Generative AI

AI systems designed to generate animated 3D scenes that include active human characters have been limited by a shortage of training data, such as matched 3D scenes and human motion-capture examples. Generated video clips can get the job done without motion capture.

Diffusion transformers learn faster when they can look at embeddings generated by a pretrained model like DINOv2.

Diffusion models usually take many noise-removal steps to produce an image, which takes time at inference. There are ways to reduce the number of steps, but the resulting systems are less effective. Researchers devised a streamlined approach that doesn’t sacrifice output quality.

Google updated its open-weights family of large language models to include versions that handle image and video inputs.

The United States Copyright Office determined that existing laws are sufficient to decide whether a given AI-generated work is protected by copyright, making additional legislation unnecessary.

Amazon announced Alexa+, a major upgrade to its long-running voice assistant.

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.

The practice of fine-tuning models on synthetic data is becoming well established. But synthetic training data, even if it represents the training task well, may include characteristics like toxicity that impart unwelcome properties in the trained model’s output...

OpenAI introduced an AI agent that performs simple web tasks on a user’s behalf.

Last year, we saw an explosion of models that generate either video or audio outputs in high quality. In the coming year, I look forward to models that produce video clips complete with audio soundtracks including speech, music, and sound effects.

Stability AI’s aim is to liberate artists of all trades from the repetitive, mechanical aspects of their work and help them spend the majority of their time on the creative side. So our highest hope for next year is that generative AI will help people to be more creative and productive.

Video generation exploded in an abundance of powerful models.

The gap is narrowing between closed and open models for video generation.

A new model improves on recent progress in generating interactive virtual worlds from still images.

Amazon introduced a range of models that confront competitors head-on.