Wenjie Luo

Yan Wang, Wenjie Luo, Junjie Bai et al. · nvidia

End-to-end architectures trained via imitation learning have advanced autonomous driving by scaling model size and data, yet performance remains brittle in safety-critical long-tail scenarios where supervision is sparse and causal understanding is limited. To address this, we introduce Alpamayo-R1 (AR1), a vision-language-action model (VLA) that integrates Chain of Causation reasoning with trajectory planning to enhance decision-making in complex driving scenarios. Our approach features three key innovations: (1) the Chain of Causation (CoC) dataset, built through a hybrid auto-labeling and human-in-the-loop pipeline producing decision-grounded, causally linked reasoning traces aligned with driving behaviors; (2) a modular VLA architecture combining Cosmos-Reason, a Vision-Language Model pre-trained for Physical AI applications, with a diffusion-based trajectory decoder that generates dynamically feasible plans in real time; (3) a multi-stage training strategy using supervised fine-tuning to elicit reasoning and reinforcement learning (RL) to optimize reasoning quality via large reasoning model feedback and enforce reasoning-action consistency. Evaluation shows AR1 achieves up to a 12% improvement in planning accuracy on challenging cases compared to a trajectory-only baseline, with a 35% reduction in off-road rate and 25% reduction in close encounter rate in closed-loop simulation. RL post-training improves reasoning quality by 45% as measured by a large reasoning model critic and reasoning-action consistency by 37%. Model scaling from 0.5B to 7B parameters shows consistent improvements. On-vehicle road tests confirm real-time performance (99 ms latency) and successful urban deployment. By bridging interpretable reasoning with precise control, AR1 demonstrates a practical path towards Level 4 autonomous driving. We plan to release AR1 models and a subset of the CoC in a future update.

Shuhan Tan, Kashyap Chitta, Yuxiao Chen et al.

Recent Vision-Language-Action (VLA) models for autonomous driving explore inference-time reasoning as a way to improve driving performance and safety in challenging scenarios. Most prior work uses natural language to express chain-of-thought (CoT) reasoning before producing driving actions. However, text may not be the most efficient representation for reasoning. In this work, we present Latent-CoT-Drive (LCDrive): a model that expresses CoT in a latent language that captures possible outcomes of the driving actions being considered. Our approach unifies CoT reasoning and decision making by representing both in an action-aligned latent space. Instead of natural language, the model reasons by interleaving (1) action-proposal tokens, which use the same vocabulary as the model's output actions; and (2) world model tokens, which are grounded in a learned latent world model and express future outcomes of these actions. We cold start latent CoT by supervising the model's action proposals and world model tokens based on ground-truth future rollouts of the scene. We then post-train with closed-loop reinforcement learning to strengthen reasoning capabilities. On a large-scale end-to-end driving benchmark, LCDrive achieves faster inference, better trajectory quality, and larger improvements from interactive reinforcement learning compared to both non-reasoning and text-reasoning baselines.

Naen Xu, Changjiang Li, Tianyu Du et al.

Text-to-image diffusion models have emerged as powerful tools for generating high-quality images from textual descriptions. However, their increasing popularity has raised significant copyright concerns, as these models can be misused to reproduce copyrighted content without authorization. In response, recent studies have proposed various copyright protection methods, including adversarial perturbation, concept erasure, and watermarking techniques. However, their effectiveness and robustness against advanced attacks remain largely unexplored. Moreover, the lack of unified evaluation frameworks has hindered systematic comparison and fair assessment of different approaches. To bridge this gap, we systematize existing copyright protection methods and attacks, providing a unified taxonomy of their design spaces. We then develop CopyrightMeter, a unified evaluation framework that incorporates 17 state-of-the-art protections and 16 representative attacks. Leveraging CopyrightMeter, we comprehensively evaluate protection methods across multiple dimensions, thereby uncovering how different design choices impact fidelity, efficacy, and resilience under attacks. Our analysis reveals several key findings: (i) most protections (16/17) are not resilient against attacks; (ii) the "best" protection varies depending on the target priority; (iii) more advanced attacks significantly promote the upgrading of protections. These insights provide concrete guidance for developing more robust protection methods, while its unified evaluation protocol establishes a standard benchmark for future copyright protection research in text-to-image generation.

