Tootfinder

This https://arxiv.org/abs/2010.13187 has been replaced.
link: https://scholar.google.com/scholar?q=a

Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling
Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the (aggregate) posterior to encourage statistical independence of the latent factors. This approach introduces a trade-off between disentangled representation learning and reconstruction quality since the model does not have enough capacity to learn correlated latent variables that capture detail information present in most image data. To overcome this trade-off, we present a novel mult…

This https://arxiv.org/abs/2403.19773 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

ShapeFusion: A 3D diffusion model for localized shape editing
In the realm of 3D computer vision, parametric models have emerged as a ground-breaking methodology for the creation of realistic and expressive 3D avatars. Traditionally, they rely on Principal Component Analysis (PCA), given its ability to decompose data to an orthonormal space that maximally captures shape variations. However, due to the orthogonality constraints and the global nature of PCA's decomposition, these models struggle to perform localized and disentangled editing of 3D shapes, wh…

PromptCodec: High-Fidelity Neural Speech Codec using Disentangled Representation Learning based Adaptive Feature-aware Prompt Encoders
Yu Pan, Lei Ma, Jianjun Zhao
https://arxiv.org/abs/2404.02702

PromptCodec: High-Fidelity Neural Speech Codec using Disentangled Representation Learning based Adaptive Feature-aware Prompt Encoders
Neural speech codec has recently gained widespread attention in generative speech modeling domains, like voice conversion, text-to-speech synthesis, etc. However, ensuring high-fidelity audio reconstruction of speech codecs under high compression rates remains an open and challenging issue. In this paper, we propose PromptCodec, a novel end-to-end neural speech codec model using disentangled representation learning based feature-aware prompt encoders. By incorporating additional feature represe…

This https://arxiv.org/abs/2403.19773 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

ShapeFusion: A 3D diffusion model for localized shape editing
In the realm of 3D computer vision, parametric models have emerged as a ground-breaking methodology for the creation of realistic and expressive 3D avatars. Traditionally, they rely on Principal Component Analysis (PCA), given its ability to decompose data to an orthonormal space that maximally captures shape variations. However, due to the orthogonality constraints and the global nature of PCA's decomposition, these models struggle to perform localized and disentangled editing of 3D shapes, wh…

This https://arxiv.org/abs/2402.14431 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Tunneling time, the barrier time-delay and weak measurement What was or can actually be measured with the Attoclock?
The measurement of the tunneling time-delay in attosecond experiments, termed attoclock, despite its controversies, offers a fruitful opportunity to understand the tunneling time and the tunnel-ionization process. In previous work, we showed a model that well describes the time-delay measured by the attoclock experiment in the adiabatic and nonadiabatic field calibrations. In the present work we show that the tunneling time reveals a universal behavior, with disentangled contribution, where the…

This https://arxiv.org/abs/2301.08394 has been replaced.
initial toot: https://mastoxiv.page/@arX…

Unconstrained quantitative magnetization transfer imaging: disentangling T1 of the free and semi-solid spin pools
Since the inception of magnetization transfer (MT) imaging, it has been widely assumed that Henkelman's two spin pools have similar longitudinal relaxation times, which motivated many researchers to constrain them to each other. However, several recent publications reported a $T_1^s$ of the semi-solid spin pool that is much shorter than $T_1^f$ of the free pool. While these studies tailored experiments for robust proofs-of-concept, we here aim to quantify the disentangled relaxation processes o…

Deep CSI Compression for Dual-Polarized Massive MIMO Channels with Disentangled Representation Learning
Suhang Fan, Wei Xu, Renjie Xie, Shi Jin, Derrick Wing Kwan Ng, Naofal Al-Dhahir
https://arxiv.org/abs/2403.19185

Deep CSI Compression for Dual-Polarized Massive MIMO Channels with Disentangled Representation Learning
Channel state information (CSI) feedback is critical for achieving the promised advantages of enhancing spectral and energy efficiencies in massive multiple-input multiple-output (MIMO) wireless communication systems. Deep learning (DL)-based methods have been proven effective in reducing the required signaling overhead for CSI feedback. In practical dual-polarized MIMO scenarios, channels in the vertical and horizontal polarization directions tend to exhibit high polarization correlation. To f…

This https://arxiv.org/abs/2211.11787 has been replaced.
link: https://scholar.google.com/scholar?q=a

Counting atypical black hole microstates from entanglement wedges
Disentangled black hole microstates are atypical states in holographic CFTs whose gravity duals do not have smooth horizons. If there exist sufficiently many disentangled microstates to account for the entire black hole entropy, then any black hole microstate can be written as a superposition of states without smooth horizons. We show that there exist sufficiently many disentangled microstates to account for almost the entire black hole entropy of a large AdS black hole at the semiclassical lim…

Shiva and Shakti - Presumed Proto-Galactic Fragments in the Inner Milky Way: #Gaia unravels the ancient threads of the #MilkyWay: #galaxy, discovering two surprising streams of stars that formed and wove together over 12 billion years ago.

