본문 바로가기

728x90

분류 전체보기

(431)
[Paper Review] Denoising Diffusion Probabilistic Models Denoising Diffusion Probabilistic ModelsWe present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational boundarxiv.org0 Abstract
[Paper Review] On decoder-only architecture for speech-to-text and large language model integration On decoder-only architecture for speech-to-text and large language model integrationLarge language models (LLMs) have achieved remarkable success in the field of natural language processing, enabling better human-computer interaction using natural language. However, the seamless integration of speech signals into LLMs has not been explorearxiv.org0. Abstract1.
[Paper Review] Investigating Decoder-only Large Language Models for Speech-to-text Translation Investigating Decoder-only Large Language Models for Speech-to-text TranslationLarge language models (LLMs), known for their exceptional reasoning capabilities, generalizability, and fluency across diverse domains, present a promising avenue for enhancing speech-related tasks. In this paper, we focus on integrating decoder-only LLMsarxiv.org0 Abstractintegrate decoder-only LLMs to the task of sp..
[Paper Review] Recent Advances in Speech Language Models: A Survey Recent Advances in Speech Language Models: A SurveyLarge Language Models (LLMs) have recently garnered significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, necessitating a shift towards voice-based models. A straightfarxiv.org0. Abstractnatural human interaction often relies on speech, necessitating a shift..
[Paper Review] Feature Unlearning for Pre-trained GANs and VAEs Feature Unlearning for Pre-trained GANs and VAEsWe tackle the problem of feature unlearning from a pre-trained image generative model: GANs and VAEs. Unlike a common unlearning task where an unlearning target is a subset of the training set, we aim to unlearn a specific feature, such as hairstyle from farxiv.org0. AbstractFeature unlearning is simply making a model to exclude the production of s..
[Math] Linear Independent, Span, Basis and Rank 1. Linear IndependentLet's say we have x1, ..., xk vectors. If we can express one vector with anotherThoese vectors are linearly dependent if and only if (at least) one of them is a linear combination of the others. In particular, if one vector is a multiple of another vector then the set is lineary dependent. Here is a practical way of checking whether vectors x1, ..., xk are lineary independen..
[Paper Review] Zipformer: A faster and better encoder for automatic speech recognition Zipformer: A faster and better encoder for automatic speech recognitionThe Conformer has become the most popular encoder model for automatic speech recognition (ASR). It adds convolution modules to a transformer to learn both local and global dependencies. In this work we describe a faster, more memory-efficient, and better-parxiv.org0. AbstractThe Conformer has become the most popular encoder m..
[Math] Groups, Vector Spaces and Vector Subspaces **My Personal opinionIn linear algebra, finding solution x from Ax = 0 is very important.And possible solution set x forms a vector subspace which is included in R^n vector space.Before defining the solution space, What we will do is to look into what group, vector space, vector subspaces are.Simply, group gurantees that the results from the operation still lives in the same group(has more speci..

728x90