📄 文章列表
16 篇文章
cn_ai
Agent自演进驶入“双轨时代”！openJiuwen首发TTSE经验学习框架
VentureBeat
A new framework teaches AI models to audit and repair each other’s reasoning, improving accuracy
AlphaSignal
vLLM's AFD Plugin Cuts DeepSeek-V3.2 Response Time by 47% | AlphaSignal
AlphaSignal
Attacks On Data Centers, Qwen3.5 In All Sizes, DeepSeek’s Huawei Play, Apple’s Multimodal Tokenizer
AlphaSignal
GLM 5.1 Thinks Strategically, Data-Center Revolt Intensifies, When Helpful LLMs Turn Unhelpful, Humanoid Robots Get to W
AlphaSignal
Qwen3.7-Max Challenges Google for Third Place, AI Saves Whales, Fine-Tuning Breaks Copyright Alignment
Rundown.AI
China's open-source AI champion
AlphaSignal
vLLM v0.23.0 Ships DeepSeek-V4 Production Hardening and 56% Throughput Boost | AlphaSignal
AlphaSignal
vLLM v0.23.0 Ships DeepSeek-V4 Production Hardening and 56% Throughput Boost | AlphaSignal
AlphaSignal
vLLM's Elastic Expert Parallelism Lets MoE Models Scale Without Restarting | AlphaSignal
TDS
Training Objective That Makes LLM Inference 3X Faster
TDS
The Geometry of Laziness: What Angles Reveal About AI Hallucinations
TDS
Single Agent vs Multi-Agent: When to Build a Multi-Agent System
TDS
Can LLMs Replace Survey Respondents?
TDS
Why Decade-Old Residual Connections Still Power All of AI (And Why That’s a Problem)
VentureBeat