Related papers: MoFlow: One-Step Flow Matching for Human Trajector…

Generative motion prediction must satisfy three simultaneous requirements for real-world autonomy: high accuracy, diverse multimodal futures, and strictly bounded latency. Diffusion models meet the first two but violate the third, requiring…

Long-term trajectory forecasting is an important and challenging problem in the fields of computer vision, machine learning, and robotics. One fundamental difficulty stands in the evolution of the trajectory that becomes more and more…

Diffusion and flow matching have emerged as expressive policy classes in reinforcement learning, but their reliance on multi-step denoising imposes substantial computational overhead at inference time, which is particularly problematic in…

Human motion sensing plays a crucial role in smart systems for decision-making, user interaction, and personalized services. Extensive research that has been conducted is predominantly based on cameras, whose intrusive nature limits their…

Recent works have shown that optical flow can be learned by deep networks from unlabelled image pairs based on brightness constancy assumption and smoothness prior. Current approaches additionally impose an augmentation regularization term…

Human motion prediction is a cornerstone of human-robot collaboration (HRC), as robots need to infer the future movements of human workers based on past motion cues to proactively plan their motion, ensuring safety in close collaboration…

Diffusion-based models have recently shown strong performance in trajectory planning, as they are capable of capturing diverse, multimodal distributions of complex behaviors. A key limitation of these models is their slow inference speed,…

Simulating trajectories of dynamical systems is a fundamental problem in a wide range of fields such as molecular dynamics, biochemistry, and pedestrian dynamics. Machine learning has become an invaluable tool for scaling physics-based…

This paper introduces Smooth-Distill, a novel self-distillation framework designed to simultaneously perform human activity recognition (HAR) and sensor placement detection using wearable sensor data. The proposed approach utilizes a…

Few-step video generation has been significantly advanced by consistency distillation. However, the performance of consistency-distilled models often degrades as more sampling steps are allocated at test time, limiting their effectiveness…

Achieving high-fidelity and temporally smooth 3D human motion generation remains a challenge, particularly within resource-constrained environments. We introduce FlowMotion, a novel method leveraging Conditional Flow Matching (CFM).…

Synthesizing novel views of dynamic humans from stationary monocular cameras is a specialized but desirable setup. This is particularly attractive as it does not require static scenes, controlled environments, or specialized capture…

The future motion of traffic participants is inherently uncertain. To plan safely, therefore, an autonomous agent must take into account multiple possible trajectory outcomes and prioritize them. Recently, this problem has been addressed…

Recent advances in diffusion$/$flow-matching policies have enabled imitation learning of complex, multi-modal action trajectories. However, they are computationally expensive because they sample a trajectory of trajectories: a…

Humans can easily describe, imagine, and, crucially, predict a wide variety of behaviors of liquids--splashing, squirting, gushing, sloshing, soaking, dripping, draining, trickling, pooling, and pouring--despite tremendous variability in…

Flow Matching (FM) models achieve remarkable results in generative tasks. Building upon diffusion models, FM's simulation-free training paradigm enables simplicity and efficiency but introduces a train-inference gap: model outputs cannot be…

Atomic transport underpins the performance of materials in technologies such as energy storage and electronics, yet its simulation remains computationally demanding. In particular, modeling ionic diffusion in solid-state electrolytes (SSEs)…

We present a new method for making diffusion models faster to sample. The method distills many-step diffusion models into few-step models by matching conditional expectations of the clean data given noisy data along the sampling trajectory.…

Stochastic human motion prediction is critical for safe and effective human-robot collaboration (HRC) in industrial remanufacturing, as it captures human motion uncertainties and multi-modal behaviors that deterministic methods cannot…

We propose GoalFlow, an end-to-end autonomous driving method for generating high-quality multimodal trajectories. In autonomous driving scenarios, there is rarely a single suitable trajectory. Recent methods have increasingly focused on…