PonderPounce: A Pretrained MLLM as an Episode Context Engine for Robot Control Paper • 2608.24115 • Published 14 days ago • 13
VideoPrism Collection VideoPrism is a foundational video encoder that enables state-of-the-art performance on a large variety of video understanding tasks. • 5 items • Updated Jul 21 • 21
Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs Paper • 2605.09063 • Published May 9 • 84
WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation Paper • 2603.16871 • Published Mar 17 • 61