ALLPCB
Large-Scale Visual SLAM with 3D Gaussian Splatting
LSG-SLAM: a stereo visual SLAM using 3D Gaussian splatting for large-scale outdoor reconstruction, improving tracking stability and mapping quality.
Bias and Variance in Machine Learning Models
Explains why ML models can't reach zero error, detailing irreducible error, bias-variance tradeoff, model complexity, overfitting, and MSE for prediction accuracy.
Embodied AI Simulation Generation System
LLM-driven system automates embodied intelligence skill generation for robotic arms, converting natural-language tasks into MuJoCo scenes, actions, and reward code.
Optimizing Deep Learning Models
Practical deep learning tuning guide covering learning rate selection, batch size effects, weight initialization, optimizers, regularization, data augmentation and training tips.
Why GPUs Are Essential for AI Training
Technical overview of why GPUs outperform CPUs for deep learning training: neural networks' matrix operations, parallelism, GPU architecture and GPGPU benefits.
Deep Learning for Defect Detection
Explore deep learning for defect detection in industries, offering accurate solutions for quality control with advanced frameworks.
Breaking Compute Bottlenecks for Large Language Models
Analysis of large-model scaling: how parameter count and training tokens drive compute requirements, showing compute grows ~quadratically with model size.
Beginner's Guide to Training Large Language Models
Technical guide to scaling LLM training: analyzes memory usage, gradient accumulation, ZeRO, and tensor/data parallelism to improve throughput and GPU utilization.
Deepseek R1 Offline Deployment Guide
Technical guide to installing RKLLM-Toolkit and converting/deploying the DeepSeek-R1 LLM on EASY-EAI-Orin-Nano (RK3576), covering env setup, conversion, and on-device inference.
What Is an RNN (Recurrent Neural Network)?
Technical overview of RNNs and LSTM architectures, how they model sequential data, application areas like signal and text processing, and MATLAB-based implementation.
Building a Multilingual Open-Ended QA Dataset
OMGEval presents an open-source multilingual open-ended QA benchmark (804 Chinese prompts) localized from AlpacaEval, using Text-Davinci-003 baseline and GPT-4 evaluation.
6G Sub-THz Communication Test Solutions
Summary of terahertz sub-THz testing for 6G: spectrum use, RF front-end modules, signal generation, and channel measurement tools for terahertz communications research.
OpenAI's Defense Against LLM Attacks
OpenAI's study unveils an instruction hierarchy to boost LLM security against attacks like prompt injections, enhancing model safety.
Classical Computer Vision vs. Deep Learning
Analysis of deep learning in computer vision: strengths, limits, dataset biases, comparison with classical vision methods, interpretability and risks in safety-critical applications.
Add AI Capability to Raspberry Pi 5
Technical overview and setup of the Raspberry Pi AI kit with Hailo 8L NPU, covering M.2 HAT+ installation, thermal management, and software setup for Pi 5.
RL-Designed GPU Arithmetic Circuits at NVIDIA
PrefixRL uses deep reinforcement learning to optimize parallel prefix circuits, producing smaller, lower-latency adders and mapping Pareto trade-offs between area and latency.
GPU Clusters for Very Large AI Models
Summary of TensorNODE, a TensorWave bare-metal AI cloud using AMD MI300X GPUs and a PCIe Gen5 memory fabric to enable petabyte-scale GPU memory pools.
7 Hyperparameter Search Methods for Machine Learning
Survey of hyperparameter optimization methods - grid/random search, Bayesian optimization, simulated annealing, genetic algorithms and successive halving for ML tuning.
Smart Classroom IoT Solution
Analysis of an IoT smart classroom solution - hardware connectivity, data interoperability and scenario intelligence for unified, energy-efficient device management.
FPGA Applications in Machine Learning
Overview of FPGA applications in machine learning: accelerating neural network inference, hardware quantization, algorithm optimization, and efficiency for edge AI deployments.