HuggingFace Dataset and Pytorch Dataset I

04-03

增進工程師效率 Python DataFrame - CSV & Plot

12-21

增進工程師效率 Python DataFrame - CSV & Plot

12-21

Math AI G-CNN (Group + CNN)

05-08

Edge AI Trilogy III - Model Compression

04-05

增進工程師效率 Python DataFrame - CSV & Plot

12-21

Math AI G-CNN (Group + CNN)

05-08

Edge AI Trilogy III - Model Compression

04-05

AI Model Sparsity Pruning Compression

09-03

Math AI G-CNN (Group + CNN)

05-08

Edge AI Trilogy III - Model Compression

04-05

Math AI G-CNN (Group + CNN)

05-08

Edge AI Trilogy III - Model Compression

04-05

AI for Coding - Claude Codex Gemini CLI

11-27

Claude Project Cross PC and Mac

08-13

Python Project Management - Minbpe

09-27

Python Project Management - Testing

10-22

Python Project Management - Structure

10-07

Julia Code Snip

09-20

Improve Engineer Efficiency - Python Image Library

12-11

增進工程師效率 Julia Linear Algebra

04-21

Julia Code Snip

09-20

增進工程師效率 Julia Linear Algebra

04-21

Math AI - ML Estimation To EM Algorithm For Hidden Data

06-30

Typora and Mermaid

02-16

Math ML - Modified Softmax w/ Margin

01-16

Jekyll Memo for Github Blog

06-30

Jekyll Memo for Github Blog

06-30

HMM Triology (III) - EM Algorithm

10-09

Math AI - VAE Coding

09-29

Reinforcement Learning

09-29

Math AI - Diffusion Generative Model Extended from VAE

08-30

Math AI - Variational Autoencoder Vs. Variational EM Algorithm

08-18

Math ML - Maximum Likelihood Vs. Bayesian

08-17

Math AI - From EM to Variational Bayesian Inference

08-15

Math AI - ML Estimation To EM Algorithm For Hidden Data

06-30

English

08-03

Learning Japanese Grammar

01-03

Learning Japanese

12-20

Claude Project Cross PC and Mac

08-13

Cross Platform Python Project Management

07-31

Autoregression vs. Diffusion

03-24

Discrete Diffusion

03-23

Three Road Diffusion

03-23

Diffusion Theory for Gaussian Mixture Model

03-23

Three Road Diffusion

03-23

Stanford AI- Diffusion Lecture

03-18

Generative AI- Diffusion Lecture

01-18

English

08-03

Math AI - 演繹推理和合情推理

07-24

Acceptance-Rejection Sampling 接受拒絕採樣

05-26

Equal Distribution - 什麽是機率分佈相等？

05-26

Math ML - Maximum Likelihood Vs. Bayesian

08-17

Math AI - From EM to Variational Bayesian Inference

08-15

Math AI - 演繹推理和合情推理

07-24

Less is More, But Scale Matters

07-24

Math AI - 機率論或論機率？

07-19

Colab 使用方法

03-24

AI Coding 編程

03-23

VS Code for Jupyter

02-12

VS Code for WSL2

12-09

Julia Code Snip

09-20

Math Stat I - Likelihood, Score Function, and Fisher Information

09-17

Windows + ML CUDA - Anaconda / WSL2 / DirectML

08-13

Excel Link to MySQL

10-22

HMM Triology (III) - EM Algorithm

10-09

Math AI - VAE Coding

09-29

Reinforcement Learning

09-29

Windows + CUDA - PyTorch and TensorFlow

09-25

Machine Learning Database

09-19

Math AI - Deterministic and Probabilistic?

09-19

Math AI - Diffusion Generative Model Extended from VAE

08-30

Math AI - Variational Autoencoder Vs. Variational EM Algorithm

08-18

Math ML - Maximum Likelihood Vs. Bayesian

08-17

Math AI - From EM to Variational Bayesian Inference

08-15

From Quantum Mechanics to Classical Mechanics

11-17

Lagrangian and Hamiltonian Mechanics

11-09

Math AI - ODE Relationship to Thermodynamics

05-26

無所不在的拉格朗日 - Lagrangian Everywhere

05-16

Generative AI- Diffusion Lecture

01-18

Attention 數學結構

10-10

Math AI - 機率論或論機率？

07-19

Acceptance-Rejection Sampling 接受拒絕採樣

05-26

Equal Distribution - 什麽是機率分佈相等？

05-26

考拉兹猜想

05-25

座標系不變 (invariant), 協變 (Covariant), 和逆變 (Contravariant)

06-25

Optimization - NN Optimization

06-19

Optimization - Manifold Gradient Descent

06-03

Math AI - Stochastic Differential Equation Forward

05-01

Math AI - Diffusion vs. SDE

05-01

Math AI - Stochastic Differential Equation Backward

04-29

Math - 積分

04-16

Math AI - Stochastic Differential Equation

04-16

Matrix Multiplication and Tensor Decomposition (?)

04-04

Fundamental theorem of GA calculus

12-17

Field Theory Fundamental and Lagrangian

12-10

Geometric Algebra (GA) Introduction and Application

12-03

Web Crawler or Scraper

10-16

Static Data Crawler

10-01

跨平臺 Markdown Plus MathJax Blog Editing 分享

09-12

Math ML - Maximum Likelihood Vs. Bayesian

08-17

Math AI - From EM to Variational Bayesian Inference

08-15

Attention 數學結構

10-10

Acceptance-Rejection Sampling 接受拒絕採樣

05-26

Equal Distribution - 什麽是機率分佈相等？

05-26

考拉兹猜想

05-25

Physics Informed ML/AI

03-03

Math AI - Stochastic Differential Equation Forward

05-01

Math AI - Diffusion vs. SDE

05-01

Math AI - Stochastic Differential Equation Backward

04-29

Math - 積分

04-16

Math AI - Stochastic Differential Equation

04-16

Matrix Multiplication and Tensor Decomposition (?)

04-04

跨平臺 Markdown Plus MathJax Blog Editing 分享

09-12

Math ML - Maximum Likelihood Vs. Bayesian

08-17

Math AI - From EM to Variational Bayesian Inference

08-15

Math ML - Maximum Likelihood Vs. Bayesian

08-17

Computer Vision - HDR Network

12-02

Computer Vision - UNet from Autoencoder and FCN

11-19

Math AI - VAE Coding

09-29

Reinforcement Learning

09-29

Math AI - Diffusion Generative Model Extended from VAE

08-30

Math AI - Variational Autoencoder Vs. Variational EM Algorithm

08-18

Math AI - VAE Coding

09-29

Reinforcement Learning

09-29

Math AI - Diffusion Generative Model Extended from VAE

08-30

Math AI - Variational Autoencoder Vs. Variational EM Algorithm

08-18

Math AI - VAE Coding

09-29

Reinforcement Learning

09-29

Math AI - Diffusion Generative Model Extended from VAE

08-30

Math AI - Variational Autoencoder Vs. Variational EM Algorithm

08-18

Math AI - Fuse Flow and Diffusion

06-05

Math AI - Expand Score Matching to Flow Matching

05-15

Math AI - Diffusion Acceleration Phases

05-10

Autoregression vs. Diffusion

03-24

Discrete Diffusion

03-23

Diffusion Theory for Gaussian Mixture Model

03-23

Three Road Diffusion

03-23

Stanford AI- Diffusion Lecture

03-18

Math AI - Score Matching is All U Need for Diffusion

02-02

Math Stat I - Likelihood, Score Function, and Fisher Information

02-01

Generative AI- Diffusion Lecture

01-18

Why does diffusion work better than auto-regression?

05-07

Math AI - Diffusion vs. SDE

05-01

Math AI - Stochastic Differential Equation

04-16

Generative AI- Stable Diffusion

02-07

Deep Learning using Nonequilibrium Thermodynamics

02-07

Math AI - Diffusion Generative Model Extended from VAE

08-30

跨平臺 Markdown Plus MathJax Blog Editing 分享

09-12

跨平臺 Markdown Plus MathJax Blog Editing 分享

09-12

Math AI - Deterministic and Probabilistic?

