Hugging Face

Tin tức, mô hình và bản phát hành AI mới nhất từ Hugging Face. ['Diffusers', 'GLM 5.2', 'LeRobot v0.6.0', 'Nunchaku Lite', 'qwen3-32b', 'Qwen/Qwen3-4B', 'Qwen/Qwen3.5-122B-A10B', 'Qwen/Qwen3.5-4B', 'SmolLM', 'SmolLM2-1.7B', 'SmolLM3', 'SmolLM3 3B', 'SmolLM3-3B', 'SmolVLM-256M', 'TinyLlama', 'tokenizers', 'Transformers v4', 'Transformers v5', 'TRL', 'Xenova/distilbert-base-uncased-finetuned-sst-2-english', 'Xenova/whisper-tiny.en']

Trang chính thức ↗

Nghiên cứu 🇺🇸

Beyond Standard LLMs: Linear Attention Hybrids, Text Diffusion Models, Code World Models, and Small Recurrent Transformers

The article explores alternatives to standard autoregressive transformer-based LLMs: linear attention hybrids (MiniMax-M1, Qwen3-Next, DeepSeek V3.2, Kimi Linear), text diffusion models, code world models, and small recurrent transformers. The author notes a return to classical attention in MiniMax-M2 and the complexity of linear attention in production.

Moonshot AI

MiniMax

Alibaba/Qwen

DeepSeek

Google/DeepMind

Mistral

Industry Leaders Unite in Open Secure AI Alliance for AI Security

Leading companies including NVIDIA, Microsoft, IBM, and Hugging Face have founded the Open Secure AI Alliance to develop open cybersecurity technologies and tools for the AI era. The alliance aims to democratize protective capabilities through open models and platforms, avoiding single points of failure and strengthening critical infrastructure defense.

NVIDIA

Hugging Face