Jingyu Qian

Yihan Hu, Siqi Chai, Zhening Yang et al.

As autonomous driving systems being deployed to millions of vehicles, there is a pressing need of improving the system's scalability, safety and reducing the engineering cost. A realistic, scalable, and practical simulator of the driving world is highly desired. In this paper, we present an efficient solution based on generative models which learns the dynamics of the driving scenes. With this model, we can not only simulate the diverse futures of a given driving scenario but also generate a variety of driving scenarios conditioned on various prompts. Our innovative design allows the model to operate in both full-Autoregressive and partial-Autoregressive modes, significantly improving inference and training speed without sacrificing generative capability. This efficiency makes it ideal for being used as an online reactive environment for reinforcement learning, an evaluator for planning policies, and a high-fidelity simulator for testing. We evaluated our model against two real-world datasets: the Waymo motion dataset and the nuPlan dataset. On the simulation realism and scene generation benchmark, our model achieves the state-of-the-art performance. And in the planning benchmarks, our planner outperforms the prior arts. We conclude that the proposed generative model may serve as a foundation for a variety of motion planning tasks, including data generation, simulation, planning, and online training. Source code is public at https://github.com/HorizonRobotics/GUMP/

Yihan Hu, Kun Li, Pingyuan Liang et al.

This paper presents our 2nd place solution for the NuPlan Challenge 2023. Autonomous driving in real-world scenarios is highly complex and uncertain. Achieving safe planning in the complex multimodal scenarios is a highly challenging task. Our approach, Imitation with Spatial-Temporal Heatmap, adopts the learning form of behavior cloning, innovatively predicts the future multimodal states with a heatmap representation, and uses trajectory refinement techniques to ensure final safety. The experiment shows that our method effectively balances the vehicle's progress and safety, generating safe and comfortable trajectories. In the NuPlan competition, we achieved the second highest overall score, while obtained the best scores in the ego progress and comfort metrics.

Yihan Hu, Wenxin Shao, Bo Jiang et al.

In this report, we introduce our solution to the Occupancy and Flow Prediction challenge in the Waymo Open Dataset Challenges at CVPR 2022, which ranks 1st on the leaderboard. We have developed a novel hierarchical spatial-temporal network featured with spatial-temporal encoders, a multi-scale aggregator enriched with latent variables, and a recursive hierarchical 3D decoder. We use multiple losses including focal loss and modified flow trace loss to efficiently guide the training process. Our method achieves a Flow-Grounded Occupancy AUC of 0.8389 and outperforms all the other teams on the leaderboard.

Baolu Li, Jingyu Qian, Rui Guo et al.

Physical world knowledge resides mainly in videos. Equipping Vision-Language-Action (VLA) models with such knowledge is fundamental for safe and generalizable planning. Predictive world modeling enables VLA to internalize physical dynamics and long-term causality by predicting future video from past observations. However, naive next-frame prediction faces two challenges: 1) unlike semantically distinct text tokens, video tokens are low-entropy and redundant, causing prediction to degenerate into trivial extrapolation. 2) world modeling poses a temporal dilemma: dense prediction captures instantaneous dynamics, but cannot efficiently model long-horizon causality. To learn world knowledge effectively, we introduce X-Foresight, a predictive world model integrated directly into the VLA architecture to jointly learn world modeling and real-time action control. At its core lies a long-horizon chunk-wise auto-regressive strategy that addresses both challenges: by predicting semantically distant chunks rather than adjacent frames, it escapes trivial extrapolation, while preserving dense intra-chunk frames for instantaneous dynamics and sparse inter-chunk transitions for long-term causality. A curriculum learning schedule progressively extends prediction horizons and stabilizes long-horizon training. To capture long-term causality effectively, we present temporal importance sampling, which concentrates supervision on safety-critical chunks identified by ego-motion and behavioral signals. We further delegate photorealistic synthesis to a diffusion-based multi-view renderer, improving photorealistic appearance. Comprehensive experiments demonstrate that X-Foresight significantly outperforms VLA baselines in planning performance while maintaining strong generative fidelity, establishing a robust paradigm for world-knowledge-driven autonomous systems.

Berkay Kaplan, Jingyu Qian

Software engineers regularly use JavaScript and Python for both front-end and back-end automation tasks. On top of JavaScript and Python, there are several frameworks to facilitate automation tasks further. Some of these frameworks are Node Manager Package (npm) and Python Package Index (PyPi), which are open source (OS) package libraries. The public registries npm and PyPi use to host packages allow any user with a verified email to publish code. The lack of a comprehensive scanning tool when publishing to the registry creates security concerns. Users can report malicious code on the registry; however, attackers can still cause damage until they remove their tool from the platform. Furthermore, several packages depend on each other, making them more vulnerable to a bad package in the dependency tree. The heavy code reuse creates security artifacts developers have to consider, such as the package reach. This project will illustrate a high-level overview of common risks associated with OS registries and the package dependency structure. There are several attack types, such as typosquatting and combosquatting, in the OS package registries. Outdated packages pose a security risk, and we will examine the extent of technical lag present in the npm environment. In this paper, our main contribution consists of a survey of common threats in OS registries. Afterward, we will offer countermeasures to mitigate the risks presented. These remedies will heavily focus on the applications of Machine Learning (ML) to detect suspicious activities. To the best of our knowledge, the ML-focused countermeasures are the first proposed possible solutions to the security problems listed. In addition, this project is the first survey of threats in npm and PyPi, although several studies focus on a subset of threats.

Hadjer Benkraouda, Jingyu Qian, Hung Quoc Tran et al.

With the rapid development of machine learning for image classification, researchers have found new applications of visualization techniques in malware detection. By converting binary code into images, researchers have shown satisfactory results in applying machine learning to extract features that are difficult to discover manually. Such visualization-based malware detection methods can capture malware patterns from many different malware families and improve malware detection speed. On the other hand, recent research has also shown adversarial attacks against such visualization-based malware detection. Attackers can generate adversarial examples by perturbing the malware binary in non-reachable regions, such as padding at the end of the binary. Alternatively, attackers can perturb the malware image embedding and then verify the executability of the malware post-transformation. One major limitation of the first attack scenario is that a simple pre-processing step can remove the perturbations before classification. For the second attack scenario, it is hard to maintain the original malware's executability and functionality. In this work, we provide literature review on existing malware visualization techniques and attacks against them. We summarize the limitation of the previous work, and design a new adversarial example attack against visualization-based malware detection that can evade pre-processing filtering and maintain the original malware functionality. We test our attack on a public malware dataset and achieve a 98% success rate.