09-19

Math AI - Deterministic and Probabilistic?

09-19

Math AI - Deterministic and Probabilistic?

09-19

HuggingFace Dataset and Pytorch Dataset I

04-03

Excel Link to MySQL

10-22

Machine Learning Database

09-19

Less is More, But Scale Matters

07-24

Math AI - 機率論或論機率？

07-19

Colab 使用方法

03-24

AI Coding 編程

03-23

VS Code for Jupyter

02-12

VS Code for WSL2

12-09

Windows + ML CUDA - Anaconda / WSL2 / DirectML

08-13

Excel Link to MySQL

10-22

Windows + CUDA - PyTorch and TensorFlow

09-25

Machine Learning Database

09-19

Colab 使用方法

03-24

AI Coding 編程

03-23

VS Code for Jupyter

02-12

VS Code for WSL2

12-09

Windows + ML CUDA - Anaconda / WSL2 / DirectML

08-13

Windows + CUDA - PyTorch and TensorFlow

09-25

Colab 使用方法

03-24

AI Coding 編程

03-23

VS Code for Jupyter

02-12

VS Code for WSL2

12-09

Windows + ML CUDA - Anaconda / WSL2 / DirectML

08-13

Windows + CUDA - PyTorch and TensorFlow

09-25

Windows + ML CUDA - Anaconda / WSL2 / DirectML

08-13

Windows + CUDA - PyTorch and TensorFlow

09-25

Colab 使用方法

03-24

AI Coding 編程

03-23

VS Code for WSL2

12-09

Windows + ML CUDA - Anaconda / WSL2 / DirectML

08-13

Windows + CUDA - PyTorch and TensorFlow

09-25

AI for Coding - Claude Codex Gemini CLI

11-27

Claude Project Cross PC and Mac

08-13

Cross Platform Python Project Management

07-31

VS Code on Colab

11-14

VS Code for Jupyter

02-12

VS Code for WSL2

12-09

Git Revision Control

11-19

Windows + ML CUDA - Anaconda / WSL2 / DirectML

08-13

VScode for Python and Julia

02-05

Windows + CUDA - PyTorch and TensorFlow

09-25

Colab 使用方法

03-24

AI Coding 編程

03-23

VS Code for WSL2

12-09

Windows + ML CUDA - Anaconda / WSL2 / DirectML

08-13

Windows + CUDA - PyTorch and TensorFlow

09-25

Colab 使用方法

03-24

AI Coding 編程

03-23

VS Code for Jupyter

02-12

VS Code for WSL2

12-09

Windows + ML CUDA - Anaconda / WSL2 / DirectML

08-13

Windows + CUDA - PyTorch and TensorFlow

09-25

Math AI - Rectified Flow (ReFlow)

06-23

Math AI - Expand Score Matching to Flow Matching

06-15

Math AI - Gaussian Flow

06-08

Math AI - Fuse Flow and Diffusion

06-05

Math AI - Improve Flow Matching

06-02

Math AI - SDE_ODE_Flow_Diffusion

05-25

Math AI - Expand Score Matching to Flow Matching

05-15

Math AI - Diffusion Acceleration Phases

05-10

Math AI - Expand Score Matching to Flow Matching

05-05

Math AI - Normalizing Flow

05-05

Math AI - Expand Score Matching to Flow Matching

05-05

Autoregression vs. Diffusion

03-24

Discrete Diffusion

03-23

Three Road Diffusion

03-23

Diffusion Theory for Gaussian Mixture Model

03-23

Three Road Diffusion

03-23

Stanford AI- Diffusion Lecture

03-18

Generation via Flow Model

03-06

Gaussian Invariant

03-02

Math AI - Score Matching is All U Need for Diffusion

02-02

Math Stat I - Likelihood, Score Function, and Fisher Information

02-01

Generative AI- Diffusion Lecture

01-18

Why does diffusion work better than auto-regression?

05-07

Math AI - Diffusion vs. SDE

05-01

Generative AI- Stable Diffusion

02-07

Deep Learning using Nonequilibrium Thermodynamics

02-07

如何避免 L2-norm or layer norm FP16 overflow or underflow

10-09

Math AI Flow and Flux PDE

01-16

Neural Network and CV Optical Flow 算法

01-05

Math AI - VAE Coding

09-29

HMM Triology (III) - EM Algorithm

10-09

HMM Triology (III) - EM Algorithm

10-09

Information Theory - Constrained Noiseless Channel Capacity

01-24

Information Theory for Noisy Communication

12-17

Math Stat II - XYZ Entropy and XYZ Information

09-24

Math ML - Entropy and Mutual Information

10-10

Information Theory - Constrained Noiseless Channel Capacity

01-24

Information Theory For Hash Code

01-23

Information Theory for Noisy Communication

12-17

Math ML - Entropy and Mutual Information

10-10

Math ML - Entropy and Mutual Information

10-10

Computer Vision - FRC and MEMC

11-13

Computer Vision - FRC and MEMC

11-13

Computer Vision - FRC and MEMC

11-13

Computer Vision - UNet from Autoencoder and FCN

11-19

Computer Vision - HDR Network

12-02

Computer Vision - UNet from Autoencoder and FCN

11-19

Computer Vision - HDR Network

12-02

Computer Vision - HDR Network

12-02

Computer Vision - HDR Network

12-02

Computer Vision - CV Image Resize

12-02

Computer Vision - CV Image Resize

12-02

Hole Detection

01-14

AI SfM - DUSt3r, MASt3r, MONSt3r

10-07

Structure from Motion

10-06

AI Coach for Bouldering Project2

10-05

Robot Deep Research

07-19

AI Coach for Bouldering Project

05-01

vSLAM with NN

05-13

vSLAM with NN

05-13

CV-SLAM Bundle Adjustment (BA)

04-23

CV-SLAM Feature Extraction - SIFT/SURF/ORB

04-16

vSLAM Introduction

04-15

SLAM Demystify

03-25

Vision Transformer

02-27

Thermal Resistance

01-17

Math AI Flow and Flux PDE

01-16

CV Super Resolution - AMD FSR

01-14

Computer Vision My Way

12-18

Improve Engineer Efficiency - Python Image Library

12-11

Computer Vision - CV Image Resize

12-02

Improve Engineer Efficiency - Python Image Library

12-11

Computer Vision - CV Image Resize

12-02

Computer Vision - CV Image Resize

12-02

Improve Engineer Efficiency - Python Image Library

12-11

Improve Engineer Efficiency - Python Image Library

12-11

Claude Project Cross PC and Mac

08-13

Cross Platform Python Project Management

07-31

Python Project Management - Minbpe

09-27

Python Project Management - Testing

10-22

Web Crawler or Scraper

10-16

Web Crawler or Scraper

10-16

Dynamic Data Crawler

10-14

Python Project Management - Structure

10-07

Static Data Crawler

10-01

Improve Engineer Efficiency - Python Image Library

12-11

Math AI - Rectified Flow (ReFlow)

06-23

Math AI - Expand Score Matching to Flow Matching

06-15

Math AI - Gaussian Flow

06-08

Math AI - Fuse Flow and Diffusion

06-05

Math AI - Improve Flow Matching

06-02

Math AI - Expand Score Matching to Flow Matching

05-15

Math AI - Expand Score Matching to Flow Matching

05-05

Math AI - Normalizing Flow

05-05

Math AI - Expand Score Matching to Flow Matching

05-05

Generation via Flow Model

03-06

如何避免 L2-norm or layer norm FP16 overflow or underflow

10-09

Math AI Flow and Flux PDE

01-16

Neural Network and CV Optical Flow 算法

01-05

Math AI - Rectified Flow (ReFlow)

