Manipulation, locomotion, sim-to-real transfer and autonomous driving: learning systems that have to survive physics.
arXiv:2501.16698v2 Announce Type: replace Abstract: Spatial intelligence, encompassing 3D perception and reasoning, is the essential next frontier of AI. Scaling current 3D vision-language models (VL...
arXiv:2601.12538v2 Announce Type: replace-cross Abstract: Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) d...
arXiv:2609.22351v1 Announce Type: new Abstract: Open-vocabulary 3D Scene Graphs (3DSGs) ground each object node in a vision-language embedding, yet they record every entry as equally certain, so a ro...
arXiv:2609.22857v1 Announce Type: new Abstract: Dynamic object segmentation and ego-motion estimation are closely coupled problems in autonomous driving, as accurate ego-motion estimation typically r...
arXiv:2609.23541v1 Announce Type: new Abstract: Multimodal 3D object detection is fundamental to robust perception in autonomous driving because it integrates complementary information from LiDAR and...
arXiv:2609.23565v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models integrate vision-language understanding with executable robot actions, enabling end-to-end learning for robot contr...
arXiv:2609.24170v1 Announce Type: new Abstract: Embodied AI systems are often organized into System 1 and System 2. System 1 is typically a pretrained policy that generates actions at high frequency,...
arXiv:2609.24308v1 Announce Type: new Abstract: Evaluating world models requires assessing both the quality of the worlds they generate and their consistency and responsiveness under exploration, int...
arXiv:2609.24313v1 Announce Type: new Abstract: World models aim to capture environmental dynamics and predict future trajectories, showing growing potential for embodied intelligence. Physics-inform...
arXiv:2609.24526v1 Announce Type: new Abstract: Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints and...
arXiv:2508.01661v2 Announce Type: replace Abstract: Amodal segmentation aims to recover complete object shapes, including occluded regions, serving as an essential technique for user-centric multimed...
arXiv:2604.15281v2 Announce Type: replace Abstract: 3D policy learning promises superior generalization and cross-embodiment transfer, but progress has been hindered by training instabilities and sev...
arXiv:2609.07780v2 Announce Type: replace Abstract: Automated drone surveillance has become increasingly important for public safety, critical infrastructure protection,and restricted airspace monito...
A robot policy trained with either absolute joint targets or delta‑relative actions inherits the chosen action parameterization in its world model, leading to catastrophic failures when the model is exposed to the alternate encoding. Experiments on three robot datasets and two morphologies show retrieval performance drops 2.6–13.4×, goal‑conditioned action selection plummets from 53% to 15%, and predictions for the same future become nearly orthogonal. The issue is not a loss of information—both encodings are highly reconstructible—but a lack of invariance in the action channel, which existing visual‑model invariance research does not address. Averaging over the two encodings partially restores performance, yet the worst‑case disagreement remains high, indicating that the defect persists in certain scenarios.
The paper introduces UniK, a universal knowledge perception platform designed to serve both digital AI—such as chatbots and agent workflows—and physical AI, which controls robots and autonomous systems. UniK handles the entire knowledge lifecycle—ingestion, enrichment, indexing, retrieval, and continuous evaluation—across diverse modalities including text, video, molecular data, and sensor telemetry, without task‑specific fine‑tuning. In five digital AI domains, UniK paired with a 70‑billion‑parameter model matches or surpasses larger proprietary LLMs, achieving high retrieval‑augmented generation accuracy on government data, medical QA, and chemistry tasks, and it also addresses similar data challenges in physical AI world‑model training.
The paper reviews the evolution of multi‑agent unmanned systems from isolated sensing to collaborative intelligence, where agents share compact features to overcome local observation limits such as occlusions and sensor range. It introduces a five‑dimensional taxonomy (collaboration stage, communication paradigm, fusion architecture, learning strategy, application domain) and three cognitive synergy conditions (Semantic Disambiguation, Pragmatic Information Exchange, Proactive Informational Foraging) to unify existing research. The authors survey architectures, neural‑communication co‑design, embodied action‑perception loops, and resilience mechanisms, map advances onto operational domains (V2X, UAV, logistics, smart cities), and propose the GCI‑Bench scoring protocol to standardize evaluation across studies.
Relationally Grounded Latent World Models for Autonomous Driving proposes using traffic scene graphs as privileged semantic supervision for latent world representations. The approach builds actor‑centric scene graphs from nuScenes 3D annotations, encodes their relational structure with a frozen text embedding model, and aligns visual latent representations to this semantic target during training. At inference the supervision branch is removed, requiring no scene graphs or 3D annotations and adding no extra computation, while achieving a 5.9% reduction in average trajectory L2 error and a 52.4% drop in collision rate compared to the LAW baseline.
LIBERO-VPro is a benchmark designed to assess the closed‑loop visual robustness of robotic foundation models by systematically perturbing visual inputs during task execution. It spans four dimensions—Visual Evidence Degradation, Camera Staleness, Visual Source Consistency, and Task‑Relevant Scene Variation—across 12 challenge categories, 96 settings, and 3,296 task‑condition cases. Evaluations on six models over 196,000 simulated episodes and 200 real‑world rollouts show that high nominal performance can hide significant weaknesses in visual grounding, adaptation, and sensitivity to stale or missing observations.
arXiv:2609.22128v1 Announce Type: cross Abstract: The wrist plays a critical role in upper-limb function by enabling precise hand positioning, force regulation, and object manipulation. Continuous br...
arXiv:2609.23269v1 Announce Type: cross Abstract: In a decentralized multi-robot team under partial observability, the fact that decides a robot's next action is often visible only to a teammate. Exi...