Reece Keller
@rdkeller
CS+Neuro @CarnegieMellon. PhD Student with @xaqlab and @aran_nayebi working on autonomy in embodied agents.
Over the past 18 months my lab has been developing a new approach to visual world modeling. There will be a magnum opus that ties it all together out in the next couple of weeks. But for now there are some individual application papers that have poked out.
📷 New Preprint: SOTA optical flow extraction from pre-trained generative video models! While it seems intuitive that video models grasp optical flow, extracting that understanding has proven surprisingly elusive.
Given the confusion around what RL does for reasoning in LLMs, @setlur_amrith & I wrote a new blog post on when RL simply sharpens the base model & when it discovers new reasoning strategies. Learn how to measure discovery + methods to enable it ⬇️ tinyurl.com/rlshadis
New paper: World models + Program synthesis by @topwasu 1. World modeling on-the-fly by synthesizing programs w/ 4000+ lines of code 2. Learns new environments from minutes of experience 3. Positive score on Montezuma's Revenge 4. Compositional generalization to new environments…