06-23

Math AI - Expand Score Matching to Flow Matching

06-15

Math AI - Gaussian Flow

06-08

Math AI - Fuse Flow and Diffusion

06-05

Math AI - Improve Flow Matching

06-02

Math AI - SDE_ODE_Flow_Diffusion

05-25

Math AI - Expand Score Matching to Flow Matching

05-15

Math AI - Diffusion Acceleration Phases

05-10

Math AI - Expand Score Matching to Flow Matching

05-05

Math AI - Normalizing Flow

05-05

Math AI - Expand Score Matching to Flow Matching

05-05

Autoregression vs. Diffusion

03-24

Discrete Diffusion

03-23

Three Road Diffusion

03-23

Diffusion Theory for Gaussian Mixture Model

03-23

Three Road Diffusion

03-23

Stanford AI- Diffusion Lecture

03-18

Generation via Flow Model

03-06

Gaussian Invariant

03-02

DeepSeek R1 On Naive Bayes and Logistic Regression

02-16

Math AI - Score Matching is All U Need for Diffusion

02-02

Math Stat I - Likelihood, Score Function, and Fisher Information

02-01

Generative AI- Diffusion Lecture

01-18

Why does diffusion work better than auto-regression?

05-07

Math AI - Diffusion vs. SDE

05-01

Generative AI- Stable Diffusion

02-07

Deep Learning using Nonequilibrium Thermodynamics

02-07

如何避免 L2-norm or layer norm FP16 overflow or underflow

10-09

Math AI Flow and Flux PDE

01-16

Neural Network and CV Optical Flow 算法

01-05

Neural Network and CV Optical Flow 算法

01-05

Thermal Resistance

01-17

Neural Network and CV Optical Flow 算法

01-05

CV Super Resolution - AMD FSR

01-14

Math AI Flow and Flux PDE

01-16

Parser From Scratch

02-01

VS Code on Colab

11-14

VS Code for Jupyter

02-12

VS Code for WSL2

12-09

VScode for Python and Julia

02-05

AI for Coding - Claude Codex Gemini CLI

11-27

Claude Project Cross PC and Mac

08-13

Cross Platform Python Project Management

07-31

Python Project Management - Minbpe

09-27

AI for Coding - Cursor + LLM

08-24

AI for Coding - VS Code + Claude-3.5 Sonnet

08-24

VScode for Python and Julia

02-05

Hole Detection

01-14

AI Agent Applications

12-28

Recent M&A Rationale and Commonality v2 and slides

12-26

Learning Japanese

12-20

Recent M&A Rationale and Commonality

12-17

LLM CI/CD with Front-End Backend

12-01

AI for Coding - Claude Codex Gemini CLI

11-27

LLM Inference Efficiency

11-25

AI SfM - DUSt3r, MASt3r, MONSt3r

10-07

Structure from Motion

10-06

AI Coach for Bouldering Project2

10-05

Robot Deep Research

07-19

LLM Perplexity Benchmark

07-18

LLM Perplexity Benchmark

07-18

AI Coach for Bouldering Project

05-01

Test or Inference Time Compute

01-01

LLM Instability

11-23

How to Improve LLM Error Resillence

11-23

大(語言)模型推理效能

10-27

LLM Adaptation

08-14

LLM 趨勢

08-03

HuggingFace LLM

06-29

Big Little LLMs Applications

06-13

LLM Temperature - 溫度和機率分佈的關係

06-12

AI Agent 實例

05-12

大(語言)模型參數微調 PEFT

05-07

大語言和自然語言處理的差異

05-01

LLM Tokenizer Code

02-21

Streaming LLM

01-04

LLM Performance Benchmark

12-24

Llama Quantization

12-23

RAG + Long Context

12-22

LLM 性能分析

12-09

LLM Tokenizer

12-02

LLM Agent

11-12

LLM Prune

11-12

LLM 計算量分析

11-04

LLM 記憶體分析

10-21

LLM Toy Example

10-14

LLM 三部曲 Part I Foundation Model

03-26

Generative AI Fine Tune

03-22

Vision Transformer

02-27

LLM CI/CD with Front-End Backend

12-01

LLM Inference Efficiency

11-25

LLM Mamba Installation

07-20

LLM Mamba Installation

07-20

LLM Perplexity Benchmark

07-18

LLM Perplexity Benchmark

07-18

Linear Attention Math Framework

07-03

From RNN to Linear Attention to Mamba

03-24

Coding of Perplexity of LLM

01-15

Perplexity of LLM

12-16

Wikitext and Alpaca Dataset

12-16

Symmetric Transformer

12-08

Differential Transformer

12-08

Attention as Kernel and Random Features

12-05

Attention as Kernel and Random Features

11-27

LLM Instability

11-23

How to Improve LLM Error Resillence

11-23

Causal Attention Kernel Code

11-22

Linear Attention Vs. Mamba

11-17

Causal Attention Kernel

11-17

Linear Attention with Topological Masking

11-17

VS Code on Colab

11-14

Performer Pytorch Code Analysis

11-13

Attention as SVM Kernel Interpretation

11-11

Efficient (Still) Transformer

10-28

大(語言)模型推理效能

10-27

Attention as SVM Kernel Interpretation

10-27

Llama3 70B Distributed Inference Code

10-19

Llama3 70B Distributed Inference

10-18

Linear Attention

10-11

Linear Attention

10-11

Attention 數學結構

10-10

Transformer Layer Normalization Placement

10-04

Batch Normalization vs Layer Normalization

10-03

PicoGPT

09-17

LLM Adaptation

08-14

LLM 趨勢

08-03

Less is More, But Scale Matters

07-24

HuggingFace LLM

06-29

MMLU on GPT

06-18

Big Little LLMs Applications

06-13

LLM Temperature - 溫度和機率分佈的關係

06-12

大(語言)模型參數微調 PEFT

05-07

大語言和自然語言處理的差異

05-01

LLM Tokenizer Code

02-21

Makemore Karpathy Code

02-20

ML Normalization

02-14

Streaming LLM

01-04

LLM Performance Benchmark

12-24

Llama Quantization

12-23

RAG + Long Context

12-22

LLM KV Cache Code

12-16

LLM 性能分析

12-09

LLM Tokenizer

12-02

Attention As Graph

11-25

LLM Prune

11-12

LLM 計算量分析

11-04

LLM KV Cache Memory and BW

10-29

LLM 記憶體分析

10-21

LLM Toy Example

10-14

Flash Attention

06-20

XYZ Is All You Need Rationale

04-09

LLM 三部曲 Part I Foundation Model

03-26

Semantic Search Using Query-Key Similarity

03-22

Generative AI Fine Tune

03-22

Semantic Search Query-Key-Value

03-22

Nano GPT

02-20

Self Attention of GPT 圖解

02-18

Generative AI- Stable Diffusion

02-07

Transformer for Speech Recognition

03-21

Vision Transformer

02-27

Hole Detection

01-14

AI SfM - DUSt3r, MASt3r, MONSt3r

10-07

Structure from Motion

10-06

AI Coach for Bouldering Project2

10-05

AI Coach for Bouldering Project

05-01

Vision Transformer

02-27

Transformer for Speech Recognition

03-21

Transformer for Speech Recognition

03-21

Transformer for Speech Recognition

03-21

Robot Deep Research

07-19

vSLAM with NN

05-13

vSLAM with NN

05-13

vSLAM Introduction

04-15

SLAM Demystify

03-25

Robot Deep Research

07-19

vSLAM with NN

05-13

vSLAM with NN

05-13

vSLAM with NN

05-13

CV-SLAM Bundle Adjustment (BA)

04-23

CV-SLAM Feature Extraction - SIFT/SURF/ORB

04-16

vSLAM Introduction

04-15

SLAM Demystify

03-25

AI Hand Pose and Tracking

04-01

A Unified View of Self-Supervised Learning (SSL)

