disentangled - Robuta Search

https://arxiv.org/abs/2402.06875v2 [2402.06875v2] Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI... Abstract page for arXiv paper 2402.06875v2: Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI Harmonization Framework https://openreview.net/forum?id=-oUhJJILWHb Learning Debiased Representation via Disentangled Feature Augmentation | OpenReview This paper proposes a novel feature-level data augmentation for debiasing via learning disentangled representation. learning representation via disentangled feature https://arxiv.org/abs/1906.03255 [1906.03255] Disentangled State Space Representations Abstract page for arXiv paper 1906.03255: Disentangled State Space Representations state space 1906 03255 disentangled representations https://openreview.net/forum?id=OS0szhkPmF&referrer=%5Bthe%20profile%20of%20Haibo%20Chen%5D(%2Fprofile%3Fid%3D~Haibo_Chen7) Disentangled Graph Self-supervised Learning for Out-of-Distribution Generalization | OpenReview Graph out-of-distribution (OOD) generalization, aiming to generalize graph neural networks (GNNs) under distribution shifts between training and testing... self supervised learning out of disentangled graph https://deepai.org/publication/learning-disentangled-discrete-representations Learning Disentangled Discrete Representations | DeepAI Jul 26, 2023 - 07/26/23 - Recent successes in image generation, model-based reinforcement learning, and text-to-image generation have demonstrated the empir... learning disentangled discrete representations deepai https://openreview.net/forum?id=SkeuipVKDH&referrer=%5Bthe%20profile%20of%20Juncheng%20B%20Li%5D(%2Fprofile%3Fid%3D~Juncheng_B_Li1) RTC-VAE: HARNESSING THE PECULIARITY OF TOTAL CORRELATION IN LEARNING DISENTANGLED REPRESENTATIONS |... diagnosed all the problem of STOA VAEs theoretically and qualitatively https://openreview.net/forum?id=MSSRhxwZP7&referrer=%5Bthe%20profile%20of%20Yiling%20Xu%5D(%2Fprofile%3Fid%3D~Yiling_Xu1) Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual... No-Reference Point Cloud Quality Assessment (NR-PCQA) aims to objectively assess the human perceptual quality of point clouds without relying on... point cloud quality assessment learning disentangled representations https://deepai.org/publication/disentangled-graph-social-recommendation Disentangled Graph Social Recommendation | DeepAI Mar 14, 2023 - 03/14/23 - Social recommender systems have drawn a lot of attention in many online web services, because of the incorporation of social infor... disentangled graph social recommendation deepai https://elifesciences.org/articles/98117 Human EEG and artificial neural networks reveal disentangled representations and processing... Neural and computational evidence reveals that real-world size is a temporally late, semantically grounded, and hierarchically stable dimension of object... artificial neural networks human eeg reveal disentangled https://www.utwente.nl/en/eemcs/dmb/assignments/open/master/Computer%20Vision%20and%20Biometrics/20231127_disentangled_flows_for_anomaly_detection/ Disentangled Flows for Anomaly Detection | Computer Vision and Biometrics | EEMCS - DMB anomaly detection computer vision disentangled flows https://openreview.net/forum?id=RQfcckT1M_4 Self-Supervised Learning Disentangled Group Representation as Feature | OpenReview An iterative IRM algorithm for unsupervised feature disentanglement and self-supervised feature learning self supervised learning group representation disentangled feature openreview https://openreview.net/forum?id=iKDbLpVgQc 3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting | OpenReview Scene image editing is crucial for entertainment, photography, and advertising design. Existing methods solely focus on either 2D individual object or 3D... gaussian splatting editing scene via https://aclanthology.org/2023.findings-acl.30/ Generating Deep Questions with Commonsense Reasoning Ability from the Text by Disentangled... Jianxing Yu, Shiqi Wang, Libin Zheng, Qinliang Su, Wei Liu, Baoquan Zhao, Jian Yin. Findings of the Association for Computational Linguistics: ACL 2023. 