Related papers: LAMP: Data-Efficient Linear Affine Weight-Space Mo…

Recently, a number of learning-based optimization methods that combine data-driven architectures with the classical optimization algorithms have been proposed and explored, showing superior empirical performance in solving various ill-posed…

The linear model uses the space defined by the input to project the target or desired signal and find the optimal set of model parameters. When the problem is nonlinear, the adaption requires nonlinear models for good performance, but it…

Learning to build 3D scene graphs is essential for real-world perception in a structured and rich fashion. However, previous 3D scene graph generation methods utilize a fully supervised learning manner and require a large amount of…

Although semi-dense Simultaneous Localization and Mapping (SLAM) has been becoming more popular over the last few years, there is a lack of efficient methods for representing and processing their large scale point clouds. In this paper, we…

Efficiently solving Optimal Power Flow (OPF) problems in power systems is crucial for operational planning and grid management. There is a growing need for scalable algorithms capable of handling the increasing variability, constraints, and…

Video Frame Interpolation (VFI) is a crucial technique in various applications such as slow-motion generation, frame rate conversion, video frame restoration etc. This paper introduces an efficient video frame interpolation framework that…

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment.…

LiDAR-based SLAM algorithms are extensively studied to providing robust and accurate positioning for autonomous driving vehicles (ADV) in the past decades. Satisfactory performance can be obtained using high-grade 3D LiDAR with 64 channels,…

Foundation models for 3D shape generation have recently shown a remarkable capacity to encode rich geometric priors across both global and local dimensions. However, leveraging these priors for downstream tasks can be challenging as…

The increasing popularity of deep learning models has created new opportunities for developing AI-based recommender systems. Designing recommender systems using deep neural networks requires careful architecture design, and further…

Synthesizing 3D scenes from open-vocabulary text descriptions is a challenging, important, and recently-popular application. One of its critical subproblems is layout generation: given a set of objects, lay them out to produce a scene…

Consistency Models (CMs) have significantly accelerated the sampling process in diffusion models, yielding impressive results in synthesizing high-resolution images. To explore and extend these advancements to point-cloud-based 3D shape…

Large Language Models (LLMs) are increasingly applied to tasks involving structured inputs such as graphs. Abstract Meaning Representations (AMRs), which encode rich semantics as directed graphs, offer a rigorous testbed for evaluating LLMs…

Autoregressive (AR) models have achieved remarkable success in natural language and image generation, but their application to 3D shape modeling remains largely unexplored. Unlike diffusion models, AR models enable more efficient and…

Large-scale AI models, such as Large Language Models (LLMs) and Diffusion Models (DMs), have grown rapidly in size, creating significant challenges for efficient deployment on resource-constrained hardware. In this paper, we introduce…

Deep neural networks (DNNs) typically employ an end-to-end (E2E) training paradigm which presents several challenges, including high GPU memory consumption, inefficiency, and difficulties in model parallelization during training. Recent…

Vision transformer family has dominated the satellite pan-sharpening field driven by the global-wise spatial information modeling mechanism from the core self-attention ingredient. The standard modeling rules within these promising…

Unsupervised generation of high-quality multi-view-consistent images and 3D shapes using only collections of single-view 2D photographs has been a long-standing challenge. Existing 3D GANs are either compute-intensive or make approximations…

We propose an approach to synthesize linear feedback controllers for linear systems in polygonal environments. Our method focuses on designing a robust controller that can account for uncertainty in measurements. Its inputs are provided by…

Deep learning (DL) is the state-of-the-art methodology in various medical image segmentation tasks. However, it requires relatively large amounts of manually labeled training data, which may be infeasible to generate in some applications.…