相关论文: ALIGN: A Vision-Language Framework for High-Accura…

Multi-view 3D visual grounding is critical for autonomous driving vehicles to interpret natural languages and localize target objects in complex environments. However, existing datasets and methods suffer from coarse-grained language…

Video-based spatial reasoning -- such as estimating distances, judging directions, or understanding layouts from multiple views -- requires selecting informative frames and, when needed, actively seeking additional viewpoints during…

Localizing objects and parts from natural language in 3D space is essential for robotics, AR, and embodied AI, yet existing methods face a trade-off between the accuracy and geometric consistency of per-scene optimization and the efficiency…

Driver visual attention prediction is a critical task in autonomous driving and human-computer interaction (HCI) research. Most prior studies focus on estimating attention allocation at a single moment in time, typically using static RGB…

Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited. We find this limitation is partially attributable to a reasoning-answer hit gap,…

Integrating large language models (LLMs) into embodied AI models is becoming increasingly prevalent. However, existing zero-shot LLM-based Vision-and-Language Navigation (VLN) agents either encode images as textual scene descriptions,…

Visual-language grounding aims to establish semantic correspondences between natural language and visual entities, enabling models to accurately identify and localize target objects based on textual instructions. Existing VLG approaches…

Recent advances in Multimodal Large Language Models (MLLMs) have achieved remarkable progress in general domains and demonstrated promise in multimodal mathematical reasoning. However, applying MLLMs to geometry problem solving (GPS)…

This paper introduces a multi-agent framework for comprehensive highway scene understanding, designed around a mixture-of-experts strategy. In this framework, a large generic vision-language model (VLM), such as GPT-4o, is contextualized…

Open-vocabulary grounding requires accurate vision-language alignment under weak supervision, yet existing methods either rely on global sentence embeddings that lack fine-grained expressiveness or introduce token-level alignment with…

Understanding and addressing corner cases is essential for ensuring the safety and reliability of autonomous driving systems. Vision-language models (VLMs) play a crucial role in enhancing scenario comprehension, yet they face significant…

Referential grounding in outdoor driving scenes is challenging due to large scene variability, many visually similar objects, and dynamic elements that complicate resolving natural-language references (e.g., "the black car on the right").…

End-to-end autonomous driving has emerged as a promising approach to unify perception, prediction, and planning within a single framework, reducing information loss and improving adaptability. However, existing methods often rely on fixed…

Rapid advances in multimodal models demand benchmarks that rigorously evaluate understanding and reasoning in safety-critical, dynamic real-world settings. We present AccidentBench, a large-scale benchmark that combines vehicle accident…

Traffic forecasting represents a crucial problem within intelligent transportation systems. In recent research, Large Language Models (LLMs) have emerged as a promising method, but their intrinsic design, tailored primarily for sequential…

Efficient target localization and autonomous navigation in complex environments are fundamental to real-world embodied applications. While recent advances in multimodal foundation models have enabled zero-shot object goal navigation,…

Despite the promise of Retrieval-Augmented Generation in grounding Multimodal Large Language Models with external knowledge, the transition to extensive contexts often leads to significant attention dilution and reasoning hallucinations.…

Safety on roads is of uttermost importance, especially in the context of autonomous vehicles. A critical need is to detect and communicate disruptive incidents early and effectively. In this paper we propose a system based on an…

Equitable urban transportation applications require high-fidelity digital representations of the built environment: not just streets and sidewalks, but bike lanes, marked and unmarked crossings, curb ramps and cuts, obstructions, traffic…

Current Large Language Models have achieved Olympiad-level logic, yet Vision-Language Models paradoxically falter on elementary spatial tasks like block counting. This capability mismatch reveals a critical ``spatial intelligence gap,''…