Ahead of AI
·
1 year ago
A researcher published a curated list of large language model research papers from January to June 2025, organized by topic including reasoning models, reinforcement learning, efficient training, and multimodal approaches. The list contains over 100 papers with the reasoning models category being particularly prominent, featuring 60+ papers on training reasoning models, inference-time scaling, and evaluation. The compilation will be updated bi-yearly to keep pace with the rapid publication rate in LLM research.
BAIR
·
1 year ago
Researchers developed PEVA, a model that predicts future egocentric video frames from whole-body human motion by conditioning on 48-dimensional action vectors representing joint movements. The model uses an autoregressive conditional diffusion transformer trained on the Nymeria dataset pairing real-world first-person video with body pose capture, and outperforms baselines on perceptual quality metrics across atomic actions and 16-second rollouts. The system enables visual planning by simulating action sequences and scoring them against goals, though current limitations include lack of long-horizon planning and explicit task intent conditioning.
