Search papers, labs, and topics across Lattice.
Affiliation:
5
0
7
22
Explicitly disentangling and structuring spatial geometry latents via CR-GEO and routed optimization unlocks significantly more effective 3D reasoning from 2D images, pushing SPAR-Bench and SPBench performance to new heights.
GeoAAC is proposed, a geometry-based adaptive action chunking method for flow-based VLA policies that adjusts the action horizon according to the reliability of the current action prediction, with geometric variation across action prefixes remaining positively correlated with predictive uncertainty.
Query-grounded visual sampling can boost long video understanding in LVLMs by over 11% without the need for extensive training.
Task-adaptive control of multimodal focus can boost evidence-grounded reasoning performance by over 6 points in critical scenarios.
Revitalizing the latent edge-sensitivity of DINO with SAM's structural priors yields state-of-the-art open-vocabulary segmentation, especially in cluttered scenes.
