Related papers: SSR: A Training-Free Approach for Streaming 3D Rec…

Studies continually find that message-passing graph convolutional networks suffer from the over-smoothing issue. Basically, the issue of over-smoothing refers to the phenomenon that the learned embeddings for all nodes can become very…

Reconstructing models of the real world, including 3D geometry, appearance, and motion of real scenes, is essential for computer graphics and computer vision. It enables the synthesizing of photorealistic novel views, useful for the movie…

Speech super-resolution (SR) reconstructs high-fidelity wideband speech from low-resolution inputs-a task that necessitates reconciling global harmonic coherence with local transient sharpness. While diffusion-based generative models yield…

Online speech recognition is crucial for developing natural human-machine interfaces. This modality, however, is significantly more challenging than off-line ASR, since real-time/low-latency constraints inevitably hinder the use of future…

This paper aims to learn a domain-generalizable (DG) person re-identification (ReID) representation from large-scale videos \textbf{without any annotation}. Prior DG ReID methods employ limited labeled data for training due to the high cost…

Random Reshuffling (RR), which is a variant of Stochastic Gradient Descent (SGD) employing sampling without replacement, is an immensely popular method for training supervised machine learning models via empirical risk minimization. Due to…

Rendering is the process of generating 2D images from 3D assets, simulated in a virtual environment, typically with a graphics pipeline. By inverting such renderer, one can think of a learning approach to predict a 3D shape from an input…

Recovering jointly sparse signals in the multiple measurement vectors (MMV) setting is a fundamental problem in machine learning, but traditional methods often require careful parameter tuning or prior knowledge of the sparsity of the…

We propose a compositional approach to synthesize policies for networks of continuous-space stochastic control systems with unknown dynamics using model-free reinforcement learning (RL). The approach is based on implicitly abstracting each…

State-space models (SSMs) are a highly expressive model class for learning patterns in time series data and for system identification. Deterministic versions of SSMs (e.g. LSTMs) proved extremely successful in modeling complex time series…

We present a novel approach that converts partial and noisy RGB-D scans into high-quality 3D scene reconstructions by inferring unobserved scene geometry. Our approach is fully self-supervised and can hence be trained solely on real-world,…

We introduce a novel, training-free system for reconstructing, understanding, and rendering 3D indoor scenes from a sparse set of unposed RGB images. Unlike traditional radiance field approaches that require dense views and per-scene…

For many streaming automatic speech recognition tasks, it is important to provide timely intermediate streaming results, while refining a high quality final result. This can be done using a multi-stage architecture, where a small…

Recently there has been substantial interest in spectral methods for learning dynamical systems. These methods are popular since they often offer a good tradeoff between computational and statistical efficiency. Unfortunately, they can be…

Deep learning (DL) has emerged as a tool for improving accelerated MRI reconstruction. A common strategy among DL methods is the physics-based approach, where a regularized iterative algorithm alternating between data consistency and a…

Scene view synthesis, which generates novel views from limited perspectives, is increasingly vital for applications like virtual reality, augmented reality, and robotics. Unlike object-based tasks, such as generating 360{\deg} views of a…

Digitalizing real-world analog signals typically involves sampling in time and discretizing in amplitude. Subsequent signal reconstructions inevitably incur an error that depends on the amplitude resolution and the temporal density of the…

Sparse model selection is ubiquitous from linear regression to graphical models where regularization paths, as a family of estimators upon the regularization parameter varying, are computed when the regularization parameter is unknown or…

Self-supervised learning has shown great potentials in improving the deep learning model in an unsupervised manner by constructing surrogate supervision signals directly from the unlabeled data. Different from existing works, we present a…

When deep learning models are sequentially trained on new data, they tend to abruptly lose performance on previously learned tasks, a critical failure known as catastrophic forgetting. This challenge severely limits the deployment of AI in…