📄 文章列表
476 篇文章
TDS
How to Optimize Vector Search When RAM Gets Too Expensive: On-Disk vs. In-Memory ANN Indexes
TDS
How I Reproduced BM25, Dense Retrieval, and SPLADE on a 16GB MacBook
AlphaSignal
Liquid AI's LFM2.5 Upgrades Its Own Tokenizer, Hitting 3.7x Faster On-Device Speed | AlphaSignal
TDS
Context Engineering for RAG Question Parsing: From a Raw Question to Typed Fields That Steer Retrieval and Generation
AlphaSignal
Mira Murati's Thinking Machines Drops Inkling, a 975B Open Multimodal Reasoning Model | AlphaSignal
AlphaSignal
PrismML Shrinks Bonsai 27B to 3.9 GB so It Runs on an iPhone | AlphaSignal
TDS
A Gentle Introduction to Autoencoders & Latent Space
TDS
Most RAG Hallucinations Are Retrieval Failures: How the Retrieval Brick Decides What the Model Can Invent
TDS
Agentic RAG: Let the Agent Search
AlphaSignal
Meta's FlashNormAttention Hides 90% of Transformer Normalization Costs | AlphaSignal
AlphaSignal
LlamaIndex Ships legal-kb to Replace Single-Shot RAG With Agentic Filesystem Retrieval | AlphaSignal
AlphaSignal
Inception Labs' Mercury 2 Hits 1,000 Tokens per Second on Azure | AlphaSignal
AlphaSignal
Google DeepMind's Gemma 4 Beats Models 10x Its Size on Math and Coding | AlphaSignal
TDS
RAG Was Always a Temporary Workaround. What is Next?
TDS
That Is Embarrassing: Why Frontier AI Still Makes Things Up, and What to Do About It
TDS
Long Context Isn’t Free — I Built a Safe Prompt-Pruning Layer That Makes LLM Systems Work
TDS
The Untaught Lessons of RAG Retrieval: Cosine Is Not the Foundation
TDS
LLM Wikis Are Over-Engineered — I Replaced Mine With a Pure Python Compiler
TDS
Long Context vs. Short Context Model: When Does a Long Context Model Win?
TDS