📄 文章列表

840 篇文章
TDS

That Is Embarrassing: Why Frontier AI Still Makes Things Up, and What to Do About It

✅ completed ⭐ ☆☆☆☆☆ 2026-07-11
TDS

Long Context Isn’t Free — I Built a Safe Prompt-Pruning Layer That Makes LLM Systems Work

✅ completed ⭐ ☆☆☆☆☆ 2026-07-11
AlphaSignal

Alibaba's Wan-Streamer v0.2 Triples Video Resolution Without Adding Latency | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-09
TDS

Stop Returning Text from RAG: The Typed Answer Contract That Prevents Hallucination

✅ completed ⭐ ☆☆☆☆☆ 2026-07-04
TDS

Setting Up Your Own Large Language Model

✅ completed ⭐ ☆☆☆☆☆ 2026-07-04
TDS

PANet Paper Walkthrough: When Feature Pyramids Go Bottom-Up

✅ completed ⭐ ☆☆☆☆☆ 2026-07-05
TDS

Assemble Each RAG Generation Prompt from a Base Prompt Plus the Rules Each Question Needs

✅ completed ⭐ ☆☆☆☆☆ 2026-07-05
TDS

Granger Causal Networks and Indirect Feedback

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

NVIDIA's Nemotron-TwoTower Hits 2.42x Faster Generation Without Retraining | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-01
AlphaSignal

Cognition's Devin Restores Claude Fable 5 After a Messy Government Ban | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-01
TDS

Prompt Engineering Fails Quietly —  Prompt Regression Is Why

✅ completed ⭐ ☆☆☆☆☆ 2026-06-29
TDS

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

✅ completed ⭐ ☆☆☆☆☆ 2026-06-29
TDS

Context Engineering for RAG : The Four Typed Inputs Behind Every RAG Answer

✅ completed ⭐ ☆☆☆☆☆ 2026-06-30
TDS

Persistent Latent Memory for Multi-Hop LLM Agents: How a 6G Handover Paper Closes the Agent Cold-Start

✅ completed ⭐ ☆☆☆☆☆ 2026-07-01
TDS

Why Powerful ML Is Deceptively Easy — Part 2

✅ completed ⭐ ☆☆☆☆☆ 2026-07-01
VentureBeat

Mistral launches OCR 4, turning document extraction into a full enterprise AI play

✅ completed ⭐ ☆☆☆☆☆ 2026-06-24
VentureBeat

DeepSeek open sources DSpark, a new framework to speed up LLM inference by up to 85%

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

Anthropic launches Claude Sonnet 5 at a steep discount to its top model as the company races toward a blockbuster IPO

✅ completed ⭐ ☆☆☆☆☆ 2026-06-30
AlphaSignal

Top Agentic Performance, Low Cost: GLM-5.2, designed for coding and long-running agentic jobs, now the top open model

✅ completed ⭐ ★★★★★ 2026-06-26
AlphaSignal

US government to vet new models: ChatGPT gets a model refresh

✅ completed ⭐ ★★★★★ 2026-05-06