arXiv:2606. 14773v1 Announce Type: cross Abstract: We present Double-Helix Vision (DH), a geometry-based visual sampler that compresses 2D images into compact 1D signals using paired golden-ratio-inspired spiral trajectories.
arXiv:2607. 07885v1 Announce Type: cross Abstract: Dynamic obstacle avoidance in unstructured outdoor environments remains a critical challenge for autonomous mobile robots, particularly when large-scale robot-specific training data and simulation-based policies are impractical.
arXiv:2608. 04515v1 Announce Type: cross Abstract: Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices.
arXiv:2606. 00746v1 Announce Type: cross Abstract: Vision foundation models are bottlenecked by the quadratic cost of self-attention, which limits usable resolution and increases the cost of large-scale pretraining.
Monocular depth estimation has seen remarkable progress through foundation models achieving robust zero-shot generalization, yet their computational demands place them far beyond the reach of embedded and mobile platforms. Lightweight alternatives exist, but have been developed almost exclusively within single-domain, self-supervised paradigms, failing silently under domain shift.
arXiv:2606. 29350v1 Announce Type: cross Abstract: Vision-language models and vision-language action models endow the robot with unprecedented capabilities.
arXiv:2606. 03940v1 Announce Type: cross Abstract: In robotics systems, vast amounts of visual data are easily captured at high resolution using low-cost, low-power hardware.
We present 4DAnyone, a framework for reconstructing 4D humans from an uncalibrated monocular video by generating reconstruction-grade multiview-consistent videos and lifting them into 4D Gaussian Splatting (4DGS). Existing camera-controlled video diffusion models synthesize plausible novel-view videos but fail to maintain consistency when scaled to the tens of target views required for 4DGS reconstruction.
arXiv:2606. 20246v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose prohibitive computational burdens during downstream fine-tuning and real-time inference.
arXiv:2603. 25937v2 Announce Type: replace-cross Abstract: Visual Navigation Models (VNMs) promise generalizable, robot navigation by learning from large-scale visual demonstrations.
Visual Geometry Grounded Transformer (VGGT) recovers dense 3D scene structure from multi-view images in one forward pass, but quadratic cross-frame attention limits its scalability. Existing training-free accelerators reduce computation uniformly along one axis, missing layer heterogeneity.
arXiv:2604. 05182v2 Announce Type: replace-cross Abstract: We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows affects feed-forward 3D reconstruction.
arXiv:2608. 20335v1 Announce Type: new Abstract: We present 4DAnyone, a framework for reconstructing 4D humans from an uncalibrated monocular video by generating reconstruction-grade multiview-consistent videos and lifting them into 4D Gaussian Splatting (4DGS).