Meta AI (FAIR)

Human motion generation gets a dose of reality: IAM shows that explicitly modeling body morphology and identity leads to more realistic and consistent movements.

Hallucinating LLMs in enterprise workflows can be tamed by a new Hybrid Utility Minimum Bayes Risk (HUMBR) framework that synthesizes semantic and lexical signals to achieve consensus without ground truth.

AI could provide a new lens on the structure of mathematics, potentially answering the age-old question of whether it is discovered or invented.

LLMs can now infer plausible stage layouts from unstructured text alone, opening up new possibilities for automated media production.

Forget imbalanced LoRA usage: ReMix leverages reinforcement learning to route effectively among LoRAs, boosting performance in parameter-efficient fine-tuning.

Unlocking the secrets of viral video ads: a new MLLM framework reveals which initial moments hook viewers and drive conversions.

Ditch the pre-trained models: PAST directly learns speech tokens from phonetic data, outperforming existing methods in representation and reconstruction.