Author

Wu Shixiong's Large Model Academy

We continuously share large‑model know‑how, helping you master core skills—LLM, RAG, fine‑tuning, deployment—from zero to job offer, tailored for career‑switchers, autumn recruiters, and those seeking stable large‑model positions.

109

Articles

Likes

109

Views

Comments

Latest from Wu Shixiong's Large Model Academy

100 recent articles max

Wu Shixiong's Large Model Academy

Sep 18, 2025 · Artificial Intelligence

How to Diagnose and Optimize RAG Systems When 30% Answers Miss the Mark

This guide explains why RAG systems often produce off‑topic answers, outlines how to measure hit‑rate, retrieval, reranking and generation metrics, provides step‑by‑step evaluation pipelines, code examples, real‑world case studies, and interview‑ready templates for diagnosing and optimizing each stage of the pipeline.

AIRAGgeneration

0 likes · 18 min read

How to Diagnose and Optimize RAG Systems When 30% Answers Miss the Mark

Wu Shixiong's Large Model Academy

Aug 26, 2025 · Artificial Intelligence

Mastering RLHF, DPO, and KTO: A Complete Guide to Human‑Feedback Alignment Techniques

This comprehensive guide explains the full RLHF training pipeline, the mathematical foundations of reward modeling and PPO, and introduces DPO and KTO algorithms—including their implementations, advantages, limitations, and practical tuning strategies—for building aligned large language models.

DPOHuman FeedbackKTO

0 likes · 32 min read

Mastering RLHF, DPO, and KTO: A Complete Guide to Human‑Feedback Alignment Techniques

Wu Shixiong's Large Model Academy

Aug 23, 2025 · Artificial Intelligence

Why LoRA, QLoRA, Prompt & Prefix Tuning Are Changing Large‑Model Fine‑Tuning

This article explains the mathematical basis of LoRA, compares it with QLoRA, Prompt Tuning, Prefix Tuning and P‑tuning, shows practical PyTorch implementations, and provides mixed‑precision training tips so readers can choose the most memory‑efficient fine‑tuning method for their large language models.

LoRAPrompt TuningQLoRA

0 likes · 17 min read

Why LoRA, QLoRA, Prompt & Prefix Tuning Are Changing Large‑Model Fine‑Tuning

Wu Shixiong's Large Model Academy

Aug 20, 2025 · Artificial Intelligence

Mastering Large‑Model Interview Questions: MHA, KV‑Cache, Scaled Dot‑Product, and Speculative Decoding

This guide walks through common large‑model interview challenges, including a hands‑on implementation of multi‑head attention with KV‑cache, the mathematical reason for scaling by sqrt(dₖ), a concise speculative decoding algorithm, and systematic debugging steps for NaN loss during training.

KV CacheLarge Model InterviewMulti‑Head Attention

0 likes · 14 min read

Mastering Large‑Model Interview Questions: MHA, KV‑Cache, Scaled Dot‑Product, and Speculative Decoding

Wu Shixiong's Large Model Academy

Jul 3, 2025 · Artificial Intelligence

Causal LM vs Prefix LM: Core Differences, Attention Masks, and Choosing the Right Model

This article explains the fundamental distinctions between Causal Language Models and Prefix Language Models, detailing their definitions, attention‑mask designs, underlying design philosophies, and practical scenarios where each architecture excels.

AIAttention MaskCausal LM

0 likes · 7 min read

Causal LM vs Prefix LM: Core Differences, Attention Masks, and Choosing the Right Model

Wu Shixiong's Large Model Academy

Nov 12, 2023 · Fundamentals

How to Compute the Shortest Distance on a Circular Road Efficiently

Given a circular road with n stations and the distances between each consecutive pair, this article explains how to determine the minimal travel distance between any two stations by evaluating both clockwise and counter‑clockwise routes, providing problem details, examples, solution logic, reference implementations in Python, Java, and C++, and complexity analysis.

ArrayJavaSimulation

0 likes · 8 min read

How to Compute the Shortest Distance on a Circular Road Efficiently

Wu Shixiong's Large Model Academy

Nov 10, 2023 · Fundamentals

Minimizing the Sum of a Distinct Array with GCD k

Given two positive integers n and k, construct an array of n distinct numbers whose greatest common divisor is k and whose total sum is as small as possible, then output that minimal sum.

ArrayGCDalgorithm

0 likes · 5 min read

Minimizing the Sum of a Distinct Array with GCD k

Wu Shixiong's Large Model Academy

Nov 7, 2023 · Fundamentals

How to Compute the Shortest Distance on a Circular Road Between Two Stations

Given a circular road with n stations and the clockwise distances between consecutive stations, this article explains how to calculate the minimum travel distance between any two stations by comparing clockwise and counter‑clockwise routes, with full Python, Java, and C++ implementations.

ArrayJavaSimulation

0 likes · 7 min read

How to Compute the Shortest Distance on a Circular Road Between Two Stations

Wu Shixiong's Large Model Academy

Nov 5, 2023 · Interview Experience

Maximizing Stacked Books: DP & LIS Solution for 2023B Problem

This article explains how to compute the maximum number of books that can be stacked without rotation by converting the problem into a longest increasing subsequence (LIS) task, sorting books by length and width, applying a dynamic‑programming DP approach, and analyzing its time and space complexities.

DPLISPython

0 likes · 9 min read

Maximizing Stacked Books: DP & LIS Solution for 2023B Problem

Wu Shixiong's Large Model Academy

Nov 2, 2023 · Fundamentals

Minimize Highway Travel Time with Optimal Rest‑Stop Charging (DP Solution)

This article presents a DP‑based algorithm to plan charging stops at highway rest stations for an electric vehicle with 1000 km range, minimizing total travel time including driving, queueing, and charging, and provides a Python implementation with O(N) time and space complexity.

Electric Vehiclealgorithmcharging stations

0 likes · 10 min read

Minimize Highway Travel Time with Optimal Rest‑Stop Charging (DP Solution)