Releases

Meta released PARTNR, a benchmark, dataset and planning model for human-robot collaboration on household tasks.

Meta researchers introduced a non-invasive deep-learning system for decoding typed sentences from EEG and MEG brain recordings.

Meta's first TRIBE brain-response model formed the foundation for its award-winning Algonauts 2025 entry; Meta's later TRIBE v2 announcement identifies the original model as 2025 work.

Meta released research on a multimodal language model that freely mixes text and speech.

Meta introduced foundation models for video generation, personalized video, editing and synchronized audio.

Meta introduced a research pipeline for generating high-quality 3D assets with text and texture control.

Meta introduced an early-fusion multimodal foundation model capable of generating and reasoning over interleaved text and images.

Meta introduced Audiobox, a foundation research model for generating and editing speech, voices and sound effects.

Meta launched Purple Llama, an open trust-and-safety initiative for generative AI.

Meta published Emu Edit for instruction-based image editing with precise task control.

Meta published Emu Video, a factorized text-to-video generation method.

Meta introduced Voicebox, a generative speech model capable of editing, sampling and cross-lingual speech generation.

Meta presented Make-A-Video, a system for generating short videos from text prompts.

Meta introduced Make-A-Scene, a multimodal generative method that gives creators scene-level control over images.

Facebook AI and university partners introduced Ego4D, a large egocentric video dataset and benchmark suite.

Facebook AI introduced unsupervised speech recognition using unpaired speech audio and text.

Facebook AI introduced wav2vec 2.0 for self-supervised speech learning with limited labeled data.

Facebook AI introduced wav2vec, a self-supervised approach to speech representation learning from raw audio.

FAIR researchers published a transformer language model that learned biological properties from protein sequences.