04-05

CV-SLAM Feature Extraction - SIFT/SURF/ORB

04-16

Human Brain

04-23

CV-SLAM Bundle Adjustment (BA)

04-23

CV-SLAM Bundle Adjustment (BA)

04-23

Geometric Deep Learning

08-19

Autoregression vs. Diffusion

03-24

Discrete Diffusion

03-23

Three Road Diffusion

03-23

Diffusion Theory for Gaussian Mixture Model

03-23

Three Road Diffusion

03-23

Stanford AI- Diffusion Lecture

03-18

Generative AI- Diffusion Lecture

01-18

Generative AI- Diffusion Lecture

01-18

Graph RAG Coding

08-13

Graph RAG

07-28

Generative AI- Stable Diffusion

02-07

Generative AI- Stable Diffusion

02-07

Deep Learning using Nonequilibrium Thermodynamics

02-07

Graph Matrix Representation Applications

01-30

二次式和正定矩陣 Quadratic Form and Positive Definite Matrix

01-28

Graph and Eigenvalue

01-28

Graph Machine Learning - Laplacian Operator

08-27

GNN - Graph Laplacian Operator/Matrix

08-27

Autoregression vs. Diffusion

03-24

Discrete Diffusion

03-23

Three Road Diffusion

03-23

Diffusion Theory for Gaussian Mixture Model

03-23

Three Road Diffusion

03-23

Stanford AI- Diffusion Lecture

03-18

Generative AI- Diffusion Lecture

01-18

Generative AI- Diffusion Lecture

01-18

Generative AI- Stable Diffusion

02-07

Generative AI- Stable Diffusion

02-07

Deep Learning using Nonequilibrium Thermodynamics

02-07

Graph Matrix Representation Applications

01-30

二次式和正定矩陣 Quadratic Form and Positive Definite Matrix

01-28

Graph and Eigenvalue

01-28

Graph Machine Learning - Laplacian Operator

08-27

GNN - Graph Laplacian Operator/Matrix

08-27

Julia Code Snip

09-20

Math Stat I - Likelihood, Score Function, and Fisher Information

09-17

Math AI - Rectified Flow (ReFlow)

06-23

Math AI - Expand Score Matching to Flow Matching

06-15

Math AI - Gaussian Flow

06-08

Math AI - Fuse Flow and Diffusion

06-05

Math AI - Improve Flow Matching

06-02

Math AI - ODE Relationship to Thermodynamics

05-26

Math AI - SDE_ODE_Flow_Diffusion

05-25

Math AI - Expand Score Matching to Flow Matching

05-15

Math AI - Diffusion Acceleration Phases

05-10

Math AI - Expand Score Matching to Flow Matching

05-05

Math AI - Normalizing Flow

05-05

Math AI - Expand Score Matching to Flow Matching

05-05

Generation via Flow Model

03-06

Gaussian Invariant

03-02

DeepSeek R1 On Naive Bayes and Logistic Regression

02-16

Math AI - Score Matching is All U Need for Diffusion

02-02

Math Stat I - Likelihood, Score Function, and Fisher Information

02-01

Julia Code Snip

09-20

Math Stat I - Likelihood, Score Function, and Fisher Information

09-17

AI for Coding - Claude Codex Gemini CLI

11-27

AI for Coding - Cursor + LLM

08-24

AI for Coding - VS Code + Claude-3.5 Sonnet

08-24

Obsidian Plugin

08-09

Dynamic Data Crawler

10-14

Static Data Crawler

10-01

AI for AI (I) - Github Copilot

09-24

Math AI - Rectified Flow (ReFlow)