Boris Ivanovic, Cristiano Saltori, Yurong You et al.

Autoregressive Transformers are increasingly being deployed as end-to-end robot and autonomous vehicle (AV) policy architectures, owing to their scalability and potential to leverage internet-scale pretraining for generalization. Accordingly, tokenizing sensor data efficiently is paramount to ensuring the real-time feasibility of such architectures on embedded hardware. To this end, we present an efficient triplane-based multi-camera tokenization strategy that leverages recent advances in 3D neural reconstruction and rendering to produce sensor tokens that are agnostic to the number of input cameras and their resolution, while explicitly accounting for their geometry around an AV. Experiments on a large-scale AV dataset and state-of-the-art neural simulator demonstrate that our approach yields significant savings over current image patch-based tokenization strategies, producing up to 72% fewer tokens, resulting in up to 50% faster policy inference while achieving the same open-loop motion planning accuracy and improved offroad rates in closed-loop driving simulations.

Sergio Casas, Wenjie Luo, Raquel Urtasun

In order to plan a safe maneuver, self-driving vehicles need to understand the intent of other traffic participants. We define intent as a combination of discrete high-level behaviors as well as continuous trajectories describing future motion. In this paper, we develop a one-stage detector and forecaster that exploits both 3D point clouds produced by a LiDAR sensor as well as dynamic maps of the environment. Our multi-task model achieves better accuracy than the respective separate modules while saving computation, which is critical to reducing reaction time in self-driving applications.

Wenyuan Zeng, Wenjie Luo, Simon Suo et al.

In this paper, we propose a neural motion planner (NMP) for learning to drive autonomously in complex urban scenarios that include traffic-light handling, yielding, and interactions with multiple road-users. Towards this goal, we design a holistic model that takes as input raw LIDAR data and a HD map and produces interpretable intermediate representations in the form of 3D detections and their future trajectories, as well as a cost volume defining the goodness of each position that the self-driving car can take within the planning horizon. We then sample a set of diverse physically possible trajectories and choose the one with the minimum learned cost. Importantly, our cost volume is able to naturally capture multi-modality. We demonstrate the effectiveness of our approach in real-world driving data captured in several cities in North America. Our experiments show that the learned cost volume can generate safer planning than all the baselines.

Wenjie Luo, Bin Yang, Raquel Urtasun

In this paper we propose a novel deep neural network that is able to jointly reason about 3D detection, tracking and motion forecasting given data captured by a 3D sensor. By jointly reasoning about these tasks, our holistic approach is more robust to occlusion as well as sparse data at range. Our approach performs 3D convolutions across space and time over a bird's eye view representation of the 3D world, which is very efficient in terms of both memory and computation. Our experiments on a new very large scale dataset captured in several north american cities, show that we can outperform the state-of-the-art by a large margin. Importantly, by sharing computation we can perform all tasks in as little as 30 ms.

Sean Segal, Eric Kee, Wenjie Luo et al.

In this paper, we tackle the problem of spatio-temporal tagging of self-driving scenes from raw sensor data. Our approach learns a universal embedding for all tags, enabling efficient tagging of many attributes and faster learning of new attributes with limited data. Importantly, the embedding is spatio-temporally aware, allowing the model to naturally output spatio-temporal tag values. Values can then be pooled over arbitrary regions, in order to, for example, compute the pedestrian density in front of the SDV, or determine if a car is blocking another car at a 4-way intersection. We demonstrate the effectiveness of our approach on a new large scale self-driving dataset, SDVScenes, containing 15 attributes relating to vehicle and pedestrian density, the actions of each actor, the speed of each actor, interactions between actors, and the topology of the road map.

