相关论文: Vector Quantization in the Brain: Grid-like Codes …

We propose a framework for conditional vector quantile regression (CVQR) that combines neural optimal transport with amortized optimization, and apply it to multivariate conformal prediction. Classical quantile regression does not extend…

Constrained quantum annealing (CQA) is a quantum annealing approach that is designed so that constraints are satisfied without penalty terms. There is an analogy between the model for the CQA of graph coloring and a set of disordered spin…

Interpretability of deep reinforcement learning systems could assist operators with understanding how they interact with their environment. Vector quantization methods -- also called codebook methods -- discretize a neural network's latent…

Due to the presence of the natural gap between Knowledge Graph (KG) structures and the natural language, the effective integration of holistic structural information of KGs with Large Language Models (LLMs) has emerged as a significant…

Vector Quantized Variational AutoEncoders (VQ-VAEs) are designed to compress a continuous input to a discrete latent space and reconstruct it with minimal distortion. They operate by maintaining a set of vectors -- often referred to as the…

In this paper a variation of the classic vector quantization problem is considered. In the standard formulation, a quantizer is designed to minimize the distortion between input and output when the number of reconstruction points is fixed.…

Generating effective query suggestions in conversational search requires aligning model outputs with user preferences, which is challenging due to sparse and noisy click signals. We propose GQS, a generative framework that integrates click…

Humans describe complex scenes with compositionality, using simple text descriptions enriched with links and relationships. While vision-language research has aimed to develop models with compositional understanding capabilities, this is…

While most frontier models still use deterministic frequency-based tokenization algorithms such as byte-pair encoding (BPE), there has been significant recent work to design learned neural tokenizers. However, these schemes generally add to…

We present Temporal and Object Quantification Networks (TOQ-Nets), a new class of neuro-symbolic networks with a structural bias that enables them to learn to recognize complex relational-temporal events. This is done by including reasoning…

As the size and complexity of models and datasets grow, so does the need for communication-efficient variants of stochastic gradient descent that can be deployed to perform parallel model training. One popular communication-compression…

As the size and complexity of models and datasets grow, so does the need for communication-efficient variants of stochastic gradient descent that can be deployed to perform parallel model training. One popular communication-compression…

Visual Question answering is a challenging problem requiring a combination of concepts from Computer Vision and Natural Language Processing. Most existing approaches use a two streams strategy, computing image and question features that are…

It is customary to deploy uniform scalar quantization in the end-to-end optimized Neural image compression methods, instead of more powerful vector quantization, due to the high complexity of the latter. Lattice vector quantization (LVQ),…

Existing neural networks are memory-consuming and computationally intensive, making deploying them challenging in resource-constrained environments. However, there are various methods to improve their efficiency. Two such methods are…

Recent progress on deep learning has made it possible to automatically transform the screenshot of Graphic User Interface (GUI) into code by using the encoder-decoder framework. While the commonly adopted image encoder (e.g., CNN network),…

Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or…

Long document question answering is a challenging task due to its demands for complex reasoning over long text. Previous works usually take long documents as non-structured flat texts or only consider the local structure in long documents.…

Vector Quantization (VQ) underpins many modern generative frameworks such as VQ-VAE, VQ-GAN, and latent diffusion models. Yet, it suffers from the persistent problem of codebook collapse, where a large fraction of code vectors remains…

One of the key issues of Visual Question Answering (VQA) is to reason with semantic clues in the visual content under the guidance of the question, how to model relational semantics still remains as a great challenge. To fully capture…