paper-with-me

Papers

Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models

2024-03-18 · Emilian Postolache, Giorgio Mariani, Luca Cosmo, Emmanouil Benetos, Emanuele Rodolà

Multi-Source Diffusion Models (MSDM) allow for compositional musical generation tasks: generating a set of coherent sources, creating accompaniments, and performing source separation. Despite their versatility, they require estimating the joint distribution over the sources, necessitating pre-separated musical data, which is rarely available, and fixing the number and type of sources at training time. This paper generalizes MSDM to arbitrary time-domain diffusion models conditioned on text embeddings. These models do not require separated data as they are trained on mixtures, can parameterize an arbitrary number of sources, and allow for rich semantic control. We propose an inference procedure enabling the coherent generation of sources and accompaniments. Additionally, we adapt the Dirac separator of MSDM to perform source separation. We experiment with diffusion models trained on Slakh2100 and MTG-Jamendo, showcasing competitive generation and separation results in a relaxed data setting.

📄 PDF Abstract BibTeX arXiv:2403.11706

Code (1)

gladia-research-group/gmsdi 공식 구현

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

CoSe-Co: Sentence Conditioned Generative CommonSense Contextualizer for Language Models

2021-09-03 · AKBC Workshop CSKB 2021 10 · Rachit Bansal, Milan Aggarwal, Sumit Bhatia, Jivat Neet Kaur 외

Pre-trained Language Models (PTLMs) have been shown to perform well on natural language reasoning tasks requiring commonsense. Prior work has leveraged structured commonsense present in knowledge graphs (KGs) to assist P…

ARCKnowledge GraphsNovel ConceptsSentence

CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection

2020-04-04 · Congying Xia, Chenwei Zhang, Hoang Nguyen, Jiawei Zhang 외

In this paper, we formulate a more realistic and difficult problem setup for the intent detection task in natural language understanding, namely Generalized Few-Shot Intent Detection (GFSID). GFSID aims to discriminate a…

Conditional Text GenerationIntent DetectionLanguage ModelingLanguage Modelling+3

QUMem: Personalized Memory for Query-Conditioned User-State Inference in LLM Agents

2026-08-17 · Heng Wang, Yifei Li, Lingling Zhang, Pengyu Li 외 arxiv

Large language model (LLM) agents increasingly use external memory systems to support personalization by drawing on long and evolving interaction histories, in which user preferences may be distributed across time, chang…

Response Generation

Generalized Domain Conditioned Adaptation Network

2021-03-23 · Shuang Li, Binhui Xie, Qiuxia Lin, Chi Harold Liu 외

Domain Adaptation (DA) attempts to transfer knowledge learned in the labeled source domain to the unlabeled but related target domain without requiring large amounts of target supervision. Recent advances in DA mainly pr…

AttributeDomain Adaptation

Generalized Zero-shot ICD Coding

2019-09-28 · Congzheng Song, Shanghang Zhang, Najmeh Sadoughi, Pengtao Xie 외

The International Classification of Diseases (ICD) is a list of classification codes for the diagnoses. Automatic ICD coding is in high demand as the manual coding can be labor-intensive and error-prone. It is a multi-la…

ClassificationGeneral ClassificationGeneralized Zero-Shot LearningMulti Label Text Classification+4