Related papers: MindDrive: A Vision-Language-Action Model for Auto…

Vision-language-action (VLA) models are emerging as embodied foundation models for robotic manipulation, but their deployment introduces a new unlearning challenge: removing unsafe, spurious, or privacy-sensitive behaviors without degrading…

The applications of Vision-Language Models (VLMs) in the field of Autonomous Driving (AD) have attracted widespread attention due to their outstanding performance and the ability to leverage Large Language Models (LLMs). By incorporating…

Recent work has begun to equip vision-language-action (VLA) policies with explicit intermediate reasoning. In embodied control, however, textual chain-of-thought is a poor fit: irrelevant or weakly textual information can interfere with…

Existing Vision-Language models (VLMs) estimate either long-term trajectory waypoints or a set of control actions as a reactive solution for closed-loop planning based on their rich scene comprehension. However, these estimations are coarse…

Visual-Language-Action (VLA) models represent a paradigm shift in embodied AI, yet existing frameworks often struggle with imprecise spatial perception, suboptimal multimodal fusion, and instability in reinforcement learning. To bridge…

Traditional autonomous driving systems often struggle with reasoning in complex, unexpected scenarios due to limited comprehension of spatial relationships. In response, this study introduces a Large Language Model (LLM)-based Autonomous…

Vision-Language-Action (VLA) models have gained much attention from the research community thanks to their strength in translating multimodal observations with linguistic instructions into desired robotic actions. Despite their…

Recent advances in Vision-Language-Action (VLA) models have shown promising capabilities in autonomous driving by leveraging the understanding and reasoning strengths of Large Language Models(LLMs).However, our empirical analysis reveals…

End-to-End autonomous driving (E2E-AD) has emerged as a new paradigm, where trajectory planning plays a crucial role. Existing studies mainly follow two directions: trajectory generation oriented, which focuses on producing high-quality…

Large language models (LLMs) as autonomous agents offer a novel avenue for tackling real-world challenges through a knowledge-driven manner. These LLM-enhanced methodologies excel in generalization and interpretability. However, the…

Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent…

Vision-language-action models (VLAs) have garnered significant attention for their potential in advancing robotic manipulation. However, previous approaches predominantly rely on the general comprehension capabilities of vision-language…

Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to…

A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments. Recent autoregressive vision-language-action (VLA)…

Large Vision Language Models (LVLMs) have shown strong capabilities in understanding and analyzing visual scenes across various domains. However, in the context of autonomous driving, their limited comprehension of 3D environments restricts…

In this paper, we propose GTA-VLA(Guide, Think, Act), an interactive Vision-Language-Action (VLA) framework that enables spatially steerable embodied reasoning by allowing users to guide robot policies with explicit visual cues. Existing…

Recent studies have explored leveraging the world knowledge and cognitive capabilities of Vision-Language Models (VLMs) to address the long-tail problem in end-to-end autonomous driving. However, existing methods typically formulate…

Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous…

Autonomous driving requires rich contextual comprehension and precise predictive reasoning to navigate dynamic and complex environments safely. Vision-Language Models (VLMs) and Driving World Models (DWMs) have independently emerged as…

Human drivers rely on commonsense reasoning to navigate diverse and dynamic real-world scenarios. Existing end-to-end (E2E) autonomous driving (AD) models are typically optimized to mimic driving patterns observed in data, without capturing…