Author

DeepHub IMBA

A must‑follow public account sharing practical AI insights. Follow now. internet + machine learning + big data + architecture = IMBA

Articles

Likes

Views

Comments

Latest from DeepHub IMBA

55 recent articles

DeepHub IMBA

Mar 25, 2026 · Artificial Intelligence

TPU Architecture and Pallas Kernels: From Memory Hierarchy to FlashAttention

This article explains why TPU programming differs from GPU, describes the explicit HBM‑VMEM‑register data movement required on TPU, introduces the Pallas grid‑BlockSpec‑Ref model, and walks through four progressively more complex kernels—including element‑wise add, tiled dot product, fused RMSNorm with scratch memory, and a production‑grade FlashAttention implementation—showing how each kernel maps to the TPU memory hierarchy and leverages Pallas features such as input_output_aliases and PrefetchScalarGridSpec.

FlashAttentionJAXMemory Hierarchy

0 likes · 20 min read

TPU Architecture and Pallas Kernels: From Memory Hierarchy to FlashAttention

DeepHub IMBA

Mar 24, 2026 · Backend Development

Dissecting the Tencent WeChat OpenClaw Plugin API and Recreating It in Pure Python

The article reverse‑engineers the @tencent‑weixin/openclaw‑weixin npm package to reveal the full ilink API (five POST JSON endpoints), explains hidden required fields, demonstrates a QR‑code login flow, and provides a complete 120‑line Python client that can send and receive messages reliably.

API reverse engineeringBotHTTP

0 likes · 17 min read

Dissecting the Tencent WeChat OpenClaw Plugin API and Recreating It in Pure Python

DeepHub IMBA

Mar 23, 2026 · Artificial Intelligence

How KgCoOp Uses Knowledge‑Guided Context Optimization to Prevent Prompt Tuning Forgetting

The article analyzes why standard prompt tuning (CoOp) causes catastrophic forgetting in visual‑language models, introduces the KgCoOp framework that adds a knowledge‑guided loss to regularize prompts, and shows through extensive experiments on 11 benchmarks that KgCoOp improves unseen‑class accuracy, harmonic mean, and efficiency while discussing trade‑offs and limitations.

Catastrophic ForgettingKnowledge-guided OptimizationPrompt Tuning

0 likes · 11 min read

How KgCoOp Uses Knowledge‑Guided Context Optimization to Prevent Prompt Tuning Forgetting

DeepHub IMBA

Mar 22, 2026 · Artificial Intelligence

Four Numeric Scaling Techniques: When to Use Standard, Robust, Power, and Min‑Max

This article explains why numeric feature engineering is essential for machine‑learning models, outlines the two main challenges of differing magnitudes and outliers, and demonstrates four scaling methods—StandardScaler, RobustScaler, PowerTransformer, and MinMaxScaler—using the California housing dataset, complete with code, visualizations, and guidance on when each method is appropriate.

feature scalingmin-max scalingpower transformer

0 likes · 13 min read

Four Numeric Scaling Techniques: When to Use Standard, Robust, Power, and Min‑Max

DeepHub IMBA

Mar 21, 2026 · Backend Development

9 Python libraries that dramatically improve production‑code quality

This article introduces nine third‑party Python libraries—glom, boltons, beartype, result, whenever, pyinstrument, dirty‑equals, stamina, and pyfunctional—that address recurring pain points such as nested data access, missing stdlib features, runtime type safety, error handling, timezone bugs, performance profiling, testing assertions, retry logic, and data pipelines, showing concrete code examples and practical benefits.

Pythonbeartypedirty-equals

0 likes · 15 min read

9 Python libraries that dramatically improve production‑code quality

DeepHub IMBA

Mar 20, 2026 · Artificial Intelligence

Claude Code Command System Explained: 3 Types, 7 Categories, 50+ Commands

This article provides a comprehensive guide to Claude Code’s command system, covering all slash commands, CLI flags, keyboard shortcuts, hidden features, and practical workflows, showing how to initialize projects, manage context, switch models, control costs, and automate development tasks efficiently.

AI coding assistantCLIClaude Code

0 likes · 29 min read

Claude Code Command System Explained: 3 Types, 7 Categories, 50+ Commands

DeepHub IMBA

Mar 19, 2026 · Artificial Intelligence

Understanding Agent Memory: From Stateless LLMs to Persistent Multi‑Layer Architecture

The article analyzes why large language models are inherently stateless, outlines a four‑layer memory architecture for AI agents—including working, situational, semantic, and procedural memory—and explains write, retrieval, and forgetting mechanisms along with current tooling such as Mem0 and Letta.

Agent MemoryLLMLetta

0 likes · 9 min read

Understanding Agent Memory: From Stateless LLMs to Persistent Multi‑Layer Architecture

DeepHub IMBA

Mar 18, 2026 · Artificial Intelligence

CRAG Architecture Explained: Fixing Erroneous Retrieval Results Before the Generator

The article analyzes how most RAG pipelines blindly feed retrieved documents to LLMs, introduces CRAG's lightweight evaluator with confidence thresholds, describes its sentence‑level decomposition, filtering, and dual‑knowledge routing, and provides a full implementation walkthrough with a real insurance query example.

CRAGFAISSLLM

0 likes · 13 min read

CRAG Architecture Explained: Fixing Erroneous Retrieval Results Before the Generator

DeepHub IMBA

Mar 17, 2026 · Artificial Intelligence

Advanced RAG Techniques: Boosting Retrieval with Query Translation and Decomposition

The article examines how retrieval‑augmented generation suffers from poor query formulation and presents two advanced strategies—query translation, which generates multiple semantically similar variants, and query decomposition, which breaks complex questions into finer sub‑queries—detailing methods such as fan‑out retrieval, reciprocal rank fusion, HyDE, step‑back prompting, and chain‑of‑thought retrieval, and explains when to combine them.

Hybrid RetrievalLLMQuery Decomposition

0 likes · 9 min read

Advanced RAG Techniques: Boosting Retrieval with Query Translation and Decomposition

DeepHub IMBA

Mar 15, 2026 · Artificial Intelligence

BookRAG: A Tree‑Graph Fusion RAG Framework for Hierarchical Documents

BookRAG introduces a tree‑graph fused Retrieval‑Augmented Generation framework that builds a native document index combining hierarchical layout trees with fine‑grained knowledge graphs, and employs an Information‑Foraging‑Theory‑inspired agent to dynamically navigate queries across complex, multi‑section documents.

RAGagent-based retrievalentity resolution

0 likes · 11 min read

BookRAG: A Tree‑Graph Fusion RAG Framework for Hierarchical Documents