AI 知识库 | 文章列表

cn_ai

2026 年 PyTorch 大会：谷歌和 Meta 开源 TorchTPU，在 TPU 上原生支持 PyTorch

✅ completed ⭐ ☆☆☆☆☆ 2026-11-06

TDS

Your Agent’s Tools Can Make Decisions, Too

✅ completed ⭐ ☆☆☆☆☆ 2026-10-30

TDS

The Hidden Cost of LLM Routing: Why Switching Models Costs More

✅ completed ⭐ ☆☆☆☆☆ 2026-10-20

VentureBeat

AI agents can be unpredictable. Your control layer shouldn't be.

✅ completed ⭐ ☆☆☆☆☆ 2026-10-10

TDS

RAG Isn't an Agent — I Built the Layer Between Retrieval and Action

✅ completed ⭐ ☆☆☆☆☆ 2026-09-25

TDS

Optimal Traffic Allocation Under Heterogeneous Variant Cost

✅ completed ⭐ ☆☆☆☆☆ 2026-09-05

TDS

LLM Wikis Are Over-Engineered — I Replaced Mine With a Pure Python Compiler

✅ completed ⭐ ☆☆☆☆☆ 2026-07-03

TDS

The Untaught Lessons of RAG Question Parsing: Structure Before You Search

✅ completed ⭐ ☆☆☆☆☆ 2026-07-02

AlphaSignal

vLLM v0.23.0 Ships DeepSeek-V4 Production Hardening and 56% Throughput Boost | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-26

AlphaSignal

vLLM v0.23.0 Ships DeepSeek-V4 Production Hardening and 56% Throughput Boost | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-23

TDS

The Hot Path Belongs to GBDTs, Agents Own the Cold Path: A Payment-Fraud Benchmark

✅ completed ⭐ ★★★☆☆ 2026-06-25

TDS

Anchor Detection for RAG: Parallel Detectors, Then One LLM Call at the End

✅ completed ⭐ ★★★☆☆ 2026-06-24

TDS

Boosting Your Anomaly Detection With LLMs

✅ completed ⭐ ★★★★★★ 2025-09-04

TDS

Agentic AI in Finance: Opportunities and Challenges for Indonesia

✅ completed ⭐ ★★★★★★ 2025-10-22

TDS

NeurIPS 2025 Best Paper Review: Qwen’s Systematic Exploration of Attention Gating

✅ completed ⭐ ★★★★★★ 2025-12-13

TDS

Building a Self-Healing Data Pipeline That Fixes Its Own Python Errors

✅ completed ⭐ ★★★★★★ 2026-01-21

TDS

Agentic AI for Modern Deep Learning Experimentation

✅ completed ⭐ ★★★★★★ 2026-02-18

TDS

Prefill Is Compute-Bound. Decode Is Memory-Bound. Why Your GPU Shouldn’t Do Both.

✅ completed ⭐ ★★★★★★ 2026-04-15

TDS

Proxy-Pointer RAG: Solving Entity and Relationship Sprawl in Large Knowledge Graphs

✅ completed ⭐ ★★★★★★ 2026-05-19

TDS

LLM Themes Are Not Observations

✅ completed ⭐ ★★★★★★ 2026-05-21

📄 文章列表

2026 年 PyTorch 大会：谷歌和 Meta 开源 TorchTPU，在 TPU 上原生支持 PyTorch

Your Agent’s Tools Can Make Decisions, Too

The Hidden Cost of LLM Routing: Why Switching Models Costs More

AI agents can be unpredictable. Your control layer shouldn't be.

RAG Isn't an Agent — I Built the Layer Between Retrieval and Action

Optimal Traffic Allocation Under Heterogeneous Variant Cost

LLM Wikis Are Over-Engineered — I Replaced Mine With a Pure Python Compiler

The Untaught Lessons of RAG Question Parsing: Structure Before You Search

vLLM v0.23.0 Ships DeepSeek-V4 Production Hardening and 56% Throughput Boost | AlphaSignal

vLLM v0.23.0 Ships DeepSeek-V4 Production Hardening and 56% Throughput Boost | AlphaSignal

The Hot Path Belongs to GBDTs, Agents Own the Cold Path: A Payment-Fraud Benchmark

Anchor Detection for RAG: Parallel Detectors, Then One LLM Call at the End

Boosting Your Anomaly Detection With LLMs

Agentic AI in Finance: Opportunities and Challenges for Indonesia

NeurIPS 2025 Best Paper Review: Qwen’s Systematic Exploration of Attention Gating

Building a Self-Healing Data Pipeline That Fixes Its Own Python Errors

Agentic AI for Modern Deep Learning Experimentation

Prefill Is Compute-Bound. Decode Is Memory-Bound. Why Your GPU Shouldn’t Do Both.

Proxy-Pointer RAG: Solving Entity and Relationship Sprawl in Large Knowledge Graphs

LLM Themes Are Not Observations