Bin Yang, Wenjie Luo, Raquel Urtasun

We address the problem of real-time 3D object detection from point clouds in the context of autonomous driving. Computation speed is critical as detection is a necessary component for safety. Existing approaches are, however, expensive in computation due to high dimensionality of point clouds. We utilize the 3D data more efficiently by representing the scene from the Bird's Eye View (BEV), and propose PIXOR, a proposal-free, single-stage detector that outputs oriented 3D object estimates decoded from pixel-wise neural network predictions. The input representation, network architecture, and model optimization are especially designed to balance high accuracy and real-time efficiency. We validate PIXOR on two datasets: the KITTI BEV object detection benchmark, and a large-scale 3D vehicle detection benchmark. In both datasets we show that the proposed detector surpasses other state-of-the-art methods notably in terms of Average Precision (AP), while still runs at >28 FPS.

Wenjie Luo, Yujia Li, Raquel Urtasun et al.

We study characteristics of receptive fields of units in deep convolutional networks. The receptive field size is a crucial issue in many visual tasks, as the output must respond to large enough areas in the image to capture information about large objects. We introduce the notion of an effective receptive field, and show that it both has a Gaussian distribution and only occupies a fraction of the full theoretical receptive field. We analyze the effective receptive field in several architecture designs, and the effect of nonlinear activations, dropout, sub-sampling and skip connections on it. This leads to suggestions for ways to address its tendency to be too small.

Shenlong Wang, Min Bai, Gellert Mattyus et al.

In this paper we introduce the TorontoCity benchmark, which covers the full greater Toronto area (GTA) with 712.5 $km^2$ of land, 8439 $km$ of road and around 400,000 buildings. Our benchmark provides different perspectives of the world captured from airplanes, drones and cars driving around the city. Manually labeling such a large scale dataset is infeasible. Instead, we propose to utilize different sources of high-precision maps to create our ground truth. Towards this goal, we develop algorithms that allow us to align all data sources with the maps while requiring minimal human supervision. We have designed a wide variety of tasks including building height estimation (reconstruction), road centerline and curb extraction, building instance segmentation, building contour extraction (reorganization), semantic labeling and scene type classification (recognition). Our pilot study shows that most of these tasks are still difficult for modern convolutional neural networks.

Wenyuan Zeng, Wenjie Luo, Sanja Fidler et al.

Encoder-decoder models have been widely used to solve sequence to sequence prediction tasks. However current approaches suffer from two shortcomings. First, the encoders compute a representation of each word taking into account only the history of the words it has read so far, yielding suboptimal representations. Second, current decoders utilize large vocabularies in order to minimize the problem of unknown words, resulting in slow decoding times. In this paper we address both shortcomings. Towards this goal, we first introduce a simple mechanism that first reads the input sequence before committing to a representation of each word. Furthermore, we propose a simple copy mechanism that is able to exploit very small vocabularies and handle out-of-vocabulary words. We demonstrate the effectiveness of our approach on the Gigaword dataset and DUC competition outperforming the state-of-the-art.

Min Bai, Wenjie Luo, Kaustav Kundu et al.

We tackle the problem of estimating optical flow from a monocular camera in the context of autonomous driving. We build on the observation that the scene is typically composed of a static background, as well as a relatively small number of traffic participants which move rigidly in 3D. We propose to estimate the traffic participants using instance-level segmentation. For each traffic participant, we use the epipolar constraints that govern each independent motion for faster and more accurate estimation. Our second contribution is a new convolutional net that learns to perform flow matching, and is able to estimate the uncertainty of its matches. This is a core element of our flow estimation pipeline. We demonstrate the effectiveness of our approach in the challenging KITTI 2015 flow benchmark, and show that our approach outperforms published approaches by a large margin.