PulseAugur / Brief
EN
LIVE 23:16:54

Brief

last 24h
[2/2] 224 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

  1. TOOL · Mastodon — sigmoid.social 한국어(KO) ·

    Lukas Ziegler (@lukas_m_ziegler) ETH Zurich has released a popular robotics course covering everything from the basics of robotics to foundation models. It offers a comprehensive view of the latest curriculum from the perspectives of robot control, learning-based robotics, and foundation models, making it valuable for robotics/agent researchers.

    ETH Zurich has released a popular robotics course that covers topics from foundational robotics principles to foundation models. The curriculum includes robot control, learning-based robotics, and the latest in foundation models, offering valuable insights for researchers and practitioners in robotics and AI agents. AI

  2. RESEARCH · Hugging Face Daily Papers English(EN) · · [3 sources]

    RepWAM: World Action Modeling with Representation Visual-Action Tokenizers

    Researchers have introduced RepWAM, a novel world action model designed for robot manipulation. This model utilizes semantic visual-action tokenization to create a latent space that better connects language instructions with robot control, outperforming traditional reconstruction-oriented tokenizers. Experiments on real-world tasks and simulations demonstrate RepWAM's effectiveness in diverse manipulation scenarios, paving the way for more generalist robot policies. AI

    IMPACT RepWAM's approach could lead to more capable and generalist robots by improving how they interpret and act on language commands.