Transformers

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.

Alibaba updated its popular Qwen3 open-weights models with a number of fresh, speed-boosting tweaks.

An alternative to attention enables large language models to track relationships among words across extraordinarily wide spans of text.

Researchers reduced the number of tokens needed to represent video frames to be fed to a transformer.

Improving a large language model’s factual accuracy typically requires making it bigger, which in turn, involves more computation. Researchers devised an architecture that enables models to recall relevant details without significantly increasing the amount of computation required.

Large language models can improve systems that recommend items to purchase by inferring customer preferences.

Researchers built a model that’s more robust to noisy inputs like misspellings, smarter about character-level information like the number of R's in strawberry, and potentially better able to understand unfamiliar languages that might share groups of letters with familiar languages.

If you have a collection of variables that represent, say, a cancer patient and you want to classify the patient’s illness as likely cancer or not, algorithms based on decision trees, such as gradient-boosted trees, typically perform better than neural networks.

Although large language models can improve their performance by generating a chain of thought (CoT) — intermediate text tokens that break down the process of responding to a prompt into a series of steps.

Contrastive loss functions make it possible to produce good embeddings without labeled data. A twist on this idea makes even more useful embeddings.