This work proposes GPERT, a framework to address the trade-off between accuracy and temporal resolution in event-based 3DGS, by decouple the rendering into two branches: event-by-event geometry (depth) rendering and snapshot-based radiance (intensity) rendering, by using ray-tracing and the image of warped events.
Kai Kohyama, Yoshimitsu Aoki, Guillermo Gallego et al.· arXiv.org· 0 citations
Endpoint-Constrained Optimization (ECO), a lightweight postprocessing layer that anchors the trajectory to the vehicle's executed history, preserves the policy's predicted endpoint, and reshapes the intermediate waypoints to improve feasibility is introduced.
Brayden Zhang, Mahsa Golchoubian, Igor Gilitschenski et al.· 0 citations
A novel architecture is proposed that addresses sample efficiency in VLAs by training a predictive world model on the embedding space of the VLA's vision encoder, and it is hypothesized that these embeddings are action-relevant and usable for future prediction.
Parsa Mastouri Kashani, Jan-Gerrit Habekost, Stefan Wermter· 0 citations
iDriveVLA is proposed, a multi-modal planning framework that improves the candidate trajectory space while enabling more reliable and context-aware trajectory evaluation and develops an oracle-aligned progressive training strategy consisting of candidate imitation pretraining, candidate space refinement, and semantic r...
Ze-Yu He, Shi-Qi Liu, Ke Chen et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
NavGen is introduced, a text-to-video data generation pipeline that produces diverse vision-language navigation episodes across indoor and outdoor scenes and a style-diversification method that scales up long-tail data that is difficult and costly to collect.
Xi-Jie Huang, Yong-Yang Wan, Cheng-Bin Dong et al.· 2 citations
This work presents a design optimization method that considers both dexterity and anatomy in the design of a bimanual dexterous sheaths robot for performing procedures on cancerous polyps in colon anatomies, achieving a 78% higher RVDSA on average than optimizing for 3D voxel coverage alone.
Tony Qin, Peter Connor, Khoa T. Dang et al.· 0 citations
An evaluation protocol is proposed for testing the incremental value of latent access and releasing per-frame failure endpoint labels across two autonomous-driving tasks: online vectorized map generation with LaneSegNet and end-to-end planning with VAD.
N. Advani, Vishwajeet Shivaji Hogale, Saurav Kumar· 0 citations
Closed-Loop contextual Uncertainty rEsolution (Closed-Loop contextual Uncertainty rEsolution), a framework for actively resolving contextual uncertainty given underspecified tasks in natural language, is presented.
Zachary Ravichandran, Jonathan Diller, Fernando Cladera et al.· 0 citations
This paper gives HRI practitioners a standardised basis for evaluating, classifying, and comparing human-robot relationships, and sets out the experimental rigour that each classification demands, and calls on researchers of human-robot relationships to adopt such rigour.
An embodied scene question-answering (QA) interface in which vision never enters the language model is studied, showing the gain survives paraphrase, attributing it to decision-aligned computation rather than answer-string leakage, while novel judgment vocabularies bound its scope.
Albireo is presented, a detector-agnostic, codec-free adaptive inference framework that wraps off-the-shelf detectors and decides when detector invocation can be safely skipped based on scene content and per-object temporal state, requiring no detector modification or retraining.
Amir Taherin, José Cano, Bin Ren et al.· 0 citations
This work proposes a framework that exposes backbone depth V, action expert depth A, and denoising steps $D$ as three jointly configurable compute axes in a VLA, and introduces a KV Cache synthesis mechanism that manages the missing keys and values of the skipped backbone layers, allowing the action expert to exit deep...
Riccardo Andrea Izzo, Rimvydas Rubavicius, Gianluca Bardaro et al.· 0 citations
A new system identifies and corrects unreliable object descriptions stored in a robot’s memory, improving the robot’s ability to interact with its environment.
Robots are getting smarter, but how can their hardware match that growth? New Microsoft Research findings show that moving AI inference beyond the robot can improve task success, boost efficiency, and support more advanced physical AI workloads. The post Offloaded inference for real-world physical AI robotics appeared first on Microsoft Research.
