📄 文章列表
61 篇文章
AlphaSignal
Z-Image-Engineer V6 Rewrites Flat Prompts Into Cinematic Scenes for Free | AlphaSignal
AlphaSignal
Google's DiffusionGemma Generates 256 Tokens at Once, 4x Faster Than Any LLM | AlphaSignal
AlphaSignal
Google DeepMind's Science Skills Pushes Gemini 3 Flash From 49% to 93% Accuracy | AlphaSignal
AlphaSignal
Google DeepMind's Gemma 4 12B Runs Multimodal AI on Your Laptop for Free | AlphaSignal
AlphaSignal
Google DeepMind's DiffusionGemma Hits 1,000 Tokens per Second by Ditching Left-to-Right Generation | AlphaSignal
AlphaSignal
Cohere's North Mini Code Now Runs Locally on a Mac at 67.6% SWE-Bench | AlphaSignal
AlphaSignal
Cohere's North Mini Code Goes Open Source and Beats Models 4x Its Size | AlphaSignal
AlphaSignal
Cohere's North Mini Code Beats Models 40x Larger at Agentic Coding | AlphaSignal
AlphaSignal
Cohere's North Mini Code Beats 120B Models With Just 3B Active Parameters | AlphaSignal
AlphaSignal
Cohere's Command A+ Beats Google Translate on 48 Languages Running on 2 GPUs | AlphaSignal
TDS
Boost 2-Bit LLM Accuracy with EoRA
TDS
LLMs + Pandas: How I Use Generative AI to Generate Pandas DataFrame Summaries
TDS
When LLMs Try to Reason: Experiments in Text and Vision-Based Abstraction
TDS
Optimizing Vector Search: Why You Should Flatten Structured Data
TDS
How to Fine-Tune an SLM for Emotion Recognition
VentureBeat
Alibabas Metis Agent Cuts Redundant Ai Tool Calls From 98 To 2 And Gets More Accurate Doing It
VentureBeat
How Recursivemas Speeds Up Multi Agent Inference By 2 4X And Reduces Token Usage By 75
VentureBeat
Researchers Trained An Open Source Ai Search Agent Harness 1 That Outperforms Gpt 5 4 On Recalling Relevant Information
VentureBeat
Googles Gemini Embedding 2 Arrives With Native Multimodal Support To Cut
VentureBeat