06-23

Math AI - Expand Score Matching to Flow Matching

06-15

Math AI - Gaussian Flow

06-08

Math AI - Fuse Flow and Diffusion

06-05

Math AI - Improve Flow Matching

06-02

Math AI - ODE Relationship to Thermodynamics

05-26

Math AI - SDE_ODE_Flow_Diffusion

05-25

Math AI - Expand Score Matching to Flow Matching

05-15

Math AI - Diffusion Acceleration Phases

05-10

Math AI - Expand Score Matching to Flow Matching

05-05

Math AI - Normalizing Flow

05-05

Math AI - Expand Score Matching to Flow Matching

05-05

Generation via Flow Model

03-06

Gaussian Invariant

03-02

DeepSeek R1 On Naive Bayes and Logistic Regression

02-16

Math AI - Score Matching is All U Need for Diffusion

02-02

Math Stat I - Likelihood, Score Function, and Fisher Information

02-01

Math Stat II - XYZ Entropy and XYZ Information

09-24

Math AI - Gaussian Flow

06-08

Three Road Diffusion

03-23

Gaussian Invariant

03-02

Generative AI- Diffusion Lecture

01-18

Math AI - 機率論或論機率？

07-19

Web Crawler or Scraper

10-16

Static Data Crawler

10-01

Dynamic Data Crawler

10-14

Static Data Crawler

10-01

Python Project Management - Testing

10-22

Python Project Management - Structure

10-07

馬克士威電磁方程和狹義相對論的相容性

10-09

馬克士威電磁方程和狹義相對論的相容性

10-09

馬克士威電磁方程和狹義相對論的相容性

10-09

Floating Point Representation

11-10

如何避免 Softmax overflow or underflow

11-07

BF16 Vs. FP16 overflow or underflow

10-09

如何避免 normalized L2-norm or layer norm FP16 overflow or underflow

10-09

如何避免 L2-norm or layer norm FP16 overflow or underflow

10-09

BF16 Vs. FP16 overflow or underflow

10-09

如何避免 normalized L2-norm or layer norm FP16 overflow or underflow

10-09

如何避免 L2-norm or layer norm FP16 overflow or underflow

10-09

BF16 Vs. FP16 overflow or underflow

10-09

如何避免 normalized L2-norm or layer norm FP16 overflow or underflow

10-09

如何避免 L2-norm or layer norm FP16 overflow or underflow

10-09

如何避免 Softmax overflow or underflow

11-07

BF16 Vs. FP16 overflow or underflow

10-09

如何避免 normalized L2-norm or layer norm FP16 overflow or underflow

10-09

如何避免 L2-norm or layer norm FP16 overflow or underflow

10-09

如何避免 Softmax overflow or underflow

11-07

BF16 Vs. FP16 overflow or underflow

10-09

如何避免 normalized L2-norm or layer norm FP16 overflow or underflow

10-09

如何避免 L2-norm or layer norm FP16 overflow or underflow

10-09

Web Crawler or Scraper

10-16

Web Crawler or Scraper

10-16

Web Crawler or Scraper

10-16

Web Crawler or Scraper

10-16

如何避免 Softmax overflow or underflow

11-07

WSL Command

11-07

WSL Command

11-07

Floating Point Representation

11-10

Floating Point Representation

11-10

Floating Point Representation

11-10

Floating Point Representation

11-10

Git Revision Control

11-19

Git Revision Control

11-19

Coherent Optical Communication

11-19

Coherent Optical Communication

11-19

Geometric Algebra (GA) Introduction and Application

12-03

Geometric Algebra (GA) Introduction and Application

12-03

Geometric Algebra (GA) Introduction and Application

12-03

Field Theory Fundamental and Lagrangian

12-10

Field Theory Fundamental and Lagrangian

12-10

Field Theory Fundamental and Lagrangian

12-10

Lagrangian and Hamiltonian Mechanics

11-09

無所不在的拉格朗日 - Lagrangian Everywhere

05-16

Field Theory Fundamental and Lagrangian

12-10

From Quantum Mechanics to Classical Mechanics

11-17

Lagrangian and Hamiltonian Mechanics

11-09

Math AI - ODE Relationship to Thermodynamics

05-26

無所不在的拉格朗日 - Lagrangian Everywhere

05-16

Physics Informed ML/AI

03-03

Field Theory Fundamental and Lagrangian

12-10

無所不在的拉格朗日 - Lagrangian Everywhere

05-16

拉格朗日力學 - Lagrange Mechanics

04-13

Lin-Alg 矩陣分解

07-10

Information Theory Application

01-21

Information Theory For Source Compression

12-17

Information Theory

12-17

Eigen value decomposition (EVD) 和 Single value decomposition (SVD) 的幾何意義

12-17

Fundamental theorem of GA calculus

12-17

Eigen-vector 和 Eigen-bivector 的幾何意義

12-17

無所不在的拉格朗日 - Lagrangian Everywhere

12-17

無所不在的拉格朗日 - Lagrangian Everywhere

05-16

拉格朗日力學 - Lagrange Mechanics

04-13

Lin-Alg 矩陣分解

07-10

Information Theory Application

01-21

Information Theory For Source Compression

12-17

Information Theory

12-17

Eigen value decomposition (EVD) 和 Single value decomposition (SVD) 的幾何意義

12-17

Fundamental theorem of GA calculus

12-17

Eigen-vector 和 Eigen-bivector 的幾何意義

12-17

無所不在的拉格朗日 - Lagrangian Everywhere

12-17

From Quantum Mechanics to Classical Mechanics

11-17

Lagrangian and Hamiltonian Mechanics

11-09

無所不在的拉格朗日 - Lagrangian Everywhere

05-16

拉格朗日力學 - Lagrange Mechanics

04-13

曲率 Curvature

07-14

座標系不變 (invariant), 協變 (Covariant), 和逆變 (Contravariant)

06-25

Information Theory Application

01-21

Information Theory For Source Compression

12-17

Information Theory

12-17

Eigen value decomposition (EVD) 和 Single value decomposition (SVD) 的幾何意義

12-17

Fundamental theorem of GA calculus

12-17

Eigen-vector 和 Eigen-bivector 的幾何意義

12-17

無所不在的拉格朗日 - Lagrangian Everywhere

12-17

Fundamental theorem of GA calculus

12-17

Information Theory For Hash Code

01-23

Information Theory - Constrained Noiseless Channel Capacity

01-24

LLM Inference Efficiency

11-25

LLM Mamba Installation

07-20

LLM Mamba Installation

07-20

LLM Perplexity Benchmark

07-18

LLM Perplexity Benchmark

07-18

Coding of Perplexity of LLM

01-15

Perplexity of LLM

12-16

Wikitext and Alpaca Dataset

12-16

PicoGPT

09-17

RAG use LlamaIndex and LangChain

09-01

AI Scientist

08-15

Speculative RAG

08-15

MMLU Dataset and Performance

06-29

MMLU and MMLU Pro

06-21

MMLU on GPT

06-18

Ollama Llama3

06-16

Token Economy

06-15

Big Little LLMs Applications

06-13

LLM Temperature - 溫度和機率分佈的關係

06-12

Token and Embedding (詞元和嵌入)

06-10

World Model Comparison 世界模型技術路綫

06-02

Pesudo Code for GPT-4o

05-25

End-to-end 端到端模型

05-25

AI Agent 實例

05-12

LLM 如何協助撰寫論文

05-12

Why does diffusion work better than auto-regression?

05-07

大(語言)模型參數微調 PEFT

05-07

中文亂碼二分之一

05-03

中文編碼，亂碼，轉碼

04-21

Trans-tokenizer

04-08

Physics Informed ML/AI

03-03

Work

02-01

Whisper Fine Tune

01-20

Long Mistral

01-09

Streaming LLM

01-04

LLM Performance Benchmark

12-24

RAG + Long Context

12-22

Perplexity of LLM

12-19

Autoregressive Math Model

12-12

LLM 性能分析

12-09

LLM Lookahead Decode

12-04

Retrieval Augmented Generation - RAG

11-29

Attention As Graph

11-25

LLM Agent

11-12

LLM Prune

11-12

LLM KV Cache Memory and BW

10-29

LLM Toy Example

10-14

LLM App - Lang Chain

06-24

RLHF

04-09

Paper Study By Amazon Li Mu and Zhu

04-08

Matrix Multiplication and Tensor Decomposition (?)

04-04

推薦系統初探 Recommendation System Exploration

04-01

Semantic Search Query-Key-Value

03-22

Token and Embedding, Query-Key-Value

03-19

Mixed Language Output

03-05

Prompt for LLM

03-05

Next Word Prediction Us GPT

02-26

HuggingFace Transformer

02-26

Nano GPT

02-20

Generative AI- Stable Diffusion

02-07

AI Agent Applications

12-28

LLM CI/CD with Front-End Backend

12-01

AI for Coding - Claude Codex Gemini CLI

11-27

LLM Inference Efficiency

11-25

Claude Project Cross PC and Mac

08-13

LLM Mamba Installation

07-20

LLM Mamba Installation

07-20

LLM Perplexity Benchmark

07-18

LLM Perplexity Benchmark

07-18

Linear Attention Math Framework

07-03

From RNN to Linear Attention to Mamba

03-24

DeepSeek R1 On Naive Bayes and Logistic Regression

02-16

Coding of Perplexity of LLM

01-15

Test or Inference Time Compute

01-01

Max Sequence Length in LLM

12-27

Perplexity of LLM

12-16

Wikitext and Alpaca Dataset

12-16

Sky (Symmetric) Transformer

12-08

Symmetric Transformer

12-08

Differential Transformer

12-08

Attention as Kernel and Random Features

12-05

Attention as Kernel and Random Features

11-27

LLM Instability

11-23

How to Improve LLM Error Resillence

11-23

Causal Attention Kernel Code

11-22

Linear Attention Vs. Mamba

11-17

Causal Attention Kernel

11-17

Linear Attention with Topological Masking

11-17

Attention as SVM Kernel Interpretation

11-11

Hashing and Locality Sensitive Hashing

11-10

Large Multimodality Model

11-04

Efficient (Still) Transformer

10-28

大(語言)模型推理效能

10-27

Attention as SVM Kernel Interpretation

10-27

RAG Framework

10-20

Llama3 70B Distributed Inference Code

10-19

Llama3 70B Distributed Inference

10-18

Linear Attention

10-11

Linear Attention

10-11

Attention 數學結構

10-10

PicoGPT

09-17

Long Context Output

09-07

NIM - Nvidia Inference Microservce

09-02

RAG use LlamaIndex and LangChain

09-01

LLM - 加速 : Prompt Lookup Decode Coding

08-20

LLM - 加速 : Prompt Lookup Decode

08-19

AI Scientist

08-15

Speculative RAG

08-15

LLM Adaptation

08-14

Graph RAG Coding

08-13

Obsidian Plugin

08-09

Edge AI

08-09

Hybrid AI

08-08

LLM 趨勢

08-03

RAG vs. Long Context vs. Fine-tuning

07-29

Graph RAG

07-28

Less is More, But Scale Matters

07-24

HuggingFace LLM

06-29

MMLU Dataset and Performance

06-29

MMLU and MMLU Pro

06-21

MMLU on GPT

06-18

Ollama Llama3

06-16

Token Economy

06-15

Big Little LLMs Applications

06-13

LLM Temperature - 溫度和機率分佈的關係

06-12

Token and Embedding (詞元和嵌入)

06-10

World Model Comparison 世界模型技術路綫

06-02

Pesudo Code for GPT-4o

05-25

End-to-end 端到端模型

05-25

AI Agent 實例

05-12

LLM 如何協助撰寫論文

05-12

Why does diffusion work better than auto-regression?

