Related papers: UniFuture: A 4D Driving World Model for Future Gen…
Recently, world-action models (WAM) have emerged to bridge vision-language-action (VLA) models and world models, unifying their reasoning and instruction-following capabilities and spatio-temporal world modeling. However, existing WAM…
Enabling embodied agents to imagine future states is essential for robust and generalizable visual navigation. Yet, state-of-the-art systems typically rely on modular designs that decouple navigation planning from visual world modeling,…
Image fusion aims to integrate complementary information from multiple source images to produce a more informative and visually consistent representation, benefiting both human perception and downstream vision tasks. Despite recent…
We propose DriveAnyMesh, a method for driving mesh guided by monocular video. Current 4D generation techniques encounter challenges with modern rendering engines. Implicit methods have low rendering efficiency and are unfriendly to…
We propose UniMo, an innovative autoregressive model for joint modeling of 2D human videos and 3D human motions within a unified framework, enabling simultaneous generation and understanding of these two modalities for the first time.…
World models serve as essential building blocks toward Artificial General Intelligence (AGI), enabling intelligent agents to predict future states and plan actions by simulating complex physical interactions. However, existing interactive…
Recent advancements in world models have revolutionized dynamic environment simulation, allowing systems to foresee future states and assess potential actions. In autonomous driving, these capabilities help vehicles anticipate the behavior…
Understanding and replicating the real world is a critical challenge in Artificial General Intelligence (AGI) research. To achieve this, many existing approaches, such as world models, aim to capture the fundamental principles governing the…
Recent breakthroughs in autonomous driving have been propelled by advances in robust world modeling, fundamentally transforming how vehicles interpret dynamic scenes and execute safe decision-making. World models have emerged as a linchpin…
Existing latent world models for autonomous driving have opened a promising path toward future-aware driving intelligence. However, they typically treat future latent states as prediction targets or auxiliary signals, rather than directly…
Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally. Despite rapid progress, the field still lacks a unified way…
We present LidarDM, a novel LiDAR generative model capable of producing realistic, layout-aware, physically plausible, and temporally coherent LiDAR videos. LidarDM stands out with two unprecedented capabilities in LiDAR generative…
Motion planning is a critical component of autonomous vehicle decision-making systems, directly determining trajectory safety and driving efficiency. While deep learning approaches have advanced planning capabilities, existing methods…
Accurate modeling of surface pressure fields around objects is fundamental to aerodynamic analysis and design. While neural networks have shown promise as efficient alternatives to expensive Computational Fluid Dynamics (CFD) simulations,…
In this work, we introduce \textbf{XSIM}, a sensor simulation framework for autonomous driving. XSIM extends 3DGUT splatting with a generalized rolling-shutter modeling tailored for autonomous driving applications. Our framework provides a…
Unified models (UMs) hold promise for their ability to understand and generate content across heterogeneous modalities. Compared to merely generating visual content, the use of UMs for interleaved cross-modal reasoning is more promising and…
LiDAR scene flow is the task of estimating per-point 3D motion between consecutive point clouds. Recent methods achieve centimeter-level accuracy on popular autonomous vehicle (AV) datasets, but are typically only trained and evaluated on a…
Synthesizing photo-realistic visual observations from an ego vehicle's driving trajectory is a critical step towards scalable training of self-driving models. Reconstruction-based methods create 3D scenes from driving logs and synthesize…
This paper introduces UniGen, a novel approach to generating new traffic scenarios for evaluating and improving autonomous driving software through simulation. Our approach models all driving scenario elements in a unified model: the…
Autonomous vehicles need to perceive not only physical elements in the driving scene, such as lane lines and traffic lights, but also logical elements like lane centerlines and their topology. Existing lane topology reasoning methods…