2023. commonsense reasoning https://deepai.org/publication/conditional-mutual-information-for-disentangled-representations-in-reinforcement-learning Conditional Mutual Information for Disentangled Representations in Reinforcement Learning | DeepAI May 23, 2023 - 05/23/23 - Reinforcement Learning (RL) environments can produce training data with spurious correlations between features due to the amount o... mutual information reinforcement learning conditional disentangled representations https://deepai.org/publication/disentangled-person-image-generation Disentangled Person Image Generation | DeepAI Dec 7, 2017 - 12/07/17 - Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image ... image generation disentangled person deepai https://openreview.net/forum?id=AguQIV9CeN DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks |... Meta-learning represents a strong class of approaches for solving few-shot learning tasks. Nonetheless, recent research suggests that simply pre-training a... self supervised meta learning dress disentangled representation https://openreview.net/forum?id=TgSVWXw22FQ&referrer=%5Bthe%20profile%20of%20Pengyu%20Cheng%5D(%2Fprofile%3Fid%3D~Pengyu_Cheng1) Improving Zero-Shot Voice Style Transfer via Disentangled Representation Learning | OpenReview Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker.... zero shot style transfer representation learning improving voice https://aclanthology.org/2024.acl-long.116/ Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks - ACL Anthology Yingji Zhang, Danilo Carvalho, Andre Freitas. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).... semantic spaces https://openreview.net/forum?id=QIrYb3Vlze&referrer=%5Bthe%20profile%20of%20Junho%20Lee%5D(%2Fprofile%3Fid%3D~Junho_Lee2) Isometric Representation Learning for Disentangled Latent Space of Diffusion Models | OpenReview Diffusion models have made remarkable progress in capturing and reproducing real-world data. Despite their success and further potential, however, their latent... representation learning latent space diffusion models isometric disentangled https://deepai.org/publication/collecting-the-puzzle-pieces-disentangled-self-driven-human-pose-transfer-by-permuting-textures Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer by Permuting Textures |... Oct 4, 2022 - 10/04/22 - Human pose transfer aims to synthesize a new view of a person under a given pose. Recent works achieve this via self-reconstructio... https://openreview.net/forum?id=d1FHmxHPEQ0 Curriculum Disentangled Recommendation with Noisy Multi-feedback | OpenReview Learn disentangled user intentions from user multi-feedback with a newly-proposed curriculum training strategy. curriculum disentangled recommendation noisy multi https://openreview.net/forum?id=YdsSr4Za66&referrer=%5Bthe%20profile%20of%20Chao%20Wang%5D(%2Fprofile%3Fid%3D~Chao_Wang17) DR2: Disentangled Recurrent Representation Learning for Data-Efficient Speech Video Synthesis |... Although substantial progress has been made in audiodriven talking video synthesis, there still remain two major difficulties: existing works 1) need a long... representation learning for data dr2 disentangled recurrent https://openreview.net/forum?id=OS0szhkPmF Disentangled Graph Self-supervised Learning for Out-of-Distribution Generalization | OpenReview Graph out-of-distribution (OOD) generalization, aiming to generalize graph neural networks (GNNs) under distribution shifts between training and testing... self supervised learning out of disentangled graph https://elifesciences.org/reviewed-preprints/98117 Human EEG and artificial neural networks reveal disentangled representations and processing... artificial neural networks human eeg reveal disentangled https://huggingface.co/papers/2307.00040 Paper page - DisCo: Disentangled Control for Referring Human Dance Generation in Real World Join the discussion on this paper page https://openreview.net/forum?id=slpR7K3OzQ&referrer=%5Bthe%20profile%20of%20Ha-Hieu%20Pham%5D(%2Fprofile%3Fid%3D~Ha-Hieu_Pham1) Learning Disentangled Stain and Structural Representations for Semi-Supervised Histopathology... Accurate gland segmentation in histopathology images is essential for cancer diagnosis and prognosis. However, significant variability in Hematoxylin and Eosin... learning disentangled stain structural representations https://openreview.net/forum?id=0p86Mhg014 Federated Disentangled Tuning with Textual Prior Decoupling and Visual Dynamic Adaptation |... Federated Parameter-Efficient Fine-Tuning aims to adapt Vision-Language Models for downstream tasks in distributed environments. However, data heterogeneity... federated