05-07

大(語言)模型參數微調 PEFT

05-07

中文亂碼二分之一

05-03

大語言和自然語言處理的差異

05-01

中文編碼，亂碼，轉碼

04-21

Hyena Vs. Transformer

04-12

Trans-tokenizer

04-08

HuggingFace Dataset and Pytorch Dataset I

04-03

HuggingFace Dataset and Pytorch Dataset I

04-03

HuggingFace Tokenizer Function

03-20

Physics Informed ML/AI

03-03

LLM Tokenizer Code

02-21

Makemore Karpathy Code

02-20

LLM MoE Toy Example

02-06

Work

02-01

Mamba Vs. Transformer

01-28

Whisper Fine Tune

01-20

Long Mistral

01-09

Streaming LLM

01-04

LLM Performance Benchmark

12-24

Llama Quantization

12-23

RAG + Long Context

12-22

Perplexity of LLM

12-19

LLM KV Cache Code

12-16

Autoregressive Math Model

12-12

LLM - 加速 : Medusa on GPU with Limited Memory

12-10

LLM 性能分析

12-09

Speculative Decode

12-04

LLM Lookahead Decode

12-04

LLM Tokenizer

12-02

Retrieval Augmented Generation - RAG

11-29

Llama with CPP

11-26

Attention As Graph

11-25

LLM Agent

11-12

LLM Prune

11-12

LLM 計算量分析

11-04

LLM KV Cache Memory and BW

10-29

LLM 記憶體分析

10-21

LLM Toy Example

10-14

Long Context

10-14

LLM App - Lang Chain

06-24

Flash Attention

06-20

XYZ Is All You Need Rationale

04-09

RLHF

04-09

Paper Study By Amazon Li Mu and Zhu

04-08

Matrix Multiplication and Tensor Decomposition (?)

04-04

推薦系統初探 Recommendation System Exploration

04-01

LLM 三部曲 Part I Foundation Model

03-26

Semantic Search Using Query-Key Similarity

03-22

Generative AI Fine Tune

03-22

Semantic Search Query-Key-Value

03-22

Token and Embedding, Query-Key-Value

03-19

Mixed Language Output

03-05

Prompt for LLM

03-05

Next Word Prediction Us GPT

02-26

HuggingFace Transformer

02-26

Nano GPT

02-20

Generative AI- Stable Diffusion

02-07

Linear Attention Math Framework

07-03

From RNN to Linear Attention to Mamba

03-24

Perplexity of LLM

12-16

Wikitext and Alpaca Dataset

12-16

Sky (Symmetric) Transformer

12-08

Symmetric Transformer

12-08

Differential Transformer

12-08

Attention as Kernel and Random Features

12-05

Attention as Kernel and Random Features

11-27

LLM Instability

11-23

How to Improve LLM Error Resillence

11-23

Causal Attention Kernel Code

11-22

Linear Attention Vs. Mamba

11-17

Causal Attention Kernel

11-17

Linear Attention with Topological Masking

11-17

VS Code on Colab

11-14

Performer Pytorch Code Analysis

11-13

Attention as SVM Kernel Interpretation

11-11

Attention as SVM Kernel Interpretation

10-27

Llama3 70B Distributed Inference Code

10-19

Llama3 70B Distributed Inference

10-18

Linear Attention

10-11

Linear Attention

10-11

Attention 數學結構

10-10

LLM KV Cache Code

12-16

Attention As Graph

11-25

LLM 計算量分析

11-04

LLM KV Cache Memory and BW

10-29

LLM 記憶體分析

10-21

Flash Attention

06-20

XYZ Is All You Need Rationale

04-09

LLM 三部曲 Part I Foundation Model

03-26

Semantic Search Using Query-Key Similarity

03-22

Semantic Search Query-Key-Value

03-22

Self Attention of GPT 圖解

02-18

LLM 計算量分析

11-04

XYZ Is All You Need Rationale

04-09

Self Attention of GPT 圖解

02-18

Next Word Prediction Us GPT

02-26

HuggingFace Transformer

02-26

LLM - 加速 : Prompt Lookup Decode Coding

08-20

LLM - 加速 : Prompt Lookup Decode

08-19

AI Scientist

08-15

Speculative RAG

08-15

HuggingFace LLM

06-29

MMLU Dataset and Performance

06-29

MMLU and MMLU Pro

06-21

MMLU on GPT

06-18

Ollama Llama3

06-16

Token Economy

06-15

Big Little LLMs Applications

06-13

LLM Temperature - 溫度和機率分佈的關係

06-12

Token and Embedding (詞元和嵌入)

06-10

World Model Comparison 世界模型技術路綫

06-02

Pesudo Code for GPT-4o

05-25

End-to-end 端到端模型

05-25

AI Agent 實例

05-12

LLM 如何協助撰寫論文

05-12

Why does diffusion work better than auto-regression?

05-07

大(語言)模型參數微調 PEFT

05-07

中文亂碼二分之一

05-03

中文編碼，亂碼，轉碼

04-21

Hyena Vs. Transformer

04-12

Trans-tokenizer

04-08

HuggingFace Dataset and Pytorch Dataset I

04-03

HuggingFace Dataset and Pytorch Dataset I

04-03

HuggingFace Tokenizer Function

03-20

Physics Informed ML/AI

03-03

LLM Tokenizer Code

02-21

Work

02-01

Mamba Vs. Transformer

01-28

Whisper Fine Tune

01-20

Long Mistral

01-09

Streaming LLM

01-04

Llama Quantization

12-23

RAG + Long Context

12-22

Perplexity of LLM

12-19

Autoregressive Math Model

12-12

LLM 性能分析

12-09

Speculative Decode

12-04

LLM Lookahead Decode

12-04

LLM Tokenizer

12-02

Retrieval Augmented Generation - RAG

11-29

Llama with CPP

11-26

LLM Agent

11-12

LLM Prune

11-12

LLM Toy Example

10-14

LLM App - Lang Chain

06-24

RLHF

04-09

Paper Study By Amazon Li Mu and Zhu

04-08

Matrix Multiplication and Tensor Decomposition (?)

04-04

推薦系統初探 Recommendation System Exploration

04-01

Token and Embedding, Query-Key-Value

03-19

Mixed Language Output

03-05

Prompt for LLM

03-05

Efficient (Still) Transformer

10-28

大(語言)模型推理效能

10-27

RAG use LlamaIndex and LangChain

09-01

Speculative RAG

08-15

MMLU Dataset and Performance

06-29

MMLU and MMLU Pro

06-21

MMLU on GPT

06-18

Ollama Llama3

06-16

Token Economy

06-15

Big Little LLMs Applications

06-13

LLM Temperature - 溫度和機率分佈的關係

06-12

Token and Embedding (詞元和嵌入)

06-10

World Model Comparison 世界模型技術路綫

06-02

Pesudo Code for GPT-4o

05-25

End-to-end 端到端模型

05-25

AI Agent 實例

05-12

LLM 如何協助撰寫論文

05-12

Why does diffusion work better than auto-regression?

05-07

大(語言)模型參數微調 PEFT

05-07

中文亂碼二分之一

05-03

中文編碼，亂碼，轉碼

04-21

Trans-tokenizer

04-08

Physics Informed ML/AI

03-03

Whisper Fine Tune

01-20

Long Mistral

01-09

Streaming LLM

01-04

LLM Performance Benchmark

12-24

Llama Quantization

12-23

RAG + Long Context

12-22

Perplexity of LLM

12-19

Autoregressive Math Model

12-12

LLM 性能分析

12-09

Speculative Decode

12-04

LLM Lookahead Decode

12-04

Retrieval Augmented Generation - RAG

11-29

LLM Agent

11-12

LLM Prune

11-12

LLM 計算量分析

11-04

LLM Toy Example

10-14

LLM App - Lang Chain

06-24

RLHF

04-09

Paper Study By Amazon Li Mu and Zhu

04-08

Matrix Multiplication and Tensor Decomposition (?)

