社区博客与文章

Community Articles

NEO-unify: Building Native Multimodal Unified Models End to End

🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do

about 19 hours ago

The ML Engineer's Guide to Protein AI

MARL: Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning

TiRex on the Edge

Structural Problems in AI Benchmarking and the Case for a Unified Evaluation Framework

Uncensor any LLM with abliteration

We’re open-sourcing our text-to-image model and the process behind it

Building Tucano 2: Open-Source Language Models That Actually _Think_ in Portuguese

LLM Architectures Explained: What Powers Today’s Top Models

From GRPO to DAPO and GSPO: What, Why, and How

Konkani LLM: Bringing a Multi-Script Low-Resource Language to the AI Era

Forge: Scalable Agent RL Framework and Algorithm

KV Caching Explained: Optimizing Transformer Inference Efficiency

Deploying Open Source Vision Language Models (VLM) on Jetson

Kanon 2 Reranker: the most powerful reranker for legal RAG

Code a simple RAG from scratch

Getting More from Your Test-Time Compute Budget with Portfolio Beam Search

Text-to-image Architectural Experiments

De-mystifying Multimodal Learning: The Hidden Inefficiency in Vision Language Modelling

llmfine-tuningopen-source

Codex 正在推动 AI 模型的开源与训练流程

2025年12月11日

partnershipsgoogleannouncement

构建开放的未来——我们与 Google Cloud 的全新合作伙伴关系

2025年11月13日

lerobotrobotics

使用 NVIDIA Isaac 构建医疗机器人：从仿真到部署

2025年10月29日

ethicsguidespeech

经同意的语音克隆

2025年10月28日

流式数据集：效率提升 100 倍

+1

2025年10月27日

huggingface_hubpythonannouncement

huggingface_hub v1.0：开源机器学习基础五周年回顾

2025年10月27日

lerobotrobotics

LeRobot v0.4.0：全面提升开源机器人的学习能力

+5

2025年10月24日

ocrvisionmultimodal

用开源模型强化你的 OCR 工作流

+3

2025年10月21日

datasetsopen-sourcevision

用 AI Sheets 解锁图像的力量

+2

2025年10月21日

transformerspytorchoptimization

来自OpenAI gpt-oss的技巧，你🫵在transformers中也可以使用

+3

2025年9月11日

spaceszerogpupytorch

ZeroGPU Spaces 加速实践：PyTorch Ahead-of-Time Compilation 全解析

2025年9月2日

openaigptgpt-oss

欢迎 GPT OSS —— 来自 OpenAI 的全新开放模型家族！

+8

2025年8月5日

llmnlpreasoning

SmolLM3: smol, multilingual, long-context reasoner

+19

2025年7月8日

smolvlalerobotrobotics

SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data

+5

2025年6月3日

Community Articles

NEW Articles from Team or Enterprise organizations will get promoted to the main section.

NEO-unify: Building Native Multimodal Unified Models End to End

🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do

about 19 hours ago

The ML Engineer's Guide to Protein AI

MARL: Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning

TiRex on the Edge

Structural Problems in AI Benchmarking and the Case for a Unified Evaluation Framework

Uncensor any LLM with abliteration

We’re open-sourcing our text-to-image model and the process behind it

Building Tucano 2: Open-Source Language Models That Actually _Think_ in Portuguese

LLM Architectures Explained: What Powers Today’s Top Models

From GRPO to DAPO and GSPO: What, Why, and How

Konkani LLM: Bringing a Multi-Script Low-Resource Language to the AI Era

Forge: Scalable Agent RL Framework and Algorithm

KV Caching Explained: Optimizing Transformer Inference Efficiency

Deploying Open Source Vision Language Models (VLM) on Jetson

Kanon 2 Reranker: the most powerful reranker for legal RAG

Code a simple RAG from scratch

Getting More from Your Test-Time Compute Budget with Portfolio Beam Search

Text-to-image Architectural Experiments

De-mystifying Multimodal Learning: The Hidden Inefficiency in Vision Language Modelling

View all articles