To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on collaboration if not removed. ...

Open-world 3D generation has recently attracted considerable attention. While many single-image-to-3D methods have yielded visually appealing outcomes, they often lack sufficient controllability and tend to produce hallucinated regions that may ...

To advance the state of the art in the creation of 3D foundation models, this paper introduces the ConDense framework for 3D pre-training utilizing existing pre-trained 2D networks and large-scale multi-view datasets. We propose a novel 2D-3D ...

Infrared and visible image fusion (IVIF) is a widely used approach to enhance scenario understanding, which fuses the salience of infrared images and the texture details of visible images. Existing methods typically focus on extracting local ...

Novel view synthesis from a sparse set of input images is a challenging problem of great practical interest, especially when camera poses are absent or inaccurate. Direct optimization of camera poses and usage of estimated depths in neural radiance ...

Drones have increasingly collaborated with human workers in some workspaces, such as warehouses. The failure of a drone flight may bring potential risks to human beings' life safety during some aerial tasks. One of the most common flight ...

Visuotactile sensors can provide rich contact information, having great potential in contact-rich manipulation tasks with reinforcement learning (RL) policies. Sim2Real technique tackles the challenge of RL's reliance on a large amount of ...

We introduce OpenShape, a method for learning multi-modal joint representations of text, image, and point clouds. We adopt the commonly used multi-modal contrastive learning framework for representation alignment, but with a specific focus on scaling up ...

We introduce OpenIllumination, a real-world dataset containing over 108K images of 64 objects with diverse materials, captured under 72 camera views and a large number of different illuminations. For each image in the dataset, we provide accurate camera ...

Large Language Models (LLMs) significantly benefit from Chain-of-Thought (CoT) prompting in performing various reasoning tasks. While CoT allows models to produce more comprehensive reasoning processes, its emphasis on intermediate reasoning steps can ...

Combining gradient-based trajectory optimization with differentiable physics simulation is an accurate and efficient technique for solving soft-body manipulation problems. Using a well-crafted optimization objective, the solver can quickly converge onto ...

Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance of 2D diffusion models but ...

Manga is a fashionable Japanese-style comic form that is composed of black-and-white strokes and is generally displayed as raster images on digital devices. Typical mangas have simple textures, wide lines, and few color gradients, which are vectorizable ...

Learning-based stereo methods usually require a large scale dataset with depth, however obtaining accurate depth in the real domain is difficult, but groundtruth depth is readily available in the simulation domain. In this article we propose a new ...

How to implement the construction of hardware course group for complex engineering problems in the context of the New engineering education certification in China, taking the cultivation of Computer System Capability as an example, through a series of ...

We present Dictionary Fields, a novel neural representation which decomposes a signal into a product of factors, each represented by a classical or neural field representation, operating on transformed input coordinates. More specifically, we factorize a ...

Training long-horizon robotic policies in complex physical environments is essential for many applications, such as robotic manipulation. However, learning a policy that can generalize to unseen tasks is challenging. In this work, we propose to achieve ...

We investigate the challenge of parametrizing policies for reinforcement learning (RL) in high-dimensional continuous action spaces. Our objective is to develop a multimodal policy that overcomes limitations inherent in the commonly-used Gaussian ...

In this paper, we examine the effectiveness of pretraining for visuo-motor control tasks. We revisit a simple Learning-from-Scratch (LfS) baseline that incorporates data augmentation and a shallow ConvNet, and find that this baseline is surprisingly ...

Traditionally, a firewall tracks the per-flow spread of each source and destination IP address to detect network scans and DDoS attacks. It is not designed with hierarchical IP addresses in mind. However, cyberattacks nowadays become more stealthy. To ...