arXiv Computer Vision

VeriFuse: Bounded Vision-Language Arbitration and Reason-Guided Refinement for Cooperative 3D Perception

VeriFuse is a bounded arbitration framework that integrates vision‑language models (VLMs) into vehicle‑infrastructure cooperative 3D perception. Each agent first generates independent detections, then VeriFuse creates a unified candidate pool of geometric proposals and cross‑source hypotheses. A frozen VLM selects among three actions—SELECT, REFINE, or REJECT—to resolve ambiguity and produce final 3D detections, achieving strong AP50/AP70 scores on the DAIR‑V2X dataset while keeping vehicle‑side BEV AP50 drop minimal under delay.

arXiv Computer Vision
Oct 21

CLOSER: Evidence-Aware Active Visual Verification for Embodied Object-Goal Navigation

CLOSER is an evidence‑aware active visual verification framework for embodied object‑goal navigation. It fine‑tunes a vision‑language model to label each view of a tracked candidate as target, non‑target, or uncertain, then selects complementary views using an embedding‑based diversity gate and fuses their probabilities with a lightweight network. When uncertainty remains, a diffusion policy directs the agent toward the candidate using only the tracked mask and depth until a decisive judgment is reached.

By Pengying Wu, Mingye Jiang, Yunze Hu, Zhejia Wen, Kangjie Zhou, Zongru Yang, Zhe Peng, Chang Liu
arXiv AI
Aug 11

CMU-Drive and V2V-VLA: Cooperative Multi-agent Unified Driving with Reasoning Benchmark and Vehicle-to-Vehicle Vision-Language-Action Models

arXiv:2608. 07621v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have recently achieved impressive performance for end-to-end autonomous driving, yet existing approaches are primarily designed for an individual single autonomous driving agent with limited support for cooperative perception, reasoning, and planning.

By Hsu-kuang Chiu, Stephen F. Smith
arXiv AI
Jul 7

BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations

arXiv:2603. 06576v2 Announce Type: replace-cross Abstract: The integration of Large Language Models (LLMs) into autonomous driving has attracted growing interest for their strong reasoning and semantic understanding abilities, which are essential for handling complex decision-making and long-tail scenarios.

By Thomas Monninger, Shaoyuan Xie, Qi Alfred Chen, Sihao Ding
arXiv Computer Vision
Aug 31

When the City Teaches the Car: Label-Free 3D Perception from Infrastructure

The paper proposes a label‑free 3D perception framework where roadside units (RSUs) act as unsupervised teachers for self‑driving cars. RSUs learn local 3D detectors from unlabeled data and broadcast predictions to passing vehicles, which use these as pseudo‑labels to train an ego‑centric detector. In a CARLA simulation, the method achieves 82.3% AP for vehicle detection, approaching a fully supervised upper bound of 94.4%, and demonstrates scalability and complementarity with existing ego‑centric approaches.

By Zhen Xu, Jinsu Yoo, Cristian Bautista, Zanming Huang, Tai-Yu Pan, Zhenzhen Liu, Katie Z Luo, Mark Campbell, Bharath Hariharan, Wei-Lun Chao
arXiv AI
Aug 10

Probing Visual Concepts in Lightweight Vision-Language Models for Automated Driving

arXiv:2603. 06054v2 Announce Type: replace-cross Abstract: The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their reasoning and generalisation capabilities to handle long-tail scenarios.

By Nikos Theodoridis, Reenu Mohandas, Ganesh Sistu, Anthony Scanlan, Ciar\'an Eising, Tim Brophy
arXiv AI
Aug 5

Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs

arXiv:2608. 01755v2 Announce Type: replace Abstract: Recent Vision-Language-Action (VLA) models for autonomous driving (AD) increasingly utilize chain-of-thought (CoT) supervision to enhance the reasoning capabilities of their Vision-Language Model (VLM) components, yet existing annotation pipelines commonly expose the teacher model to the logged ground-truth (GT) future trajectory.

By Zixuan Huang, Yang Zhou, Kaixuan Wang, Guli Zhang, Hongyan Xie, Yakun Zhu, Hao Geng, Xiaozhi Chen, Yikun Ban, Deqing Wang
arXiv AI
3d ago

Can MLLMs Reason over Surround-View Driving Videos? A Multi-View Autonomous Driving QA Benchmark

The paper introduces MVDriveBench, a benchmark for evaluating Multimodal Large Language Models (MLLMs) on surround‑view driving video understanding. It features synchronized multi‑view inputs, spatio‑temporal reasoning tasks, and 12 QA categories spanning perception to decision‑making. Experiments on 23 MLLMs show limited surround‑view reasoning, and closed‑loop tests link better reasoning to improved driving performance.

By Shunming Liu, Jianyi Peng, Cheng Li, Lu Hou, Pei Huang, Yajing Sun, Huaxiao Liu
arXiv AI
3d ago

From Foundation VLM to Versatile Driving VLM: A Triplet Incremental Training Approach

The paper introduces the Triplet Incremental Training Framework, a non‑intrusive method that adds 3D geometric awareness to general Vision‑Language Models (VLMs) for autonomous driving. By training on automatically generated (image, depth, QA) triplets, the framework uses an auxiliary depth stream to guide the VLM’s visual backbone while a frozen twin stream prevents semantic drift. The depth branch is removed at inference, yielding zero overhead, and the resulting model outperforms state‑of‑the‑art driving VLMs while preserving general reasoning abilities.

By Shengtao Wu, Zichao Dong, Weixuan Qiao, Xiaolu Liu, Xin Zhan, Junbo Chen, Jianke Zhu