Event cameras offer microsecond temporal resolution, low latency, and high dynamic range, making them attractive for robotics. However, labeled event-camera data for a specific robot and scene is scarce and expensive to collect, which slows the development of event-based perception and control.
arXiv:2505. 08438v4 Announce Type: replace-cross Abstract: Event cameras are rapidly emerging as powerful vision sensors for 3D reconstruction, uniquely capable of asynchronously capturing per-pixel brightness changes.
The paper introduces 4DStreamCtrl, a system that unifies camera motion, object trajectories, and depth into a single 3D point‑track representation, enabling joint control, depth editing, and motion transfer in a single forward pass. By mining in‑the‑wild video for 3D motion supervision and encoding it with a lightweight Geometric Motion Head, the authors train a causal streaming student that can generate arbitrarily long videos in just four denoising steps, achieving 20 FPS on a single high‑end GPU for 480p video. This approach outperforms prior camera‑only, 2D, and offline‑3D methods in motion‑control precision while maintaining temporal coherence over hundreds of frames, thereby enabling interactive 4D‑controllable streaming generation for the first time.
arXiv:2607. 26005v1 Announce Type: cross Abstract: Self-play in simulation produces robust driving policies at scale.
arXiv:2610.28594v1 Announce Type: new Abstract: Reliable multi-view forecasting requires videos from different cameras to describe the same evolving 3D scene. To this end, we introduce Video-Point Mo...
arXiv:2603. 03953v2 Announce Type: replace-cross Abstract: Safe visual navigation is critical for indoor mobile robots operating in cluttered environments.
ZimaBlue is a scalable framework that learns generalizable World Action Models (WAMs) from large-scale egocentric videos. It follows a three-stage curriculum: causal video pre‑training, video‑action mid‑training with a unified action representation, and final specialization to a target robot. The system employs an asynchronous Slow‑Fast architecture to enable real‑time 30 Hz action prediction, achieving a jump in real‑robot zero‑shot success from 36.1% to 77.8% when leveraging over 120,000 hours of embodied video.
PDRVLA is a Vision‑Language‑Action model that incorporates a lightweight Physical Dynamics Module to extract physical tokens from vision‑language features, enabling action generation without online video synthesis. The module predicts future RGB, depth, and optical‑flow features, guided by auxiliary supervision from a frozen pretrained video world model. Trained solely on publicly available data augmented with human‑to‑robot synthesis, subtask annotation, and embodied chain‑of‑thought (ECoT) annotation, PDRVLA achieves high success rates across four simulation benchmarks, with ablations demonstrating the benefits of world‑model supervision and various conditioning strategies.
arXiv:2610.33356v1 Announce Type: new Abstract: Event cameras provide microsecond temporal resolution, high dynamic range, and sparse asynchronous measurements, making them compelling for odometry un...
arXiv:2610.28631v1 Announce Type: new Abstract: Current world models for explicit world simulation typically follow two distinct pathways: (1) video generative models (e.g., Sora), which simulate rea...
arXiv:2609.24815v2 Announce Type: cross Abstract: Scalable simulation is essential for robot data generation, policy training, evaluation, and safe iteration, yet real-world interaction is costly and...
arXiv:2607. 20785v1 Announce Type: cross Abstract: Deploying navigation systems at scale requires a recipe that minimizes sensor assumptions, generalizes across robot embodiments, and trains efficiently.