04-04

推薦系統初探 Recommendation System Exploration

04-01

Token and Embedding, Query-Key-Value

03-19

Mixed Language Output

03-05

Prompt for LLM

03-05

LLM Perplexity Benchmark

07-18

Coding of Perplexity of LLM

01-15

Token Economy

06-15

Token and Embedding (詞元和嵌入)

06-10

文本分類 - IMDB 意見分析

05-01

大語言和自然語言處理的差異

05-01

Trans-tokenizer

04-08

HuggingFace Dataset and Pytorch Dataset I

04-03

HuggingFace Tokenizer Function

03-20

LLM Tokenizer Code

02-21

LLM Tokenizer

12-02

Token and Embedding, Query-Key-Value

03-19

Token Economy

06-15

Token and Embedding (詞元和嵌入)

06-10

Trans-tokenizer

04-08

HuggingFace Dataset and Pytorch Dataset I

04-03

HuggingFace Tokenizer Function

03-20

LLM Tokenizer Code

02-21

LLM Tokenizer

12-02

Token and Embedding, Query-Key-Value

03-19

Generative AI Fine Tune

03-22

LLM Adaptation

08-14

RAG vs. Long Context vs. Fine-tuning

07-29

Generative AI Fine Tune

03-22

Generative AI Fine Tune

03-22

Generative AI Fine Tune

03-22

XYZ Is All You Need Rationale

04-09

Optimization - Proxmial Gradient Descent

05-21

Math Optimization - PPO

05-11

Optimization - Gradient Descent

05-11

Math AI - Optimization II

05-01

Math Optimization - Convex Optimization

05-01

Math Optimization - Conjugate Convex

05-01

Math AI - Stochastic Differential Equation Forward

05-01

Math AI - Diffusion vs. SDE

05-01

Math AI - Stochastic Differential Equation Backward

04-29

Math AI - Stochastic Differential Equation

04-16

無限旅館悖論

02-08

Math - 積分

04-16

Math - 積分

04-16

無限旅館悖論

02-08

Math - 積分

04-16

Optimization - Proxmial Gradient Descent

05-21

Math Optimization - PPO

05-11

Optimization - Gradient Descent

05-11

Math AI - Optimization II

05-01

Math Optimization - Convex Optimization

05-01

Math Optimization - Conjugate Convex

05-01

Math AI - Stochastic Differential Equation Forward

05-01

Math AI - Diffusion vs. SDE

05-01

Math AI - Stochastic Differential Equation Backward

04-29

Optimization - Proxmial Gradient Descent

05-21

Math Optimization - PPO

05-11

Optimization - Gradient Descent

05-11

Math AI - Optimization II

05-01

Math Optimization - Convex Optimization

05-01

Math Optimization - Conjugate Convex

05-01

Math AI - Stochastic Differential Equation Forward

05-01

Math AI - Diffusion vs. SDE

05-01

Math AI - Stochastic Differential Equation Backward

04-29

Optimization - Proxmial Gradient Descent

05-21

Math Optimization - PPO

05-11

Optimization - Gradient Descent

05-11

Math AI - Optimization II

05-01

Math Optimization - Convex Optimization

05-01

Math Optimization - Conjugate Convex

05-01

Math AI - Stochastic Differential Equation Forward

05-01

Math AI - Diffusion vs. SDE

05-01

Math AI - Stochastic Differential Equation Backward

04-29

Optimization - Proxmial Gradient Descent

05-21

Math Optimization - PPO

05-11

Optimization - Gradient Descent

05-11

Math AI - Optimization II

05-01

Math Optimization - Convex Optimization

05-01

Math Optimization - Conjugate Convex

05-01

Math AI - Stochastic Differential Equation Forward

05-01

Math AI - Diffusion vs. SDE

05-01

Math AI - Stochastic Differential Equation Backward

04-29

Quantum mechanics is just thermodynamics in imaginary time.

07-15

Gauss-Bonnet Theorem

07-07

曲率

06-23

微積分基本定理

03-30

複分析 and 複幾何

03-30

可視微分幾何

03-30

曲率 Curvature

07-14

張量分析

07-12

直綫和測地綫 geodesic

07-12

非歐幾何

07-12

平行公理和平行移動 Parallel Postulate and Parallel Transport

07-12

Connection and Covariant Derivative？

07-09

五次方程式無根式解

07-02

座標系不變 (invariant), 協變 (Covariant), 和逆變 (Contravariant)

06-25

Optimization - NN Optimization

06-19

Optimization - Manifold Gradient Descent

06-03

Optimization - Accelerate Gradient Descent

06-03

Test or Inference Time Compute

01-01

Optimization - NN Optimization

06-19

Optimization - Manifold Gradient Descent

06-03

Optimization - Accelerate Gradient Descent

06-03

Optimization - Manifold Gradient Descent

06-03

LLM KV Cache Memory and BW

10-29

LLM 記憶體分析

10-21

Long Context

10-14

Flash Attention

06-20

Quantum mechanics is just thermodynamics in imaginary time.

07-15

Gauss-Bonnet Theorem

07-07

曲率

06-23

微積分基本定理

03-30

複分析 and 複幾何

03-30

可視微分幾何

03-30

曲率 Curvature

07-14

張量分析

07-12

直綫和測地綫 geodesic

07-12

非歐幾何

07-12

平行公理和平行移動 Parallel Postulate and Parallel Transport

07-12

Connection and Covariant Derivative？

07-09

五次方程式無根式解

07-02

座標系不變 (invariant), 協變 (Covariant), 和逆變 (Contravariant)

06-25

Quantum mechanics is just thermodynamics in imaginary time.

07-15

Gauss-Bonnet Theorem

07-07

曲率

06-23

微積分基本定理

03-30

複分析 and 複幾何

03-30

可視微分幾何

03-30

張量分析

07-12

非歐幾何

07-12

Connection and Covariant Derivative？

07-09

五次方程式無根式解

07-02

座標系不變 (invariant), 協變 (Covariant), 和逆變 (Contravariant)

