Berkeley Artificial Intelligence Research (BAIR)

Latest AI news, models and releases from Berkeley Artificial Intelligence Research (BAIR). ['GPT-4o mini', 'GRASP', 'LLM', 'PEVA', 'ResNet', 'Transitive RL (TRL)']

Official site ↗

Research 🇺🇸

PEVA: Predicting Egocentric Video from Whole-Body Actions

Researchers from BAIR (Berkeley AI) introduce PEVA, a model that predicts egocentric video frames from human whole-body actions. It uses an autoregressive conditional diffusion transformer trained on the Nymeria dataset, enabling atomic action synthesis, counterfactual simulation, and long video generation. PEVA can also be used for visual planning by optimizing action sequences.

Berkeley Artificial Intelligence Research (BAIR)

BAIR (Berkeley AI)27.07 · 17:05

Research 🇺🇸

What Does word2vec Really Learn? Researchers Finally Have an Exact Learning Theory

Researchers from BAIR (Berkeley AI) have developed the first quantitative and predictive theory for word2vec's learning process. They prove that under realistic conditions, training reduces to unweighted least-squares matrix factorization, with final embeddings given by PCA of a specific matrix derived from corpus statistics.

Berkeley Artificial Intelligence Research (BAIR)

BAIR (Berkeley AI)27.07 · 17:04

Show more ↓