Tagged: model-architecture

8 articles

Latest

T5 and BART share one architecture: How encoder-decoders actually work

PolyAI’s New Model Listens to Raw Audio, Skips the Transcript and Boosts Containment 11%

Thinking Machines drops Inkling: a 975B-param open model that sees, hears, and reads

GPT-5 arrives with a brain router and a real shot at usefulness

DeepSeek's V4 slashes KV cache to 2% of normal size, making million-token agents practical

Google's Gemma 4 packs GPT-rivaling power into a 4B-parameter model

MoE, Tiny Models, and Domestic Chips: China's Open-Source AI Playbook After DeepSeek

Ettin benchmarks prove encoder models crush decoders at 4X the efficiency