Personal archive

Notes on language and AI. Language models and multimodal AI(01),
NLP and machine learning(02),
and linguistics(03).

(01) MODELS

Model architecture, fine-tuning, inference, RAG, and agents.

(02) NLP

Embeddings, Transformers, prompt-based learning, and machine learning basics.

(03) LANGUAGE

Syntax, semantics, conversation analysis, and linguistic knowledge in models.

Categories

Latest posts by category ↓
01 / LLM & MULTIMODAL

LLM / Multimodal

Language models, multimodal models, RAG, and agents.

  1. REA (Reverse Engineer Anything)
  2. Decision Model: Jev, Kev
  3. LLM Attention (with Code)
  4. KAMF : Kafka-A2A-MCP-Flink
  5. Agent's Memory: Knowledge Graph Memory MCP Server, Memory OS of AI Agent
02 / NLP & MACHINE LEARNING

NLP

Notes on NLP, machine learning, and deep learning.

  1. Prompt-Based Learning 3 | P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks
  2. Prompt-Based Learning 2 | P-tuniung: GPT Understands, Too
  3. Prompt-Based Learning 1 | PET(Pattern Exploiting Training), iPET(Iterative Pattern Exploiting Training)
  4. Language Models Summary(unfinished post)
  5. DAPT-TAPT | Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks
03 / LINGUISTICS

NLP and Linguistics

Linguistics, language study, and linguistic analysis of models.

  1. Deutsch | Wendung2
  2. Deutsch | Wendung
  3. Coreference Resolution | Speech and Language Processing(Daniel Jurafsky and James H. Martin, 2019)
  4. Investigating BERT’s Knowledge of Language:Five Analysis Methods with NPIs(Warstadt et al.(2019))
  5. Long-Distance Dependency(LDD)
All categories FINDDME / A PERSONAL ARCHIVEBack to top ↑
https://pleasereadthisforme.github.io/https://finddme-jomul.github.io/