NexT
Home
Archives
Tags
Category
Highlight Test
07-19
Next Theme Tutorial
07-20
From Quantum Mechanics to Classical Mechanics
11-17
Lagrangian and Hamiltonian Mechanics
11-09
Linear Attention Math Framework
07-03
Math AI - ODE Relationship to Thermodynamics
05-26
無所不在的拉格朗日 - Lagrangian Everywhere
05-16
From RNN to Linear Attention to Mamba
03-24
Generative AI- Diffusion Lecture
01-18
Test or Inference Time Compute
01-01
Max Sequence Length in LLM
12-27
Wikitext and Alpaca Dataset
12-16
Advanced Packaging
12-10
Sky (Symmetric) Transformer
12-08
Attention as Kernel and Random Features
12-05
Hashing and Locality Sensitive Hashing
11-10
AI Nonlinear History
11-03
PN Junction vs. Neuron Membrane
10-13
Linear Attention
10-11
Attention 數學結構
10-10
Transformer Layer Normalization Placement
10-04
Batch Normalization vs Layer Normalization
10-03
Radar Introduction
09-28
Long Context Output
09-07
NIM - Nvidia Inference Microservce
09-02
AI for Coding - Cursor + LLM
08-24
AI Evolution
08-15
AI Scientist
08-15
Edge AI
08-09
Test Obsidian Dataview Plugin
08-08
Hybrid AI
08-08
Math AI - 演繹推理和合情推理
07-24
Math AI - 機率論或論機率？
07-19
Curse or Bless of Dimensionality
07-18
Quantum mechanics is just thermodynamics in imaginary time.
07-15
Gauss-Bonnet Theorem
07-07
MMLU Dataset and Performance
06-29
曲率
06-23
MMLU and MMLU Pro
06-21
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
End-to-end 端到端模型
05-25
LLM 如何協助撰寫論文
05-12
中文亂碼二分之一
05-03
文本分類 - IMDB 意見分析
05-01
拉格朗日力學 - Lagrange Mechanics
04-13
Hyena Vs. Transformer
04-12
HuggingFace Dataset and Pytorch Dataset I
04-03
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
Colab 使用方法
03-24
Physics Informed ML/AI
03-03
Makemore Karpathy Code
02-20
ML Normalization
02-14
無限旅館悖論
02-08
AI for AI (II) - Jupyter-ai
02-07
LLM MoE Toy Example
02-06
Work
02-01
Whisper Fine Tune
01-20
Long Mistral
01-09
LLM - 加速 : Medusa on GPU with Limited Memory
12-10
Retrieval Augmented Generation - RAG
11-29
LLM KV Cache Memory and BW
10-29
Long Context
10-14
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
Lin-Alg 矩陣分解
07-10
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
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 - 積分
04-16
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
Semantic Search Using Query-Key Similarity
03-22
Mixed Language Output
03-05
Next Word Prediction Us GPT
02-26
HuggingFace Transformer
02-26
Self Attention of GPT 圖解
02-18
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
Information Theory - Constrained Noiseless Channel Capacity
01-24
Information Theory For Hash Code
01-23
Information Theory Application
01-21
Information Theory for Noisy Communication
12-17
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
Field Theory Fundamental and Lagrangian
12-10
Geometric Algebra (GA) Introduction and Application
12-03
Coherent Optical Communication
11-19
Coherent Optical Communication
11-19
Floating Point Representation
11-10
WSL Command
11-07
如何避免 Softmax overflow or underflow
11-07
Web Crawler or Scraper
10-16
Web Crawler or Scraper
10-16
Dynamic Data Crawler
10-14
BF16 Vs. FP16 overflow or underflow
10-09
如何避免 normalized L2-norm or layer norm FP16 overflow or underflow
10-09
馬克士威電磁方程和狹義相對論的相容性
10-09
Static Data Crawler
10-01
Math Stat II - XYZ Entropy and XYZ Information
09-24
AI for AI (I) - Github Copilot
09-24
Math Stat I - Likelihood, Score Function, and Fisher Information
09-17
Graph Machine Learning - Laplacian Operator
08-27
GNN - Graph Laplacian Operator/Matrix
08-27
Geometric Deep Learning
08-19
vSLAM with NN
05-13
vSLAM with NN
05-13
vSLAM with NN
05-13
CV-SLAM Bundle Adjustment (BA)
04-23
Human Brain
04-23
CV-SLAM Feature Extraction - SIFT/SURF/ORB
04-16
vSLAM Introduction
04-15
A Unified View of Self-Supervised Learning (SSL)
04-05
SLAM Demystify
03-25
Parser From Scratch
02-01
Thermal Resistance
01-17
CV Super Resolution - AMD FSR
01-14
Computer Vision My Way
12-18
Computer Vision - HDR Network
12-02
Computer Vision - UNet from Autoencoder and FCN
11-19
Computer Vision - FRC and MEMC
11-13
Excel Link to MySQL
10-22
Math ML - Entropy and Mutual Information
10-10
HMM Triology (III) - EM Algorithm
10-09
Reinforcement Learning
09-29
Machine Learning Database
09-19
Math AI - Deterministic and Probabilistic?
