Deep Learning - Pagina 5

Gemini 3 di Google: Guida al nuovo modello stato dell’arte

Gemini 3!

Back to Basics: Let Denoising Generative Models Denoise

NVQLink: il ponte tra quantum e AI supercomputing

MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation

Grok 4.1 di xAI: Guida al nuovo modello stato dell’arte

Virtual Width Networks

Instella: Fully Open Language Models with Stellar Performance

Depth Anything 3: Recovering the Visual Space from Any Views

Black-Box On-Policy Distillation of Large Language Models

Che dire, lunga vita alle GAN!

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics

Kimi K2 Thinking: Quando l’AI Impara a Pensare in Profondità

GPT-5.1

RF-DETR: Neural Architecture Search for Real-Time Detection Transformers

Mixture-of-Channels: Exploiting Sparse FFNs for Efficient LLMs Pre-Training and Inference

Accelerating Training Speed of Tiny Recursive Models