Search papers, labs, and topics across Lattice.
3
1
8
Ditch slow, external segmentation pipelines: TrajTok learns trajectory tokens end-to-end, boosting video understanding while staying lean and adaptable.
Scaling VLMs won't magically unlock reasoning skills; you need to address the reporting bias in training data that suppresses tacit information.
Unlock robot learning with hidden knowledge: TOPReward extracts surprisingly accurate task progress signals directly from VLM token probabilities, bypassing the need for explicit reward engineering.
