324/) (2025)
- [Quantize-Sample-and-Verify: LLM Acceleration via Adaptive Edge-Cloud Speculative Decoding](https://mlsanity.com/paper/2507.00605/) (2025)
- [Emotional Support with LLM-based Empathetic Dialogue Generation](https://mlsanity.com/paper/2507.12820/) (2025)
- [CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs](https://mlsanity.com/paper/2510.26843/) (2025)
- [Training Report of TeleChat3-MoE](https://mlsanity.com/paper/2512.24157/) (2025)
- [PhysOmni: Physics-Grounded Multi-Object Scene Generation from a Single Image with Real-Time Interaction](https://mlsanity.com/paper/2605.20290/) (2026)
- [CineWeaver: Training-Free Reference-Controllable Multi-Shot Long Video Generation for Cinematic Storytelling](https://mlsanity.com/paper/2607.26529/) (2026)
- [TableZoomer: A Collaborative Agent Framework for Large-scale Table Question Answering](https://mlsanity.com/paper/2509.01312/) (2025)
- [The Law of Multi-Model Collaboration: Scaling Limits of Model Ensembling for Large Language Models](https://mlsanity.com/paper/2512.23340/) (2025)
- [Theoretical Foundations of Scaling Law in Familial Models](https://mlsanity.com/paper/2512.23407/) (2025)
- [Enhancing Neural Video Compression of Static Scenes with Positive-Incentive Noise](https://mlsanity.com/paper/2603.06095/) (2026)
- [Ruyi2 Technical Report](https://mlsanity.com/paper/2602.22543/) (2026)
- [Generative Transmission: Rethinking Computation, Bandwidth, and Memory in Communication](https://mlsanity.com/paper/2607.17482/) (2026)
- [WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN](https://mlsanity.com/paper/2608.07267/) (2026)
- [TourPhysics: Bringing Physics to World Models for Exploration and Manipulation from a Single Image](https://mlsanity.com/paper/2609.04911/) (2026)
- [ScRPO: From Errors to Insights](https://mlsanity.com/paper/2511.06065/) (2025)
- [Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding](https://mlsanity.com/paper/2511.19005/) (2025)
- [Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity](https://mlsanity.com/paper/2601.06596/) (2026)
- [A Real-Time Privacy-Preserving Behavior Recognition System via Edge-Cloud Collaboration](https://mlsanity.com/paper/2601.22938/) (2026)

## Abstract (arXiv)

Recent advancements in large language models (LLMs) and their multimodal variants have led to remarkable progress across various domains, demonstrating impressive capabilities and unprecedented potential. In the era of ubiquitous connectivity, leveraging communication networks to distribute intelligence is a transformative concept, envisioning AI-powered services accessible at the network edge. However, pushing large models from the cloud to resource-constrained environments faces critical challenges. Model inference on low-end devices leads to excessive latency and performance bottlenecks, while raw data transmission over limited bandwidth networks causes high communication overhead. This article presents AI Flow, a framework that streamlines the inference process by jointly leveraging the heterogeneous resources available across devices, edge nodes, and cloud servers, making intelligence flow across networks. To facilitate cooperation among multiple computational nodes, the proposed framework explores a paradigm shift in the design of communication network systems from transmitting information flow to intelligence flow, where the goal of communications is task-oriented and folded into the inference process. Experimental results demonstrate the effectiveness of the proposed framework through an image captioning use case, showcasing the ability to reduce response latency while maintaining high-quality captions. This article serves as a position paper for identifying the motivation, challenges, and principles of AI Flow.