1 citations · 2 across the 8 of their papers we have counts for
9 papers
Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis
Samuele Punzo, Niccolò Caselli, Ippokratis Pantelidis +3
We study whether pretrained video foundation models encode intuitive-physics information in their frozen representations, and how this information varies across model families, lay…
AmaraSpatial-10K: A Spatially and Semantically Aligned 3D Dataset for Spatial Computing and Embodied AI
Mohammad Sadegh Salehi, Alex Perkins, Igor Maurell +2
Web-scale 3D asset collections are abundant but rarely deployment-ready, suffering from arbitrary metric scaling, incorrect pivots, brittle geometry, and incomplete textures, defec…
VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition
Tanush Yadav, Mohammadreza Salehi, Jae Sung Park +6
Videos are unique in their ability to capture actions which transcend multiple frames. Accordingly, for many years action recognition was the quintessential task for video understa…
MolmoPoint: Better Pointing for VLMs with Grounding Tokens
Christopher Clark, Yue Yang, Jae Sung Park +8
Grounding has become a fundamental capability of vision-language models (VLMs). Most existing VLMs point by generating coordinates as part of their text output, which requires lear…
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
Christopher Clark, Jieyu Zhang, Zixian Ma +18
Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effectively distilling from…
One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory
Chenhao Zheng, Jieyu Zhang, Mohammadreza Salehi +5
Effective video tokenization is critical for scaling transformer models for long videos. Current approaches tokenize videos using space-time patches, leading to excessive tokens an…