DeepSeek releases ‘sparse attention’ model that cuts API costs in half

Researchers at DeepSeek released a new experimental model designed to have dramatically lower inference costs when used in ...

DeepSeek Debuts ‘Sparse Attention’ Next-Generation AI Model

DeepSeek updated an experimental AI model in what it called a step toward next-generation artificial intelligence.

DeepSeek tests “sparse attention” to slash AI processing costs

DeepSeek-V3.2-Exp builds on the company's previous V3.1-Terminus model but incorporates DeepSeek Sparse Attention. According ...

China’s DeepSeek Unveils New AI Model That Could Halve Usage Cost

DeepSeek called the model the an advancement in its next-generation lineup of AI.

DeepSeek's new V3.2-Exp model cuts API pricing in half to less than 3 cents per 1M input tokens

MMLU-Pro holds steady at 85.0, AIME 2025 slightly improves to 89.3, while GPQA-Diamond dips from 80.7 to 79.9. Coding and agent benchmarks tell a similar story, with Codeforces ratings rising from ...

DeepSeek’s new model cuts API costs in half

DeepSeek claims that for long-context tasks, its method can cut API costs by half. The model’s weights are open and free, so third-party tinkerers on Hugging Face can start poking holes in those ...

DeepSeek introduces sparse attention model to slash API costs

DeepSeek has launched the V3.2-exp model, introducing Sparse Attention to cut inference costs in long-context tasks by nearly ...
NextBigFuture

Analog in-memory Computing Attention Mechanism for Fast and Energy-efficient Large Language Models

A Nature paper describes an innovative analog in-memory computing (IMC) architecture tailored for the attention mechanism in ...
Yale Environment 360

Attention scan: How our minds shift focus in dynamic settings

A person’s capacity for attention has a profound impact on what they see, dictating which details they glean from the world around them. As they walk down a busy street, the focus of their attention ...