Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning

EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation

There is an increasing demand for lightweight multi-person pose estimation for many emerging smart IoT applications. However, the existing algorithms tend to have large model sizes and intense computational requirements, making them ill-suited for real-time applications and deployment on resource-constrained hardware. Lightweight and real-time approaches are exceedingly rare and come at the cost of inferior accuracy. In this paper, we present EfficientHRNet, a family of lightweight multi-person human pose estimators that are able to perform in real-time on resource-constrained devices. By unif…

解码听者身份：使用轻量级脉冲Transformer从EEG信号进行人员识别

Decoding Listeners Identity: Person Identification from EEG Signals Using a Lightweight Spiking Transformer

针对现有EEG人员识别深度学习方法计算成本高的问题，提出结合轻量级脉冲Transformer的脉冲神经网络方法，在EEG音乐情绪识别挑战数据集上实现100%准确率且能耗不足传统深度网络10%，为高能效BCI提供新方向。

可验证性优先代理：可证明的可观测性和轻量级审计代理用于控制自主大语言模型系统

Verifiability-First Agents: Provable Observability and Lightweight Audit Agents for Controlling Autonomous LLM Systems

本文提出了一种以可验证性为核心的代理架构，通过加密和符号方法实现运行时认证，嵌入轻量级审计代理并采用挑战-响应协议，以提高自主大语言模型系统的可控性和可审计性。

Person Detection Using an Ultra Low-resolution Thermal Imager on a Low-cost MCU

Detecting persons in images or video with neural networks is a well-studied subject in literature. However, such works usually assume the availability of a camera of decent resolution and a high-performance processor or GPU to run the detection algorithm, which significantly increases the cost of a complete detection system. However, many applications require low-cost solutions, composed of cheap sensors and simple microcontrollers. In this paper, we demonstrate that even on such hardware we are not condemned to simple classic image processing techniques. We propose a novel ultra-lightweight C…

LightSleepX：一种轻量级、基于Inception的双模态睡眠分期网络

LightSleepX: A Lightweight, Inception-Based Dual-Modal Network for Sleep Staging

LightSleepX提出轻量级双模态睡眠分期网络，结合Inception架构、深度可分离卷积、多尺度注意力与Mamba编码器，在低资源下实现高精度，参数仅0.049M。

SALT：一种面向封闭拆分计算环境的轻量级模型适配方法

SALT: A Lightweight Model Adaptation Method for Closed Split Computing Environments

针对封闭拆分计算中用户无法访问头尾网络、传统适配方法失效的问题，提出轻量级框架SALT，通过客户端可训练适配器优化潜在特征实现适配，在低延迟下提升分类精度，还支持有损网络鲁棒推理，为边缘AI个性化推理提供实用方案。