06-25

Lin-Alg 矩陣分解

07-10

Lin-Alg 矩陣分解

07-10

曲率 Curvature

07-14

直綫和測地綫 geodesic

07-12

平行公理和平行移動 Parallel Postulate and Parallel Transport

07-12

Long Context Output

09-07

LLM 趨勢

08-03

Long Context

10-14

LLM KV Cache Code

12-16

LLM KV Cache Memory and BW

10-29

LLM KV Cache Code

12-16

LLM KV Cache Memory and BW

10-29

AI Agent Applications

12-28

Hashing and Locality Sensitive Hashing

11-10

Large Multimodality Model

11-04

LLM 趨勢

08-03

AI Agent 實例

05-12

LLM Agent

11-12

LLM Inference Efficiency

11-25

LLM Mamba Installation

07-20

LLM Mamba Installation

07-20

LLM Perplexity Benchmark

07-18

LLM Perplexity Benchmark

07-18

Coding of Perplexity of LLM

01-15

Perplexity of LLM

12-16

Wikitext and Alpaca Dataset

12-16

Attention As Graph

11-25

Llama3 70B Distributed Inference Code

10-19

Llama3 70B Distributed Inference

10-18

HuggingFace LLM

06-29

Llama with CPP

11-26

LLM Tokenizer Code

02-21

LLM Tokenizer

12-02

LLM Tokenizer

12-02

LLM - 加速 : Prompt Lookup Decode Coding

08-20

LLM - 加速 : Prompt Lookup Decode

08-19

LLM - 加速 : Medusa on GPU with Limited Memory

12-10

Speculative Decode

12-04

LLM - 加速 : Prompt Lookup Decode Coding

08-20

LLM - 加速 : Prompt Lookup Decode

08-19

LLM - 加速 : Medusa on GPU with Limited Memory

12-10

Speculative Decode

12-04

LLM - 加速 : Medusa on GPU with Limited Memory

12-10

LLM - 加速 : Medusa on GPU with Limited Memory

12-10

RAG Framework

10-20

RAG use LlamaIndex and LangChain

09-01

Speculative RAG

08-15

LLM Adaptation

08-14

Graph RAG Coding

08-13

RAG vs. Long Context vs. Fine-tuning

07-29

Graph RAG

07-28

RAG + Long Context

12-22

RAG Framework

10-20

RAG use LlamaIndex and LangChain

09-01

Speculative RAG

08-15

Graph RAG Coding

08-13

RAG vs. Long Context vs. Fine-tuning

07-29

Graph RAG

07-28

RAG + Long Context

12-22

AI Markdown Editor

02-04

簡單文本編輯器

01-06

AI Markdown Editor

02-04

簡單文本編輯器

01-06

LLM Mamba Installation

07-20

LLM Mamba Installation

07-20

Linear Attention Vs. Mamba

11-17

Mamba Vs. Transformer

01-28

LLM Mamba Installation

07-20

LLM Mamba Installation

07-20

Linear Attention Vs. Mamba

11-17

Mamba Vs. Transformer

01-28

RAG use LlamaIndex and LangChain

09-01

AI for AI (II) - Jupyter-ai

02-07

無限旅館悖論

02-08

Transformer Layer Normalization Placement

10-04

Batch Normalization vs Layer Normalization

10-03

ML Normalization

02-14

Hyena Vs. Transformer

04-12

Acceptance-Rejection Sampling 接受拒絕採樣

05-26

考拉兹猜想

05-25

Curse or Bless of Dimensionality

07-18

Math AI - 機率論或論機率？

07-19

Less is More, But Scale Matters

07-24

Math AI - 機率論或論機率？

07-19

LLM 趨勢

08-03

LLM 趨勢

08-03

Hashing and Locality Sensitive Hashing

11-10

Large Multimodality Model

11-04

LLM 趨勢

08-03

NIM - Nvidia Inference Microservce

09-02

Edge AI

08-09

Hybrid AI

08-08

Obsidian Plugin

08-09

Test Obsidian Dataview Plugin

08-08

Obsidian Plugin

08-09

AI Nonlinear History

11-03

AI Evolution

08-15

AI Nonlinear History

11-03

AI Evolution

08-15

AI Nonlinear History

11-03

AI Evolution

08-15

LLM - 加速 : Prompt Lookup Decode Coding

08-20

LLM - 加速 : Prompt Lookup Decode

08-19

AI for Coding - Claude Codex Gemini CLI

11-27

Claude Project Cross PC and Mac

08-13

Cross Platform Python Project Management

07-31

AI for Coding - Cursor + LLM

08-24

AI for Coding - VS Code + Claude-3.5 Sonnet

08-24

AI for Coding - Cursor + LLM

08-24

RAG use LlamaIndex and LangChain

09-01

RAG use LlamaIndex and LangChain

09-01

AI Model Sparsity Pruning Compression

09-03

AI Model Sparsity Pruning Compression

09-03

Long Context Output

09-07

PicoGPT

09-17

PicoGPT

09-17

Radar Introduction

09-28

Radar Introduction

09-28

PN Junction vs. Neuron Membrane

10-13

Llama3 70B Distributed Inference Code

10-19

Llama3 70B Distributed Inference

10-18

RAG Framework

10-20

RAG Framework

10-20

Linear Attention Math Framework

07-03

From RNN to Linear Attention to Mamba

03-24

Attention as Kernel and Random Features

12-05

Attention as Kernel and Random Features

11-27

LLM Instability

11-23

How to Improve LLM Error Resillence

11-23

Causal Attention Kernel Code

11-22

Linear Attention Vs. Mamba

11-17

Causal Attention Kernel

11-17

Linear Attention with Topological Masking

11-17

VS Code on Colab

11-14

Performer Pytorch Code Analysis

11-13

Attention as SVM Kernel Interpretation

11-11

Attention as SVM Kernel Interpretation

10-27

Attention as Kernel and Random Features

12-05

Attention as Kernel and Random Features

11-27

Attention as SVM Kernel Interpretation

10-27

Linear Attention Math Framework

07-03

From RNN to Linear Attention to Mamba

03-24

LLM Instability

11-23

How to Improve LLM Error Resillence

11-23

Causal Attention Kernel Code

11-22

Linear Attention Vs. Mamba

11-17

Causal Attention Kernel

11-17

Linear Attention with Topological Masking

11-17

Linear Attention Math Framework

07-03

From RNN to Linear Attention to Mamba

03-24

LLM Instability

11-23

How to Improve LLM Error Resillence

11-23

Causal Attention Kernel Code

11-22

Linear Attention Vs. Mamba

11-17

Causal Attention Kernel

11-17

Linear Attention with Topological Masking

11-17

LLM Inference Efficiency

11-25

LLM Mamba Installation

07-20

LLM Mamba Installation

07-20

LLM Perplexity Benchmark

07-18

LLM Perplexity Benchmark

07-18

Linear Attention Math Framework

07-03

From RNN to Linear Attention to Mamba

03-24

Coding of Perplexity of LLM

01-15

LLM Perplexity Benchmark

07-18

Coding of Perplexity of LLM

01-15

Math AI - Rectified Flow (ReFlow)

06-23

Math AI - Expand Score Matching to Flow Matching

06-15

Math AI - Gaussian Flow

06-08

Math AI - Fuse Flow and Diffusion

06-05

Math AI - Improve Flow Matching

06-02

Math AI - ODE Relationship to Thermodynamics

05-26

Math AI - SDE_ODE_Flow_Diffusion

05-25

Math AI - Expand Score Matching to Flow Matching

05-15

Math AI - Diffusion Acceleration Phases

05-10

Math AI - Expand Score Matching to Flow Matching

05-05

Math AI - Normalizing Flow

05-05

Math AI - Expand Score Matching to Flow Matching

05-05

Generation via Flow Model

03-06

Gaussian Invariant

03-02

DeepSeek R1 On Naive Bayes and Logistic Regression

02-16

Math AI - Score Matching is All U Need for Diffusion

02-02

Math Stat I - Likelihood, Score Function, and Fisher Information

02-01

Math AI - Rectified Flow (ReFlow)

06-23

Math AI - Expand Score Matching to Flow Matching

06-15

Math AI - Gaussian Flow

06-08

Math AI - Fuse Flow and Diffusion

06-05

Math AI - Improve Flow Matching

06-02

Math AI - ODE Relationship to Thermodynamics

05-26

Math AI - SDE_ODE_Flow_Diffusion

05-25

Math AI - Expand Score Matching to Flow Matching

05-15

Math AI - Diffusion Acceleration Phases

05-10

Math AI - Expand Score Matching to Flow Matching

05-05

Math AI - Normalizing Flow

05-05

Math AI - Expand Score Matching to Flow Matching

05-05

Generation via Flow Model

03-06

Gaussian Invariant

03-02

DeepSeek R1 On Naive Bayes and Logistic Regression

02-16

Math AI - Score Matching is All U Need for Diffusion

02-02

Math Stat I - Likelihood, Score Function, and Fisher Information

02-01

Hole Detection

01-14

AI Coach for Bouldering Project2

10-05

AI Coach for Bouldering Project

05-01

Hole Detection

01-14

AI Coach for Bouldering Project2

10-05

AI Coach for Bouldering Project

05-01

Math AI - SDE_ODE_Flow_Diffusion

05-25

Math AI - ODE Relationship to Thermodynamics

05-26

Cross Platform Python Project Management

07-31

AI SfM - DUSt3r, MASt3r, MONSt3r

10-07

Structure from Motion

10-06

AI SfM - DUSt3r, MASt3r, MONSt3r

10-07

Structure from Motion

10-06

From Quantum Mechanics to Classical Mechanics

11-17

Recent M&A Rationale and Commonality v2 and slides

12-26

Recent M&A Rationale and Commonality

12-17

Recent M&A Rationale and Commonality v2 and slides

12-26

Recent M&A Rationale and Commonality

12-17

Recent M&A Rationale and Commonality v2 and slides

12-26

Recent M&A Rationale and Commonality

12-17

Learning Japanese Grammar

01-03

Learning Japanese

12-20

Learning Japanese

12-20

AI Agent Applications

12-28