相关论文: Flow-based Intrinsic Curiosity Module

Scene flow estimation, which aims to predict per-point 3D displacements of dynamic scenes, is a fundamental task in the computer vision field. However, previous works commonly suffer from unreliable correlation caused by locally constrained…

Deep reinforcement learning (DRL) provides a promising way for intelligent agents (e.g., autonomous vehicles) to learn to navigate complex scenarios. However, DRL with neural networks as function approximators is typically considered a…

Several deep learning (DL) approaches have been proposed to deal with image classification tasks. However, despite their effectiveness, they lack interpretability, as they are unable to explain or justify their results. To address the…

Conveying complex objectives to reinforcement learning (RL) agents often requires meticulous reward engineering. Preference-based RL methods are able to learn a more flexible reward model based on human preferences by actively incorporating…

Self-supervised multi-frame methods have currently achieved promising results in depth estimation. However, these methods often suffer from mismatch problems due to the moving objects, which break the static assumption. Additionally,…

This work proposes a novel approach to 4D radar-based scene flow estimation via cross-modal learning. Our approach is motivated by the co-located sensing redundancy in modern autonomous vehicles. Such redundancy implicitly provides various…

Control of legged robots is a challenging problem that has been investigated by different approaches, such as model-based control and learning algorithms. This work proposes a novel Imitating and Finetuning Model Predictive Control (IFM)…

Flow Matching (FM) has shown remarkable ability in modeling complex distributions and achieves strong performance in offline imitation learning for cloning expert behaviors. However, despite its behavioral cloning expressiveness, FM-based…

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…

Effectively exploring the environment is a key challenge in reinforcement learning (RL). We address this challenge by defining a novel intrinsic reward based on a foundation model, such as contrastive language image pretraining (CLIP),…

The FitzHugh-Nagumo (FHN) model, from computational neuroscience, has attracted attention in nonlinear dynamics studies as it describes the behavior of excitable systems and exhibits interesting bifurcation properties. The accurate…

Deep Reinforcement Learning (DRL) has recently been proposed as a methodology to discover complex Active Flow Control (AFC) strategies [Rabault, J., Kuchta, M., Jensen, A., Reglade, U., & Cerardi, N. (2019): "Artificial neural networks…

Dimensionality reduction (DR) plays a vital role in the visual analysis of high-dimensional data. One main aim of DR is to reveal hidden patterns that lie on intrinsic low-dimensional manifolds. However, DR often overlooks important…

Flow models have rapidly become the go-to method for training and deploying large-scale generators, owing their success to inference-time flexibility via adjustable integration steps. A crucial ingredient in flow training is the choice of…

This paper focuses on the active flow control (AFC) of the flow over a circular cylinder with synthetic jets through deep reinforcement learning (DRL) by implementing a reward function based on dynamic mode decomposition (DMD). As a main…

Deep Reinforcement Learning (DRL) has achieved remarkable success in sequential decision-making problems. However, existing DRL agents make decisions in an opaque fashion, hindering the user from establishing trust and scrutinizing…

The interpretation of ego motion and scene change is a fundamental task for mobile robots. Optical flow information can be employed to estimate motion in the surroundings. Recently, unsupervised optical flow estimation has become a research…

Many scenes in real life can be abstracted to the sparse reward visual scenes, where it is difficult for an agent to tackle the task under the condition of only accepting images and sparse rewards. We propose to decompose this problem into…

Class-incremental learning (CIL) is typically evaluated under predefined schedules with equal-sized tasks, leaving more realistic and complex cases unexplored. However, a practical CIL system should learns immediately when any number of new…

To realize efficient computational fluid dynamics (CFD) prediction of two-phase flow, a multi-scale framework was proposed in this paper by applying a physics-guided data-driven approach. Instrumental to this framework, Feature Similarity…