Probes test spatial state in ten visual foundation models
Strong visible-scene readout does not ensure object persistence, future-feature retrieval or reliable action utility.
Stories per day · 30 days
3 RSS
Relatedworld-models2holiworld1multimodal1probing1spatial-reasoning1spatial-representation1visual-foundation-models1
4 stories, newest first · one card per story
Stories tagged #egocentric-vision
Holi-World builds world records and a 4B model from ego video
About 100 scenes yield roughly 80K QA pairs used to train HOLIWORLD-VL-4B, evaluated on HOLIWORLD-Bench.
Reflex: Visually Grounded Reactive Humanoid Control
Reflex enables a Unitree G1 to catch thrown boxes from egocentric RGB-D, with 65% success at 2.5 meters.
EventEgoHands++: Event-based Egocentric 3D Hand Mesh Reconstruction with Real Dataset
EventEgoHands++ reconstructs egocentric 3D hand meshes from event cameras using instance-level detection and a 1M-frame real dataset.