IEEE

MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders

Abstract: Visual encoders are fundamental components in vision-language models (VLMs), each showcasing unique strengths derived from various pre-trained visual foundation models. To leverage the ...
GitHub

SC-Series Servo library for Arduino and ESP32

📚 SCSERVO LIBRARY Target Description Usage lint-arduino lint Arduino code using arduino-lint `make lint-arduino` lint-cpp lint C++ code using cpplint and clang-format `make lint-cpp` help display a ...
CNX Software

Compact development board features a single ESP32-P4 + ESP32-C5 dual-band Wi-Fi 6 module, MIPI display and camera interfaces

S1, which combines the ESP32-P4 with an ESP32-C5 dual-band WiFi 6 module, instead of the more commonly used ESP32-C6 wireless ...
IEEE

Exchanging Dual-Encoder–Decoder: A New Strategy for Change Detection With Semantic Guidance and Spatial Localization

Abstract: Change detection is a critical task in earth observation applications. Recently, deep-learning-based methods have shown promising performance and are quickly adopted in change detection.
GitHub

An MCP-based Chatbot

As a voice interaction entry, the XiaoZhi AI chatbot leverages the AI capabilities of large models like Qwen / DeepSeek, and achieves multi-terminal control via the MCP protocol. The current v2 ...