📄 文章列表
64 篇文章
cn_ai
世界模型首次指导设计芯片!超大核NPU700TOPS,99%算力可用
TDS
How Do Word Embeddings Capture Relationships Between Words?
TDS
AI Agents Beat PyTorch: Writing Faster CUDA Kernels
TDS
The Consistency Quadrant: A Visual Guide to LLM Reliability
TDS
The Reversal Curse: Why a Language Model That Knows “A Is B” Can’t Tell You “B Is A”
TDS
Reparameterization Tricks: Variance Reduction by Smarter Gradients
TDS
Why Transformers Need Positional Encoding For Time Series: A Visual Guide
TDS
Can an LLM Forget the Right Things?
TDS
Estimating from No Data: Deriving a Continuous Score from Categories
TDS
Before Q, K, and V: Reconstructing the Transformer
TDS
How a Frontier Model Gets Built, Read from the Kimi K3 Report
TDS
How to Decode the Temperature Parameter in LLMs
AlphaSignal
Moonshot AI Open-Sources FlashKDA, Making Kimi Linear 2x Faster on GPUs | AlphaSignal
TDS
How To Build Your Own LLM Runtime From Scratch
TDS
Tabular LLMs: An Introduction to the Foundation Models That Predict Your Spreadsheet
TDS
Context Rot: Why Claude Code Sessions Decay, and How to Govern Them
AlphaSignal
Alibaba's HydraHead Cuts Transformer Memory 65% by Mixing Attention Heads | AlphaSignal
TDS
Anchor Detection for RAG: Parallel Detectors, Then One LLM Call at the End
TDS
Behind the Magic: How Tensors Drive Transformers
TDS