RT @jesu9: Can you inject causal control to models trained solely on video data? How about eliciting their understanding of physical forces….

RT @GillmanLab: Ever wish you could turn your video generator into a controllable physics simulator? . We're thrilled to introduce Force Pr….

RT @fchollet: People who treat prediction markets as some kind of magical oracle are hopelessly lost. Even the valuation of very high-liqui….

RT @fchollet: Remember that prediction markets are very low-liquidity -- with a couple M$ you can clear the entire order book. They do *not….

RT @jesu9: .@GillmanLab and the team have done it again! 🎉 Fourier Head brings theory-driven enhancements to LLMs when modeling continuous….

RT @GillmanLab: Check out our project page for more details (paper, code, visuals…). This was a team effort :) joi….

RT @GillmanLab: LLMs are powerful sequence modeling tools! They not only can generate language, but also actions for playing video games, o….

RT @GillmanLab: Check out our @ICMLconf poster tomorrow if you want to learn how you can improve human motion generation performance by inj….

RT @jesu9: Now accepted by #ICML2024, code is available at !.

RT @jesu9: Video genmos (e.g. #Sora) are touted as "world simulators". Can we leverage their outputs to create more powerful genmos? Our pa….

RT @GillmanLab: Excited to share our latest preprint: “Self-Correcting Self-Consuming Loops for Generative Model Training”. It's a step tow….