09-19
跨平臺 Markdown Plus MathJax Blog Editing 分享
09-12
Math AI - Diffusion Generative Model Extended from VAE
08-30
Math ML - Maximum Likelihood Vs. Bayesian
08-17
Math AI - From EM to Variational Bayesian Inference
08-15
English
08-03
Math AI - ML Estimation To EM Algorithm For Hidden Data
06-30
Jekyll Memo for Github Blog
06-30
Typora and Mermaid
02-16
Math ML - Modified Softmax w/ Margin
01-16
增進工程師效率 Julia Linear Algebra
04-21
Edge AI Trilogy III - Model Compression
04-05
增進工程師效率 Python DataFrame - CSV & Plot
12-21
RNN
12-21
Poincare Theorem and Ricci Flow
12-21
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
AI Hand Pose and Tracking
04-01
Transformer for Speech Recognition
03-21
Vision Transformer
02-27
Neural Network and CV Optical Flow 算法
01-05
Improve Engineer Efficiency - Python Image Library
12-11
Computer Vision - CV Image Resize
12-02
Math AI G-CNN (Group + CNN)
05-08
AI for Coding - Claude Codex Gemini CLI
11-27
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
Coding of Perplexity of LLM
01-15
Causal Attention Kernel Code
11-22
VS Code on Colab
11-14
Performer Pytorch Code Analysis
11-13
Attention as SVM Kernel Interpretation
11-11
Large Multimodality Model
11-04
Llama3 70B Distributed Inference Code
10-19
AI Model Sparsity Pruning Compression
09-03
RAG use LlamaIndex and LangChain
09-01
LLM - 加速 : Prompt Lookup Decode Coding
08-20
LLM - 加速 : Prompt Lookup Decode
08-19
Graph RAG Coding
08-13
World Model Comparison 世界模型技術路綫
06-02
Why does diffusion work better than auto-regression?
05-07
中文編碼，亂碼，轉碼
04-21
LLM Tokenizer Code
02-21
VS Code for Jupyter
02-12
LLM KV Cache Code
12-16
Autoregressive Math Model
12-12
VS Code for WSL2
12-09
Speculative Decode
12-04
LLM Lookahead Decode
12-04
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
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
Julia Code Snip
09-20
VScode for Python and Julia
02-05
Math AI Flow and Flux PDE
01-16
Math AI - VAE Coding
09-29
Math AI - Variational Autoencoder Vs. Variational EM Algorithm
08-18
Learning Japanese Grammar
01-03
Learning Japanese
12-20
LLM CI/CD with Front-End Backend
12-01
Claude Project Cross PC and Mac
08-13
Cross Platform Python Project Management
07-31
Python Project Management - Minbpe
09-27
AI for Coding - VS Code + Claude-3.5 Sonnet
08-24
Obsidian Plugin
08-09
Test Obsidian Dataview Plugin
08-08
AI Coding 編程
03-23
AI Markdown Editor
02-04
簡單文本編輯器
01-06
Git Revision Control
11-19
Python Project Management - Testing
10-22
Python Project Management - Structure
10-07
Windows + ML CUDA - Anaconda / WSL2 / DirectML
08-13
Windows + CUDA - PyTorch and TensorFlow
09-25
AI Agent Applications
12-28
Gemini3 Slides
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
Perplexity of LLM
12-16
Symmetric Transformer
12-08
Differential Transformer
12-08
Attention as Kernel and Random Features
11-27
LLM Instability
11-23
How to Improve LLM Error Resillence
11-23
Linear Attention Vs. Mamba
11-17
Causal Attention Kernel
11-17
Linear Attention with Topological Masking
11-17
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
10-18
Linear Attention
10-11
PicoGPT
09-17
Speculative RAG
08-15
LLM Adaptation
08-14
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 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
Pesudo Code for GPT-4o
05-25
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
Trans-tokenizer
04-08
HuggingFace Dataset and Pytorch Dataset I
04-03
HuggingFace Tokenizer Function
03-20
Mamba Vs. Transformer
01-28
Streaming LLM
01-04
LLM Performance Benchmark
12-24
Llama Quantization
12-23
RAG + Long Context
12-22
Perplexity of LLM
12-19
LLM 性能分析
12-09
LLM Tokenizer
12-02
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 記憶體分析
10-21
LLM Toy Example
10-14
LLM App - Lang Chain
06-24
Flash Attention
06-20
LLM 三部曲 Part I Foundation Model
03-26
Generative AI Fine Tune
03-22
Semantic Search Query-Key-Value
03-22
Token and Embedding, Query-Key-Value
03-19
Prompt for LLM
03-05
Nano GPT
02-20
Generative AI- Stable Diffusion
02-07
Recent M&A Rationale and Commonality v2 and slides
12-26
Recent M&A Rationale and Commonality
12-17