Imagen de Portada

Probing the Reliability of Driving VLMs: From Inconsistent Responses to Grounded Temporal Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chang, Chun-Peng, Wang, Chen-Yu, Caesar, Holger, Pagani, Alain
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Seeing Clearly, Forgetting Deeply: Revisiting Fine-Tuned Video Generators for Driving Simulation
por: Chang, Chun-Peng, et al.
Publicado: (2025)

Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
por: Chang, Chun-Peng, et al.
Publicado: (2026)

MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding
por: Chang, Chun-Peng, et al.
Publicado: (2024)

3D Spatial Understanding in MLLMs: Disambiguation and Evaluation
por: Chang, Chun-Peng, et al.
Publicado: (2024)

How Auxiliary Reasoning Unleashes GUI Grounding in VLMs
por: Li, Weiming, et al.
Publicado: (2025)

TAR-TVG: Enhancing VLMs with Timestamp Anchor-Constrained Reasoning for Temporal Video Grounding
por: Guo, Chaohong, et al.
Publicado: (2025)

ICP-Flow: LiDAR Scene Flow Estimation with ICP
por: Lin, Yancong, et al.
Publicado: (2024)

Offline Tracking with Object Permanence
por: Liu, Xianzhong, et al.
Publicado: (2023)

AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning
por: Jiang, Bo, et al.
Publicado: (2025)

Uni-SLAM: Uncertainty-Aware Neural Implicit SLAM for Real-Time Dense Indoor Scene Reconstruction
por: Wang, Shaoxiang, et al.
Publicado: (2024)

Cross-Domain Semantic Segmentation on Inconsistent Taxonomy using VLMs
por: Lim, Jeongkee, et al.
Publicado: (2024)

BikeScenes: Online LiDAR Semantic Segmentation for Bicycles
por: Goren, Denniz, et al.
Publicado: (2025)

ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs
por: Li, Jiangyang, et al.
Publicado: (2026)

Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding
por: Zheng, Zelin, et al.
Publicado: (2026)

Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives
por: Xie, Shaoyuan, et al.
Publicado: (2025)

nuScenes Revisited: Progress and Challenges in Autonomous Driving
por: Fong, Whye Kit, et al.
Publicado: (2025)

Are VLMs Ready for Lane Topology Awareness in Autonomous Driving?
por: Chen, Xin, et al.
Publicado: (2025)

4DRC-OCC: Robust Semantic Occupancy Prediction Through Fusion of 4D Radar and Camera
por: Ninfa, David, et al.
Publicado: (2026)

4D-RaDiff: Latent Diffusion for 4D Radar Point Cloud Generation
por: Kwok, Jimmie, et al.
Publicado: (2025)

BaSAL: Size-Balanced Warm Start Active Learning for LiDAR Semantic Segmentation
por: Wei, Jiarong, et al.
Publicado: (2023)

DPFT: Dual Perspective Fusion Transformer for Camera-Radar-based Object Detection
por: Fent, Felix, et al.
Publicado: (2024)

VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generation
por: Zhou, Zijian, et al.
Publicado: (2023)

Med-R2: An Adversarial Benchmark for Evidence-Grounded Reasoning in Medical VLMs
por: Ma, Wen, et al.
Publicado: (2026)

Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning
por: Li, Yue, et al.
Publicado: (2025)

NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving
por: Ljungbergh, William, et al.
Publicado: (2024)

Drive-KD: Multi-Teacher Distillation for VLMs in Autonomous Driving
por: Lian, Weitong, et al.
Publicado: (2026)

Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels
por: Zong, Yongshuo, et al.
Publicado: (2025)

LeAP: Consistent multi-domain 3D labeling using Foundation Models
por: Gebraad, Simon, et al.
Publicado: (2025)

A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs
por: Vaishnav, Mohit, et al.
Publicado: (2025)

ViFP: A Framework for Visual False Positive Detection to Enhance Reasoning Reliability in VLMs
por: Zhang, Ben, et al.
Publicado: (2025)

CLGRPO: Reasoning Ability Enhancement for Small VLMs
por: Wang, Fanyi, et al.
Publicado: (2025)

G3FA: Geometry-guided GAN for Face Animation
por: Javanmardi, Alireza, et al.
Publicado: (2024)

OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models
por: Zhou, Zijian, et al.
Publicado: (2024)

What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs
por: Lin, Jiaping, et al.
Publicado: (2026)

CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving
por: Song, Rui, et al.
Publicado: (2025)

VLMs Guided Interpretable Decision Making for Autonomous Driving
por: Hu, Xin, et al.
Publicado: (2025)

AsyncBEV: Cross-modal Flow Alignment in Asynchronous 3D Object Detection
por: Wang, Shiming, et al.
Publicado: (2026)

NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics
por: Lan, Jian, et al.
Publicado: (2026)

DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
por: Vo, Hao, et al.
Publicado: (2026)

Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers
por: Wang, Jiancheng, et al.
Publicado: (2026)