📄 文章列表

11 篇文章
TDS

How a Frontier Model Gets Built, Read from the Kimi K3 Report

✅ completed ⭐ ☆☆☆☆☆ 2026-08-05
AlphaSignal

Moonshot AI Open-Sources FlashKDA, Making Kimi Linear 2x Faster on GPUs | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-27
AlphaSignal

PrismML Shrinks Bonsai 27B to 3.9 GB so It Runs on an iPhone | AlphaSignal

✅ completed ⭐ ☆☆☆☆☆ 2026-07-14
AlphaSignal

Alibaba's HydraHead Cuts Transformer Memory 65% by Mixing Attention Heads | AlphaSignal

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

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

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

Claude Code’s Source Leaks, OpenAI Exits Video Generation, Gemini Adds Music Generation, LLMs Learn at Inference

✅ completed ⭐ ★★★★★ 2026-04-03
AlphaSignal

LightSeek's TokenSpeed Hits 580 Tokens per Second on Qwen3.5's 400B Model | AlphaSignal

✅ completed ⭐ ★★★★★ 2026-06-27
TDS

The Age of Self-Evolving AI Is Here

✅ completed ⭐ ★★★★★★ 2025-07-17
TDS

How LLMs Handle Infinite Context With Finite Memory

✅ completed ⭐ ★★★★★★ 2026-01-09
TDS

Detecting Translation Hallucinations with Attention Misalignment

✅ completed ⭐ ★★★★★★ 2026-04-08
TDS

I Built a Tiny Computer Inside a Transformer

✅ completed ⭐ ★★★★★★ 2026-04-13