LLM / Multimodal
1
LLM Attention (with Code)
2
KAMF : Kafka-A2A-MCP-Flink
3
Agent's Memory: Knowledge Graph Memory MCP Server, Memory OS of AI Agent
4
VLM : Models Summary (unfinished post: 0618 update)
5
Prompt Engineering
6
GraphRAG (Microsoft)
7
What's different? : Agent, Agentic AI, Multi-Agent, Agentic RAG
8
DeepSeek-V3
9
Meta-Chunking: Learning Efficient Text Segmentation via Logical Perception
10
RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation
11
🚶➡Generative Agents: Interactive Simulacra of Human Behavior
12
Entropix : Entropy Based Sampling and Parallel CoT Decoding
13
Speculative Decoding
14
Vision : Self-Attention vs. Cross-Attention
15
Semantic Entropy: Summary of Two Papers on LLM Hallucination Detection 😱
16
LLaMa 3.1
17
MoE, MoA
18
Merge algorithms
19
Key-Value caching
20
DocLLM: A layout-aware generative language model for multimodal document understanding
21
VLM : Architecture / Fusion Methods
22
VLM : Applications
23
LLaVA : Visual Instruction Tuning
24
LLaMa 3
25
Fine-tuning variations : RLHF/PPO, DPO, ORPO
26
RAG : Embedding Model, Reranking Model
27
RAG : Similarity search (Keyword Search, Semantic Search, Hybrid Search)
28
RAG : Query Transformation/ Query Routing
29
RAG(Retrieval-Augmented Generation)
30
Mistral 7B
31
LLAMA 2: Open Foundation and Fine-Tuned Chat Models
32
Quentization basic
33
PEFT : Parameter-Efficient Finetuning methods
34
About Fine-tuning
35
LLM Architecture
36
Multimodal Learning with Transformers : A Survey
37
ㅡ
