← Back to all news
arXiv Computer Vision By Zeping Zhang, Zhuoya Zhao, Robert Lagani\`ere

Let LiDAR Decide Where to Look: Geometry-Measured Token Selection for Efficient Sparse Latent World Models

Read the original on arXiv Computer Vision →

The paper introduces Geometry-Aware Token Selection (GATS), a method that uses LiDAR and radar point projections to filter image tokens before they enter a vision backbone, thereby reducing computational load. By encoding only the selected patches, GATS cuts FLOPs by up to 18× while maintaining or improving performance on nuScenes and NAVSIM benchmarks. Even with a 10% token budget, the approach outperforms dense models in displacement error and collision rate on intent‑critical scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

Hugging Face Trending Papers
Aug 6

G$^2$ARD-GS: Geometry-Guided Anchor-Regularized Gaussian Splatting Distillation

Dense colored LiDAR maps provide accurate city-scale geometry, but lifting them into 3D Gaussian Splatting (3DGS) retains millions of primitives, making the resulting models costly to store, transmit, render, and adapt. Aggressive primitive reduction alleviates this burden, but can remove the local surface support needed for stable novel-view synthesis and downstream geometric use.

efficiency
More like this →
arXiv Computer Vision
Oct 9

Look Where You Can: Active View Selection for CAD Reconstruction under Occlusion

The paper introduces SightCAD, a framework for parametric CAD reconstruction that explicitly handles view feasibility constraints in realistic indoor scenes. It learns a view selector to choose a small set of feasible viewpoints for a vision‑language model that generates executable CadQuery code, and jointly trains the selector and the VLM using a reward that depends on the final geometric fidelity. The approach outperforms baseline methods on several benchmarks, achieving higher intersection‑over‑union scores and a lower invalid‑code rate.

By Kartik Bali, Mahish Guru, Yiderigun Borjigin, Alexandra Starostina, Christian J. Cyron, Roland Aydin
llmsmultimodalbenchmarks
More like this →