arXiv AI September 17, 2026 By Jakub {\L}ucki, Jonathan Becktor, Georgios Georgakis, Rob Royce, Shehryar Khattak

Visual Perception Engine: Fast and Flexible Multi-Head Inference for Robotic Vision Tasks

Visual Perception Engine (VPEngine) is a modular framework that enables efficient GPU usage for robotic vision tasks by sharing a foundation model backbone across multiple specialized task heads. It eliminates redundant feature extraction, supports dynamic task prioritization, and achieves up to 3× speedup over sequential execution. The open‑source Python implementation, with ROS2 C++ bindings, delivers real‑time performance (≥50 Hz) on NVIDIA Jetson Orin AGX using TensorRT‑optimized models.

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 AI.

arXiv AI

Aug 18

Efficient Block-Layer Parallel Inference for Vision-Language-Action on Hybrid Architectures

arXiv:2608. 14586v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are becoming a promising paradigm for autonomous driving, but their deployment on existing vehicle platforms remains difficult because they introduce both high inference latency and strong GPU-side resource pressure.

By Haibo HU, Lianming Huang, Qiao Li, Nan Guan, Chun Jason Xue

llms agents robotics efficiency multimodal

arXiv AI

Jun 19

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

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.

By Gia-Binh Nguyen, Trong-Bao Ho, Thien-Loc Ha, Khoa Vo, Philip Lund M{\o}ller, Quang T. Nguyen, Long Dinh, Tuan Dam, Vu Duong, Tung M. Luu, Trung Le, Tran Nguyen Le, Minh Vu, An Thai Le, Ngan Le, Daniel Sonntag, James Zou, Jan Peters, Duy M. H. Nguyen, Ngo Anh Vien

robotics fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jun 16

MegaFold: Efficient Training of Next-Generation 3D Attention Protein Models on Cross-Platform GPUs

arXiv:2506. 20686v2 Announce Type: replace-cross Abstract: Recent advances in biomolecular modeling have been catalyzed by models such as AlphaFold3 (AF3), which introduce science-informed changes to the transformer architecture.

By Hoa La, Ahan Gupta, Alex Morehead, Jianlin Cheng, Minjia Zhang

llms

arXiv Machine Learning

4d ago

Efficient Vision-Language-Action Management and Serving for Robot Factories

Robion is a new serving and management system designed to run Vision‑Language‑Action (VLA) models on multi‑GPU edge servers for robot factories. It splits the VLM and ADiT stages within a single GPU, shares streams across multiple models, and prioritizes requests by remaining SLO time, enabling high robot load while meeting strict latency requirements. In experiments, Robion achieves 6.7× higher robot load than vLLM‑Omni and 1.5× higher than a monolithic pipeline, and can serve 64 robots on a 4‑GPU server with 98% SLO attainment.

By Dionysios Adamopoulos, Nattapol Chanpaisit, Basel Fakhri, Christina Giannoula

llms diffusion robotics efficiency multimodal safety

arXiv AI

Jul 15

Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference

arXiv:2607. 12659v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have achieved impressive performance on diverse embodied tasks.

By Zebin Yang, Qi Wang, Yunhe Wang, Xiurui Guo, Bo Yu, Shaoshan Liu, Jiafeng Xu, Hao Dong, Meng Li

llms robotics efficiency multimodal benchmarks

arXiv AI

Jul 20

DPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense Prediction

arXiv:2607. 16012v1 Announce Type: cross Abstract: Multi-Task Learning (MTL) in robotics perception systems supports comprehensive 3D spatial scene understanding by integrating semantic segmentation and depth estimation.

By Jehun Kang, Jungha Wang, Youngjun Hwang, David Hyunchul Shim

llms computer-vision robotics efficiency benchmarks

One email a morning, machine-written

Related stories

Efficient Block-Layer Parallel Inference for Vision-Language-Action on Hybrid Architectures

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

MegaFold: Efficient Training of Next-Generation 3D Attention Protein Models on Cross-Platform GPUs

Efficient Vision-Language-Action Management and Serving for Robot Factories

Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference

DPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense Prediction