Related papers: PAINET: A Principled Efficient Transformer for 3D …

The existing physical-informed Deep Operator Networks are mostly based on either the well-known mathematical formula of the system or huge amounts of data for different scenarios. However, in some cases, it is difficult to get the exact…

Predicting the dynamics of complex systems is crucial for various scientific and engineering applications. The accuracy of predictions depends on the model's ability to capture the intrinsic dynamics. While existing methods capture key…

Rotation equivariance is a desirable property in many practical applications such as motion forecasting and 3D perception, where it can offer benefits like sample efficiency, better generalization, and robustness to input perturbations.…

Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models…

All-in-one image restoration tackles different types of degradations with a unified model instead of having task-specific, non-generic models for each degradation. The requirement to tackle multiple degradations using the same model can…

Deep Operator Networks (DeepONets) and their physics-informed variants have shown significant promise in learning mappings between function spaces of partial differential equations, enhancing the generalization of traditional neural…

Learning-based simulators show great potential for simulating particle dynamics when 3D groundtruth is available, but per-particle correspondences are not always accessible. The development of neural rendering presents a new solution to…

We present EWareNet, a novel intent and affect-aware social robot navigation algorithm among pedestrians. Our approach predicts the trajectory-based pedestrian intent from gait sequence, which is then used for intent-guided navigation…

Many processes in biology and drug discovery involve various 3D interactions between molecules, such as protein and protein, protein and small molecule, etc. Given that different molecules are usually represented in different granularity,…

Physics-Informed Neural Networks (PINNs) have enabled significant improvements in modelling physical processes described by partial differential equations (PDEs). PINNs are based on simple architectures, and learn the behavior of complex…

While Physics-Based Simulation (PBS) can accurately drape a 3D garment on a 3D body, it remains too costly for real-time applications, such as virtual try-on. By contrast, inference in a deep network, requiring a single forward pass, is…

Humans naturally perceive a 3D scene in front of them through accumulation of information obtained from multiple interconnected projections of the scene and by interpreting their correspondence. This phenomenon has inspired artificial…

Dynamic computation has emerged as a promising avenue to enhance the inference efficiency of deep networks. It allows selective activation of computational units, leading to a reduction in unnecessary computations for each input sample.…

Transformer-based language models utilize the attention mechanism for substantial performance improvements in almost all natural language processing (NLP) tasks. Similar attention structures are also extensively studied in several other…

Physics-informed Machine Learning has recently become attractive for learning physical parameters and features from simulation and observation data. However, most existing methods do not ensure that the physics, such as balance laws (e.g.,…

In this paper, we introduce a deep learning solution for video activity recognition that leverages an innovative combination of convolutional layers with a linear-complexity attention mechanism. Moreover, we introduce a novel quantization…

Neural operators have emerged as powerful tools for learning nonlinear mappings between function spaces, enabling real-time prediction of complex dynamics in diverse scientific and engineering applications. With their growing adoption in…

Understanding and predicting video content is essential for planning and reasoning in dynamic environments. Despite advancements, unsupervised learning of object representations and dynamics remains challenging. We present VideoPCDNet, an…

This article trained a network for perceiving three-dimensional motion information of binocular vision target, which can provide real-time three-dimensional coordinate, velocity, and acceleration, and has a basic spatiotemporal perception…

3D scene understanding from point clouds plays a vital role for various robotic applications. Unfortunately, current state-of-the-art methods use separate neural networks for different tasks like object detection or room layout estimation.…