LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation

Hugging Face Daily Papers Papers
neural-codec compression real-time lightweight rate-distortion signal-processing open-source

Summary

This paper introduces LiVeAction, a lightweight neural codec designed for real-time operation on resource-constrained devices. It utilizes an FFT-like structure and variance-based rate penalty to achieve superior rate-distortion performance while remaining practical for low-power sensors.

Modern sensors generate rich, high-fidelity data, yet applications operating on wearable or remote sensing devices remain constrained by bandwidth and power budgets. Standardized codecs such as JPEG and MPEG achieve efficient trade-offs between bitrate and perceptual quality but are designed for human perception, limiting their applicability to machine-perception tasks and non-traditional modalities such as spatial audio arrays, hyperspectral images, and 3D medical images. General-purpose compression schemes based on scalar quantization or resolution reduction are broadly applicable but fail to exploit inherent signal redundancies, resulting in suboptimal rate-distortion performance. Recent generative neural codecs, or tokenizers, model complex signal dependencies but are often over-parameterized, data-hungry, and modality-specific, making them impractical for resource-constrained environments. We introduce a Lightweight, Versatile, and Asymmetric neural codec architecture (LiVeAction), that addresses these limitations through two key ideas. (1) To reduce the complexity of the encoder to meet the resource constraints of the execution environments, we impose an FFT-like structure and reduce the overall size and depth of the neural-network-based analysis transform. (2) To allow arbitrary signal modalities and simplify training, we replace adversarial and perceptual losses with a variance-based rate penalty. Our design produces codecs that deliver superior rate-distortion performance compared to state-of-the-art generative tokenizers, while remaining practical for deployment on low-power sensors. We release our code, experiments, and python library at https://github.com/UT-SysML/liveaction .
Original Article
View Cached Full Text

Cached at: 05/11/26, 07:21 AM

Paper page - LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation

Source: https://huggingface.co/papers/2605.06628

Abstract

LiVeAction is a lightweight neural codec architecture that improves rate-distortion performance for resource-constrained devices by using an FFT-like structure and variance-based rate penalty instead of adversarial losses.

Modern sensors generate rich, high-fidelity data, yet applications operating on wearable or remote sensing devices remain constrained by bandwidth and power budgets. Standardized codecs such as JPEG and MPEG achieve efficient trade-offs between bitrate and perceptual quality but are designed for human perception, limiting their applicability to machine-perception tasks and non-traditional modalities such as spatial audio arrays, hyperspectral images, and 3D medical images. General-purpose compression schemes based on scalar quantization or resolution reduction are broadly applicable but fail to exploit inherent signal redundancies, resulting in suboptimalrate-distortion performance. Recent generativeneural codecs, or tokenizers, model complex signal dependencies but are often over-parameterized, data-hungry, and modality-specific, making them impractical for resource-constrained environments. We introduce a Lightweight, Versatile, and Asymmetricneural codecarchitecture (LiVeAction), that addresses these limitations through two key ideas. (1) To reduce the complexity of the encoder to meet the resource constraints of the execution environments, we impose anFFT-like structureand reduce the overall size and depth of theneural-network-based analysis transform. (2) To allow arbitrary signal modalities and simplify training, we replace adversarial and perceptual losses with avariance-based rate penalty. Our design produces codecs that deliver superiorrate-distortion performancecompared to state-of-the-artgenerative tokenizers, while remaining practical for deployment on low-power sensors. We release our code, experiments, and python library at https://github.com/UT-SysML/liveaction .

View arXiv pageView PDFProject pageGitHub1Add to collection

Get this paper in your agent:

hf papers read 2605\.06628

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper1

#### danjacobellis/autocodec Image-to-Image• Updated3 days ago

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.06628 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.06628 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

AdaCodec: A Predictive Visual Code for Video MLLMs

Hugging Face Daily Papers

AdaCodec reduces video encoding redundancy in multimodal LLMs by transmitting full visual tokens only when scene prediction fails, otherwise using compact inter-frame change descriptions. It outperforms per-frame RGB baselines at matched token budgets and achieves better or comparable results with significantly fewer tokens, reducing time-to-first-token from 9.26s to 1.62s.

LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence

Hugging Face Daily Papers

LLaVA-OneVision-2 introduces codec-stream tokenization and windowed attention for efficient video understanding, achieving state-of-the-art performance across multiple multimodal benchmarks including video, spatial, and tracking tasks.

Real-Time Long Video Generation (GitHub Repo)

TLDR AI

NVlabs releases LongLive 2.0, a parallel infrastructure for real-time long video generation using NVFP4 quantization, supporting both training and inference. It achieves 45.7 FPS and is accepted at ICLR 2026.