disentangled tuning textual https://arxiv.org/abs/2402.00375v1 [2402.00375v1] Disentangled Multimodal Brain MR Image Translation via Transformer-based Modality... Abstract page for arXiv paper 2402.00375v1: Disentangled Multimodal Brain MR Image Translation via Transformer-based Modality Infuser https://huggingface.co/papers/2212.01393 Paper page - Continual Learning for On-Device Speech Recognition using Disentangled Conformers Join the discussion on this paper page continual learning https://arxiv.org/abs/1908.09961 [1908.09961] Theory and Evaluation Metrics for Learning Disentangled Representations Abstract page for arXiv paper 1908.09961: Theory and Evaluation Metrics for Learning Disentangled Representations evaluation metrics for learning 1908 theory disentangled https://openreview.net/forum?id=8NMwh7TVhw Leveraging sparse and shared feature activations for disentangled representation learning |... Recovering the latent factors of variation of high dimensional data has so far focused on simple synthetic settings. Mostly building on unsupervised and... leveraging sparse shared feature activations https://www.amazon.science/publications/parrottts-text-to-speech-synthesis-exploiting-disentangled-self-supervised-representations ParrotTTS: Text-to-speech synthesis exploiting disentangled self-supervised representations -... We present ParrotTTS, a modularized text-to-speech synthesis model leveraging disentangled self-supervised speech representations. It can train a multi-speaker... text to speech self supervised synthesis exploiting disentangled https://arxiv.org/abs/2512.14162v1 [2512.14162v1] FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation Abstract page for arXiv paper 2512.14162v1: FastDDHPose: Towards Unified, Efficient, and Disentangled 3D Human Pose Estimation https://github.com/BUPT-GAMMA/DisC GitHub - BUPT-GAMMA/DisC: NeurIPS2022-Debiasing Graph Neural Networks via Learning Disentangled... NeurIPS2022-Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure - BUPT-GAMMA/DisC graph neural networks https://research.google/pubs/dissect-disentangled-simultaneous-explanations-via-concept-traversals/ DISSECT: Disentangled Simultaneous Explanations via Concept Traversals dissect disentangled simultaneous explanations via https://openreview.net/forum?id=rJlhYa4FPB&referrer=%5Bthe%20profile%20of%20Xiaojiang%20Yang%5D(%2Fprofile%3Fid%3D~Xiaojiang_Yang1) An Information Theoretic Perspective on Disentangled Representation Learning | OpenReview Existing works on disentangled representation learning usually lie on a common assumption: all factors in a disentangled representation should be independent.... an information representation learning theoretic perspective disentangled https://jmlr.org/papers/v21/19-976.html A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation https://deepai.org/publication/disentangled-makeup-transfer-with-generative-adversarial-network Disentangled Makeup Transfer with Generative Adversarial Network | DeepAI Jul 2, 2019 - 07/02/19 - Facial makeup transfer is a widely-used technology that aims to transfer the makeup style from a reference face image to a non-mak... disentangled makeup transfer generative adversarial https://huggingface.co/papers/2503.24391 Paper page - Easi3R: Estimating Disentangled Motion from DUSt3R Without Training Join the discussion on this paper page paper estimating disentangled motion without https://openreview.net/forum?id=66dbWSTips&referrer=%5Bthe%20profile%20of%20Yu%20Deng%5D(%2Fprofile%3Fid%3D~Yu_Deng2) Generative Deformable Radiance Fields for Disentangled Image Synthesis of Topology-Varying Objects... 3D-aware generative models have demonstrated their superb performance to generate 3D neural radiance fields (NeRF) from a collection of monocular 2D images... radiance fields https://arxiv.org/abs/2010.13187v3 [2010.13187v3] Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage... Abstract page for arXiv paper 2010.13187v3: Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling the reconstruction https://resynthesis-ssl.github.io/ Speech Resynthesis from Discrete Disentangled Self-Supervised Representations self supervised speech discrete disentangled representations https://arxiv.org/abs/2401.03599v1 [2401.03599v1] Disentangled Neural Relational Inference for Interpretable Motion Prediction Abstract page for arXiv paper 2401.03599v1: Disentangled Neural