BestHub
Sign in
NewBeeNLP
Author

NewBeeNLP

Always insightful, always fun

119
Articles
0
Likes
1
Views
0
Comments
Recent Articles

Latest from NewBeeNLP

100 recent articles max
NewBeeNLP
NewBeeNLP
Jul 5, 2024 · Artificial Intelligence

Unveiling Meta’s Wukong: How Scaling Laws Boost Large‑Scale Recommendation Performance

Meta’s new paper introduces the Wukong model, demonstrating that expanding dense‑layer parameters and computational FLOPs in large‑scale recommendation systems follows a clear scaling law, yielding consistent performance gains across massive internal datasets, with detailed analysis of feature modules, parameter impacts, and experimental results.

CTR modelsLarge-Scale AIMeta
0 likes · 10 min read
Unveiling Meta’s Wukong: How Scaling Laws Boost Large‑Scale Recommendation Performance
NewBeeNLP
NewBeeNLP
Jul 3, 2024 · Industry Insights

What Dominated the AI Landscape in Q2 2024? From Llama 3 to GPT‑4o and Global Price Wars

The second quarter of 2024 saw a whirlwind of AI developments—including Meta’s open‑source Llama 3, Microsoft’s fleeting WizardLM‑2, a wave of model price cuts, major IPOs, legislative restrictions, and the debut of OpenAI’s multimodal GPT‑4o—painting a vivid picture of rapid innovation, fierce competition, and shifting market dynamics across the global AI ecosystem.

AI ModelsAI policyIndustry trends
0 likes · 24 min read
What Dominated the AI Landscape in Q2 2024? From Llama 3 to GPT‑4o and Global Price Wars
NewBeeNLP
NewBeeNLP
Jun 28, 2024 · Artificial Intelligence

Why Large Language Models Aren’t Magic: Understanding Compression and Prompt Engineering

This article demystifies large language models by comparing them to classic compression algorithms, explains how they compress massive data into compact parameters, explores their ability to learn abstract patterns, and provides practical insights into prompt engineering, sampling strategies, and multi‑step agent architectures for real‑world applications.

Agent architectureLLMSampling
0 likes · 19 min read
Why Large Language Models Aren’t Magic: Understanding Compression and Prompt Engineering
NewBeeNLP
NewBeeNLP
Jun 26, 2024 · Interview Experience

From AI Research to Development: My Summer Internship Reflection

After a summer internship, I compare the challenges of pursuing AI research versus software development, recount my friend's success in algorithm roles, and share personal insights on choosing a career path, interview preparation, and the true value of understanding over credentials.

AIReflectioncareer
0 likes · 5 min read
From AI Research to Development: My Summer Internship Reflection
NewBeeNLP
NewBeeNLP
Jun 24, 2024 · Artificial Intelligence

How Domain Large Models Are Shaping the Future of AI: Challenges and Solutions

This article reviews Fudan University's Knowledge Factory Lab research on domain large models, covering background, three major deployment challenges, data‑selection strategies, ability‑enhancement techniques, collaborative workflows, and retrieval‑augmented generation methods that aim to make large models practical for real‑world tasks.

Domain AdaptationKnowledge ExtractionModel Alignment
0 likes · 18 min read
How Domain Large Models Are Shaping the Future of AI: Challenges and Solutions
NewBeeNLP
NewBeeNLP
Jun 20, 2024 · Artificial Intelligence

How LLMs Transform Recommendation Systems: Insights from Kuaishou’s LERAN Paper

This article analyzes Kuaishou’s May 2024 paper on LLM‑driven recommendation, detailing its dual‑tower architecture, contrastive learning of user and item embeddings, and a CVR‑auxiliary task that together improve cold‑start handling and boost both offline and online AUC metrics.

Industrial ApplicationItem EmbeddingLLM
0 likes · 10 min read
How LLMs Transform Recommendation Systems: Insights from Kuaishou’s LERAN Paper
NewBeeNLP
NewBeeNLP
Jun 19, 2024 · Artificial Intelligence

Can Symbolic Chain‑of‑Thought Boost LLM Logical Reasoning?

The paper introduces SymbCoT, a Symbolic Chain‑of‑Thought framework that translates natural‑language problems into symbolic form, plans, solves, and verifies reasoning steps, achieving significantly higher logical reasoning performance than traditional CoT methods across multiple benchmark datasets.

ACL 2024LLMLogical Reasoning
0 likes · 13 min read
Can Symbolic Chain‑of‑Thought Boost LLM Logical Reasoning?
NewBeeNLP
NewBeeNLP
Jun 18, 2024 · Artificial Intelligence

How Shopee Builds an E‑Commerce Knowledge Graph and Leverages Large Models

This article presents Shopee's comprehensive approach to constructing an e‑commerce knowledge graph, detailing the challenges of heterogeneous data, multi‑language handling, entity disambiguation, and the integration of deep learning and large language models to improve product matching, recommendation, and operational efficiency.

AIKnowledge Graphe-commerce
0 likes · 22 min read
How Shopee Builds an E‑Commerce Knowledge Graph and Leverages Large Models
NewBeeNLP
NewBeeNLP
Jun 14, 2024 · Artificial Intelligence

Why Coarse Ranking Matters: Goals, Metrics, and Model Design in Search Systems

The article explains the purpose of coarse ranking in industrial search pipelines, outlines key evaluation metrics, discusses sample construction and model architecture choices, and highlights trade‑offs between consistency with downstream ranking and overall system performance.

coarse rankingevaluation metricssearch ranking
0 likes · 11 min read
Why Coarse Ranking Matters: Goals, Metrics, and Model Design in Search Systems
NewBeeNLP
NewBeeNLP
Jun 12, 2024 · Artificial Intelligence

Beyond Cosine Decay: Fixed LR + Quick Decay Beats Traditional Schedules in LLM Training

The article analyzes why the traditional cosine decay learning‑rate schedule hinders continued training of large language models and shows that fixed‑learning‑rate strategies such as Warmup‑Stable‑Decay, Cooldown, SWA, and Schedule‑Free Optimizer can match or surpass cosine performance while being more friendly to fine‑tuning.

CooldownLLM trainingSFO
0 likes · 7 min read
Beyond Cosine Decay: Fixed LR + Quick Decay Beats Traditional Schedules in LLM Training