Loading activity…
@vincesitzmann
Building AI that learns by interacting with the world. Associate Professor @ MIT, leading the Scene Representation Group (http://scenerepresentations.org).
AI
The post introducing Mirror says it collects video-to-action data by incrementally following a video planner.
AI
A researcher says they'll post about the result, describing it as active learning or an RL-like algorithm.
AI
The poster says image representations converge to features whose dot product with another image's representation equals their pointwise mutual information.
AI
The H-CDLM announcement claims denoising hierarchical token representations brings better generations for less compute.
AI
A Rhoda team member says the in-house sensor is much smaller than commercially available tactile sensors.
AI
Matt Niessner calls Kocsis’s Intrinsic Image Diffusion among the first efforts to bring diffusion models to material estimation.
AI
One poster argues that the EU lags in building AI and receives almost none of its gains amid scant investment.
AI
Organizer Bardienus Duisterhof announced a debate on the case for and against world models in robotics, with research and position paper submissions closing October 12.
AI
World Labs says Fei-Fei Li will join AMD as executive vice president and chief scientist, working directly with CEO Lisa Su. The company says the move will bring its spatial AI research closer to the hardware.
AI
A September 25, 2026 update says the paper was accepted to NeurIPS, following an arXiv link shared in June.
AI
An essay argues that engineers’ work is shifting from writing code by hand to designing systems that let AI code correctly at scale, using tests, review agents and feedback loops.
AI
The speaker’s September 8 announcement listed the X-Reason workshop talk for 10:20 a.m. Malmö time in the Palisades South room.
AI
A reply says language models could improve with a closed feedback loop, accurate task checks and safety guardrails—but argues the system needed for that setup is still far off.
AI
Atlas generates videos with exact camera control and reconstructs 3D scenes from input images.
AI
Perplexity founders confirm appointment with focus on open research in continual learning and multi-agent systems.