Relational Inference for Interpretable Motion Prediction 2401 disentangled neural relational inference https://openreview.net/forum?id=lkmlNHuzY4 ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts | OpenReview Dataset bias, where data points are skewed to certain concepts, is ubiquitous in machine learning datasets. Yet, systematically identifying these biases is... visual concepts dataset bias via disentangled https://www.aanda.org/articles/aa/full_html/2011/02/aa15913-10/T3.html Constrained fitting of disentangled binary star spectra: application to V615 Persei in the open... https://deepai.org/publication/disentangled3d-learning-a-3d-generative-model-with-disentangled-geometry-and-appearance-from-monocular-images Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from... Mar 29, 2022 - 03/29/22 - Learning 3D generative models from a dataset of monocular images enables self-supervised 3D reasoning and controllable synthesis. ... a 3d generative model https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2023.1241370/full Frontiers | DRCM: a disentangled representation network based on coordinate and multimodal... Recent studies on medical image fusion based on deep learning have made remarkable progress, but the common and exclusive features of different modalities, e... based on frontiers drcm disentangled representation https://arxiv.org/abs/2209.14107v1 [2209.14107v1] Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure Abstract page for arXiv paper 2209.14107v1: Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure graph neural networks 2209 debiasing https://deepai.org/publication/human-pose-transfer-with-disentangled-feature-consistency Human Pose Transfer with Disentangled Feature Consistency | DeepAI Jul 23, 2021 - 07/23/21 - Deep generative models have made great progress in synthesizing images with arbitrary human poses and transferring poses of one pe... human pose transfer disentangled feature https://arxiv.org/html/2602.15031v2 EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing https://arxiv.org/abs/2509.21584 [2509.21584] IndiSeek learns information-guided disentangled representations Abstract page for arXiv paper 2509.21584: IndiSeek learns information-guided disentangled representations 2509 21584 learns information guided https://www.utwente.nl/en/eemcs/dmb/assignments/open/master/Computer%20Vision%20and%20Biometrics/20231123_disentangled_flows_for_face_editing/ Disentangled Flows for Face editing | Computer Vision and Biometrics | EEMCS - DMB for face computer vision disentangled flows editing https://deepai.org/publication/stylediffusion-controllable-disentangled-style-transfer-via-diffusion-models StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models | DeepAI Aug 15, 2023 - 08/15/23 - Content and style (C-S) disentanglement is a fundamental problem and critical challenge of style transfer. Existing approaches bas... style transfer diffusion models controllable disentangled via https://huggingface.co/papers/2504.17670 Paper page - DiMeR: Disentangled Mesh Reconstruction Model Join the discussion on this paper page paper dimer disentangled mesh reconstruction https://openreview.net/forum?id=9w3iw8wDuE Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors |... Test-time adaptation (TTA) fine-tunes pre-trained deep neural networks for unseen test data. The primary challenge of TTA is limited access to the entire test... https://arxiv.org/abs/2503.19486 [2503.19486] Exploring Disentangled and Controllable Human Image Synthesis: From End-to-End to... Abstract page for arXiv paper 2503.19486: Exploring Disentangled and Controllable Human Image Synthesis: From End-to-End to Stage-by-Stage human image synthesis https://deepai.org/publication/learning-disentangled-feature-representation-for-hybrid-distorted-image-restoration Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration | DeepAI Jul 22, 2020 - 07/22/20 - Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions. ... image restoration learning disentangled feature representation https://openreview.net/forum?id=ZzUz0jo200 Sparsity regularization via tree-structured environments for disentangled representations |... Many causal systems such as biological processes in cells can only be observed indirectly via measurements, such as gene expression. Causal representation... sparsity regularization via tree structured environments