Transformers

Simulating complex physical systems through traditional numerical methods is slow and expensive, and simulations based on machine learning are usually specialized for a specific type of system, such as water in a pipe or atmosphere surrounding a planet.

An open-weights model could help scientists compare the impact of genetic variations, identify mutations that cause diseases, and develop treatments.

Large language models typically become less accurate and slower when they process longer contexts, but researchers enabled an LLM to keep accuracy stable and inference time constant as its context grew.

Multimodal models typically use different tokenizers to embed different media types, and different encoders when training to generate media rather than classify it.

Difficulty sleeping often precedes heart disease, psychiatric disorders, and many other illnesses. Researchers used data gathered during sleep studies to detect such conditions.

Reasoning models in the 1 to 2 billion-parameter range typically require more than 1 gigabyte of RAM to run. Liquid AI released one that runs in less than 900 megabytes, and does it with exceptional speed and efficiency.

Mistral compressed Mistral Small 3.1 into much smaller versions, yielding a family of relatively small, open-weights, vision-language models that perform better by some measures than competing models of similar size. The method combines pruning and distillation.

Image generators often mangle text. An open-weights model outperforms open and proprietary competitors in text rendering.

Chain-of-thought reasoning can help autonomous vehicles decide what to do next.

Baidu debuted two models: a lightweight, open-weights, vision-language model and a giant, proprietary, multimodal model built to take on U.S. competitors.

The latest open-weights large language model from Moonshot AI challenges top proprietary LLMs at agentic tasks by executing hundreds of tool calls sequentially and pausing to think between each.

Transformers are well suited to predicting future values of time series like energy prices, wages, or weather, but often — as in those examples — multiple time series often influence one another. Researchers built a model that can forecast multiple time series simultaneously.

Reasoning models typically learn to undertake a separate process of “thinking” through their output of before they produce final response. Ant Group built a top non-reasoning model that can take similar steps as part of its immediate response.

DeepSeek’s latest large language model can cut inference costs by more than half and processes long contexts dramatically faster relative to its predecessor.

A new type of transformer can check its work. Instead of guessing the next output token in one shot like a typical transformer, it starts with a rough version of the token and improves it step by step.