📄 文章列表

174 篇文章
VentureBeat

Nvidia finds that simple linear math can replace costly AI model handoffs

✅ completed ⭐ ☆☆☆☆☆ 2026-08-21
TDS

Backpropagation Explained for Beginners (Part 3): How Backpropagation Really Works

✅ completed ⭐ ☆☆☆☆☆ 2026-08-12
TDS

Variational Autoencoders (VAEs) Explained: From Theory to ELBO and the Reparameterization Trick

✅ completed ⭐ ☆☆☆☆☆ 2026-08-10
TDS

SPP-Net Paper Walkthrough: Breaking the Fixed-Size Constraint

✅ completed ⭐ ☆☆☆☆☆ 2026-08-10
TDS

Before Q, K, and V: Reconstructing the Transformer

✅ completed ⭐ ☆☆☆☆☆ 2026-08-08
TDS

The Python Ecosystem That Changed AI Development

✅ completed ⭐ ☆☆☆☆☆ 2026-07-30
TDS

Don’t Just “Throw Adam at It”: Misunderstanding Adam Will Cost You

✅ completed ⭐ ☆☆☆☆☆ 2026-07-28
TDS

Backpropagation Explained for Beginners (Part 2): There Has to Be a Better Way

✅ completed ⭐ ☆☆☆☆☆ 2026-07-28
TDS

Backpropagation Explained for Beginners (Part 1): Building the Intuition

✅ completed ⭐ ☆☆☆☆☆ 2026-07-19
AlphaSignal

Sakana AI Builds a Brain-Like Neural Network That Learns Without Backpropagation | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-20
TDS

Building Models in Two Worlds: From Latent Constructs to Behavioral Signals

✅ completed ⭐ ☆☆☆☆☆ 2026-07-13
AlphaSignal

Alibaba's LOGOS Replaces Dozens of Science AI Models With One Open-Source Grammar | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-12
AlphaSignal

PyTorch 2.13 Ships 12x Faster Attention and 4x Memory Savings for LLM Training | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-08
TDS

PANet Paper Walkthrough: When Feature Pyramids Go Bottom-Up

✅ completed ⭐ ☆☆☆☆☆ 2026-07-05
TDS

How Far Can Classical NLP Go? From Bag-of-Words to Stacking on Spooky Author Identification

✅ completed ⭐ ☆☆☆☆☆ 2026-06-29
AlphaSignal

State Media Influences LLM Responses: Significant portions of AI training material reflect national propaganda

✅ completed ⭐ ★★★★★ 2026-06-12
AlphaSignal

Reinforcement Learning With Hints: Privileged On-Policy Exploration (POPE) trains models to expand on partial solutions

✅ completed ⭐ ★★★★★ 2026-06-19
AlphaSignal

Qwen3.7-Max, China’s latest top model: OpenAI model disproves key math conjecture

✅ completed ⭐ ★★★★★ 2026-05-25
AlphaSignal

DiffusionGemma breaks 1,000 tokens/second: Anthropic closes Fable and Mythos after US intervention

✅ completed ⭐ ★★★★★ 2026-06-15
Rundown.AI

Zuck goes all-in on AI

✅ completed ⭐ ★★★★★★ 2024-01-12