This https://arxiv.org/abs/2305.02759 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Disentangled Contrastive Collaborative Filtering
Recent studies show that graph neural networks (GNNs) are prevalent to model high-order relationships for collaborative filtering (CF). Towards this research line, graph contrastive learning (GCL) has exhibited powerful performance in addressing the supervision label shortage issue by learning augmented user and item representations. While many of them show their effectiveness, two key questions still remain unexplored: i) Most existing GCL-based CF models are still limited by ignoring the fact…

Disentangling Exploration from Exploitation
Alessandro Lizzeri, Eran Shmaya, Leeat Yariv
https://arxiv.org/abs/2404.19116 https://arx…

Disentangling Exploration from Exploitation
Starting from Robbins (1952), the literature on experimentation via multi-armed bandits has wed exploration and exploitation. Nonetheless, in many applications, agents' exploration and exploitation need not be intertwined: a policymaker may assess new policies different than the status quo; an investor may evaluate projects outside her portfolio. We characterize the optimal experimentation policy when exploration and exploitation are disentangled in the case of Poisson bandits, allowing for gen…

This https://arxiv.org/abs/2401.16184 has been replaced.
link: https://scholar.google.com/scholar?q=a

On the Semantics of LM Latent Space: A Vocabulary-defined Approach
Understanding the latent space of language models (LM) is crucial to refining their performance and interpretability. Existing analyses often fall short in providing disentangled (model-centric) insights into LM semantics, and neglect essential aspects of LM adaption. In response, we introduce a pioneering method called vocabulary-defined semantics, which establishes a reference frame within the LM latent space, ensuring disentangled semantic analysis grounded in LM vocabulary. Our approach tra…

Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI Harmonization Framework
Mengqi Wu, Lintao Zhang, Pew-Thian Yap, Hongtu Zhu, Mingxia Liu
https://arxiv.org/abs/2402.06875

Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI Harmonization Framework
Brain magnetic resonance imaging (MRI) has been extensively employed across clinical and research fields, but often exhibits sensitivity to site effects arising from nonbiological variations such as differences in field strength and scanner vendors. Numerous retrospective MRI harmonization techniques have demonstrated encouraging outcomes in reducing the site effects at image level. However, existing methods generally suffer from high computational requirements and limited generalizability, res…

Disentangled Cascaded Graph Convolution Networks for Multi-Behavior Recommendation
Zhiyong Cheng, Jianhua Dong, Fan Liu, Lei Zhu, Xun Yang, Meng Wang
https://arxiv.org/abs/2404.11519

Disentangled Cascaded Graph Convolution Networks for Multi-Behavior Recommendation
Multi-behavioral recommender systems have emerged as a solution to address data sparsity and cold-start issues by incorporating auxiliary behaviors alongside target behaviors. However, existing models struggle to accurately capture varying user preferences across different behaviors and fail to account for diverse item preferences within behaviors. Various user preference factors (such as price or quality) entangled in the behavior may lead to sub-optimization problems. Furthermore, these model…

This https://arxiv.org/abs/2301.08394 has been replaced.
initial toot: https://mastoxiv.page/@arX…

Unconstrained quantitative magnetization transfer imaging: disentangling T1 of the free and semi-solid spin pools
Since the inception of magnetization transfer (MT) imaging, it has been widely assumed that Henkelman's two spin pools have similar longitudinal relaxation times, which motivated many researchers to constrain them to each other. However, several recent publications reported a $T_1^s$ of the semi-solid spin pool that is much shorter than $T_1^f$ of the free pool. While these studies tailored experiments for robust proofs-of-concept, we here aim to quantify the disentangled relaxation processes o…

Tunneling time, the barrier time-delay and weak measurement What was or can actually be measured with the Attoclock?
Ossama Kullie
https://arxiv.org/abs/2402.14431

Tunneling time, the barrier time-delay and weak measurement What was or can actually be measured with the Attoclock?
The measurement of the tunneling time-delay in attosecond experiments, termed attoclock, despite its controversies, offers a fruitful opportunity to understand the tunneling time and the tunnel-ionization process. In previous work, we showed a model that well describes the time-delay measured by the attoclock experiment in the adiabatic and nonadiabatic field calibrations. In the present work we show that the tunneling time reveals a universal behavior, with disentangled contribution, where the…

CSA-Trans: Code Structure Aware Transformer for AST
Saeyoon Oh, Shin Yoo
https://arxiv.org/abs/2404.05767 https://arxiv.org/pdf/2404.…

CSA-Trans: Code Structure Aware Transformer for AST
When applying the Transformer architecture to source code, designing a good self-attention mechanism is critical as it affects how node relationship is extracted from the Abstract Syntax Trees (ASTs) of the source code. We present Code Structure Aware Transformer (CSA-Trans), which uses Code Structure Embedder (CSE) to generate specific PE for each node in AST. CSE generates node Positional Encoding (PE) using disentangled attention. To further extend the self-attention capability, we adopt Sto…

DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency
Wenfang Ya, Kejing Yin, William K. Cheung, Jia Liu, Jing Qin
https://arxiv.org/abs/2403.06197

DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency
The combination of electronic health records (EHR) and medical images is crucial for clinicians in making diagnoses and forecasting prognosis. Strategically fusing these two data modalities has great potential to improve the accuracy of machine learning models in clinical prediction tasks. However, the asynchronous and complementary nature of EHR and medical images presents unique challenges. Missing modalities due to clinical and administrative factors are inevitable in practice, and the signi…

This https://arxiv.org/abs/2404.02702 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

PromptCodec: High-Fidelity Neural Speech Codec using Disentangled Representation Learning based Adaptive Feature-aware Prompt Encoders
Neural speech codec has recently gained widespread attention in generative speech modeling domains, like voice conversion, text-to-speech synthesis, etc. However, ensuring high-fidelity audio reconstruction of speech codecs under high compression rates remains an open and challenging issue. In this paper, we propose PromptCodec, a novel end-to-end neural speech codec model using disentangled representation learning based feature-aware prompt encoders. By incorporating additional feature represe…

This https://arxiv.org/abs/2310.17101 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Boosting Multi-Speaker Expressive Speech Synthesis with Semi-supervised Contrastive Learning
This paper aims to build a multi-speaker expressive TTS system, synthesizing a target speaker's speech with multiple styles and emotions. To this end, we propose a novel contrastive learning-based TTS approach to transfer style and emotion across speakers. Specifically, contrastive learning from different levels, i.e. utterance and category level, is leveraged to extract the disentangled style, emotion, and speaker representations from speech for style and emotion transfer. Furthermore, a semi-…

DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency
Wenfang Ya, Kejing Yin, William K. Cheung, Jia Liu, Jing Qin
https://arxiv.org/abs/2403.06197

DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency
The combination of electronic health records (EHR) and medical images is crucial for clinicians in making diagnoses and forecasting prognosis. Strategically fusing these two data modalities has great potential to improve the accuracy of machine learning models in clinical prediction tasks. However, the asynchronous and complementary nature of EHR and medical images presents unique challenges. Missing modalities due to clinical and administrative factors are inevitable in practice, and the signi…

This https://arxiv.org/abs/2403.18551 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Attention Calibration for Disentangled Text-to-Image Personalization
Recent thrilling progress in large-scale text-to-image (T2I) models has unlocked unprecedented synthesis quality of AI-generated content (AIGC) including image generation, 3D and video composition. Further, personalized techniques enable appealing customized production of a novel concept given only several images as reference. However, an intriguing problem persists: Is it possible to capture multiple, novel concepts from one single reference image? In this paper, we identify that existing appr…

Intent-aware Recommendation via Disentangled Graph Contrastive Learning
Yuling Wang, Xiao Wang, Xiangzhou Huang, Yanhua Yu, Haoyang Li, Mengdi Zhang, Zirui Guo, Wei Wu
https://arxiv.org/abs/2403.03714

Intent-aware Recommendation via Disentangled Graph Contrastive Learning
Graph neural network (GNN) based recommender systems have become one of the mainstream trends due to the powerful learning ability from user behavior data. Understanding the user intents from behavior data is the key to recommender systems, which poses two basic requirements for GNN-based recommender systems. One is how to learn complex and diverse intents especially when the user behavior is usually inadequate in reality. The other is different behaviors have different intent distributions, so…

Learning Multidimensional Disentangled Representations of Instrumental Sounds for Musical Similarity Assessment
Yuka Hashizume, Li Li, Atsushi Miyashita, Tomoki Toda
https://arxiv.org/abs/2404.06682

Learning Multidimensional Disentangled Representations of Instrumental Sounds for Musical Similarity Assessment
To achieve a flexible recommendation and retrieval system, it is desirable to calculate music similarity by focusing on multiple partial elements of musical pieces and allowing the users to select the element they want to focus on. A previous study proposed using multiple individual networks for calculating music similarity based on each instrumental sound, but it is impractical to use each signal as a query in search systems. Using separated instrumental sounds alternatively resulted in less a…

Joint Quality Assessment and Example-Guided Image Processing by Disentangling Picture Appearance from Content
Abhinau K. Venkataramanan, Cosmin Stejerean, Ioannis Katsavounidis, Hassene Tmar, Alan C. Bovik
https://arxiv.org/abs/2404.13484

Joint Quality Assessment and Example-Guided Image Processing by Disentangling Picture Appearance from Content
The deep learning revolution has strongly impacted low-level image processing tasks such as style/domain transfer, enhancement/restoration, and visual quality assessments. Despite often being treated separately, the aforementioned tasks share a common theme of understanding, editing, or enhancing the appearance of input images without modifying the underlying content. We leverage this observation to develop a novel disentangled representation learning method that decomposes inputs into content …