Related papers: Scaling Image Tokenizers with Grouped Spherical Qu…

Visual tokenizer is a critical component for vision generation. However, the existing tokenizers often face unsatisfactory trade-off between compression ratios and reconstruction fidelity. To fill this gap, we introduce a powerful and…

In the realm of deep neural network deployment, low-bit quantization presents a promising avenue for enhancing computational efficiency. However, it often hinges on the availability of training data to mitigate quantization errors, a…

Quantum generative modeling is a rapidly evolving discipline at the intersection of quantum computing and machine learning. Contemporary quantum machine learning is generally limited to toy examples or heavily restricted datasets with few…

Image retrieval methods that employ hashing or vector quantization have achieved great success by taking advantage of deep learning. However, these approaches do not meet expectations unless expensive label information is sufficient. To…

3D Gaussian Splatting (GS) has emerged as a powerful representation for high-quality scene reconstruction, offering compelling rendering quality. However, the training process of GS often suffers from slow convergence due to inefficient…

We develop a scalable algorithmic framework for sparse convex quantile regression (SCQR), addressing key computational challenges in the literature. Enhancing the classical CQR model, we introduce L2-norm regularization and an…

Scalable characterization of quantum processors is crucial for mitigating noise and imperfections. While randomized measurement protocols enable efficient access to local observables, inferring a globally consistent description of…

Capturing high-quality images from only a few detected photons is a fundamental challenge in computational imaging. Single-photon avalanche diode (SPAD) sensors promise high-quality imaging in regimes where conventional cameras fail, but…

Recent advances in multimodal models highlight the pivotal role of image tokenization in high-resolution image generation. By compressing images into compact latent representations, tokenizers enable generative models to operate in…

Despite significant advancements in human motion generation, current motion representations, typically formulated as discrete frame sequences, still face two critical limitations: (i) they fail to capture motion from a multi-scale…

Network quantization is a powerful technique to compress convolutional neural networks. The quantization granularity determines how to share the scaling factors in weights, which affects the performance of network quantization. Most…

Generative adversarial networks (GANs) have gained increasing popularity in various computer vision applications, and recently start to be deployed to resource-constrained mobile devices. Similar to other deep models, state-of-the-art GANs…

Vector quantization (VQ) is a key technique in high-resolution and high-fidelity image synthesis, which aims to learn a codebook to encode an image with a sequence of discrete codes and then generate an image in an auto-regression manner.…

Generative adversarial networks (GANs) learn a latent space whose samples can be mapped to real-world images. Such latent spaces are difficult to interpret. Some earlier supervised methods aim to create an interpretable latent space or…

The quality of the latent space in visual tokenizers (e.g., VAEs) is crucial for modern generative models. However, the standard reconstruction-based training paradigm produces a latent space that is biased towards low-level information,…

Vision Transformers (ViTs) are essential in computer vision but are computationally intensive, too. Model quantization, particularly to low bit-widths like 4-bit, aims to alleviate this difficulty, yet existing Post-Training Quantization…

Layer-wise quantization is a key technique for efficiently compressing large models without expensive retraining. Previous methods typically quantize the weights of each layer by "uniformly" optimizing the layer reconstruction loss across…

Learning compact and meaningful latent space representations has been shown to be very useful in generative modeling tasks for visual data. One particular example is applying Vector Quantization (VQ) in variational autoencoders (VQ-VAEs,…

3D Gaussian Splatting (3DGS) has attracted considerable attention for enabling high-quality real-time rendering. Although 3DGS compression methods have been proposed for deployment on storage-constrained devices, two limitations hinder…

Quantization is a key technique to reduce network size and computational complexity by representing the network parameters with a lower precision. Traditional quantization methods rely on access to original training data, which is often…