32 citations · 34 across the 27 of their papers we have counts for
31 papers
Orbia: Do Generated Videos Form a Consistent 3D World?
Dongyue Lu, Guian Fang, Hur Lim +20
Video generators serve as interactive worlds for exploration and simulation, yet realistic and visually appealing frames do not necessarily depict a consistent 3D world. Existing b…
A Query Is Not a Commitment: Learning to Correct Expert Answers in Online Deferral
Yannis Montreuil, Axel Carlier, Lai Xing Ng +1
An inaccurate expert can still provide useful information after correction. We study online learning to defer in which the learner chooses an expert and fixes a correction function…
EventDrive: Event Cameras for Vision-Language Driving Intelligence
Dongyue Lu, Rong Li, Ao Liang +6
Event cameras sense the world through asynchronous brightness changes with microsecond latency and high dynamic range, offering motion fidelity far beyond frame-based sensors and c…
Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer
Yannis Montreuil, Axel Carlier, Lai Xing Ng +1
A learning-to-defer (L2D) system decides, for each input, whether to predict on its own or to hand it to one of several available experts. The very well established recipe trains c…
Is Your Driving World Model an All-Around Player?
Lingdong Kong, Ao Liang, Tianyi Yan +20
Today's driving world models can generate remarkably realistic dash-cam videos, yet no single model excels universally. Some generate photorealistic textures but violate basic phys…
Online Learning-to-Defer with Varying Experts
Dang Hoang Duy, Yannis Montreuil, Maxime Meyer +3
Learning-to-Defer (L2D) methods route each query either to a predictive model or to external experts. Real-world deployments require handling streaming data, changing expert availa…
Consistent Learning-to-Defer with Expert-Conditional Advice
Yannis Montreuil, Leïna Montreuil, Axel Carlier +2
We introduce learning-to-defer with advice, a new setting in which a system learns both which expert should handle an input and which information that expert should receive. The po…
The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms
Lingdong Kong, Shaoyuan Xie, Zeying Gong +135
Autonomous systems are increasingly deployed in open and dynamic environments -- from city streets to aerial and indoor spaces -- where perception models must remain reliable under…
Learning-to-Defer in Non-Stationary Time Series via Switching State-Space Models
Yannis Montreuil, Letian Yu, Axel Carlier +2
Learning-to-defer (L2D) lets a predictor decide, at each round, whether to issue its own forecast or pay for an expert's. In non-stationary time series this decision must keep adap…
SCAR-GS: Spatial Context Attention for Residuals in Progressive Gaussian Splatting
Diego Revilla, Pooja Suresh, Ooi Wei Tsang +1
Recent advances in 3D Gaussian Splatting have allowed for real-time, high-fidelity novel view synthesis. Nonetheless, these models have significant storage requirements for large a…
Learning to Remove Lens Flare in Event Camera
Haiqian Han, Lingdong Kong, Jianing Li +7
Event cameras have the potential to revolutionize vision systems with their high temporal resolution and dynamic range, yet they remain susceptible to lens flare, a fundamental opt…
WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World
Ao Liang, Lingdong Kong, Tianyi Yan +19
Generative world models are reshaping embodied AI, enabling agents to synthesize realistic 4D driving environments that look convincing but often fail physically or behaviorally. D…
See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting
Dongyue Lu, Ao Liang, Tianxin Huang +8
Immersive applications call for synthesizing spatiotemporal 4D content from casual videos without costly 3D supervision. Existing video-to-4D methods typically rely on manually ann…
Adversarial Robustness in One-Stage Learning-to-Defer
Yannis Montreuil, Letian Yu, Axel Carlier +2
Learning-to-Defer (L2D) enables hybrid decision-making by routing inputs either to a predictor or to external experts. While promising, L2D is highly vulnerable to adversarial pert…
Learning to Generate 4D LiDAR Sequences
Ao Liang, Youquan Liu, Yu Yang +5
While generative world models have advanced video and occupancy-based data synthesis, LiDAR generation remains underexplored despite its importance for accurate 3D perception. Exte…
Visual Grounding from Event Cameras
Lingdong Kong, Dongyue Lu, Ao Liang +6
Event cameras capture changes in brightness with microsecond precision and remain reliable under motion blur and challenging illumination, offering clear advantages for modeling hi…
3D and 4D World Modeling: A Survey
Lingdong Kong, Yu Yang, Jianbiao Mei +20
World modeling has become a cornerstone in AI research, enabling agents to understand, represent, and predict the dynamic environments they inhabit. While prior work largely emphas…
LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences
Ao Liang, Youquan Liu, Yu Yang +5
Generative world models have become essential data engines for autonomous driving, yet most existing efforts focus on videos or occupancy grids, overlooking the unique LiDAR proper…
Perspective-Invariant 3D Object Detection
Ao Liang, Lingdong Kong, Dongyue Lu +4
With the rise of robotics, LiDAR-based 3D object detection has garnered significant attention in both academia and industry. However, existing datasets and methods predominantly fo…
Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras
Lingdong Kong, Dongyue Lu, Ao Liang +6
Event cameras offer microsecond-level latency and robustness to motion blur, making them ideal for understanding dynamic environments. Yet, connecting these asynchronous streams to…
One-Stage Top- Learning-to-Defer: Score-Based Surrogates with Theoretical Guarantees
Yannis Montreuil, Axel Carlier, Lai Xing Ng +1
We introduce the first one-stage Top- Learning-to-Defer framework, which unifies prediction and deferral by learning a shared score-based model that selects the most cost-ef…
Why Ask One When You Can Ask ? Learning-to-Defer to the Top- Experts
Yannis Montreuil, Axel Carlier, Lai Xing Ng +1
Existing Learning-to-Defer (L2D) frameworks are limited to single-expert deferral, forcing each query to rely on only one expert and preventing the use of collective expertise. We…
EventFly: Event Camera Perception from Ground to the Sky
Lingdong Kong, Dongyue Lu, Xiang Xu +3
Cross-platform adaptation in event-based dense perception is crucial for deploying event cameras across diverse settings, such as vehicles, drones, and quadrupeds, each with unique…
Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees
Yannis Montreuil, Axel Carlier, Lai Xing Ng +1
Two-stage Learning-to-Defer (L2D) enables optimal task delegation by assigning each input to either a fixed main model or one of several offline experts, supporting reliable decisi…