Disentangled Representation Learning

Ask about this topic

Overview

Disentangled representation learning studies how to encode separate factors—such as content and style, identity and viewpoint, or disease and acquisition conditions—in distinct parts of a representation. Common approaches include variational autoencoders, contrastive objectives, sparse or orthogonal subspaces, causal models, and symmetry-based methods; many applications use the resulting factors for editing, robust prediction, or transfer across domains. Work now spans images, speech, graphs, time series, medicine, and robotics, with increasing attention to interventions and practical controllability. A central tension remains: factors are generally not identifiable from unlabelled data alone without assumptions or useful supervision, and standard disentanglement metrics can fail when their assumptions do not hold.

Latest papers

CardsList

234 papers24 papers in the last four weeks, up 118% on the four weeks before. 0.1% of all new papers.

Mar 30, 2026

DipGuava: Disentangling Personalized Gaussian Features for 3D Head Avatars from Monocular Video

While recent 3D head avatar creation methods attempt to animate facial dynamics, they often fail to capture personalized details, limiting realism and expressiveness. To fill this gap, we present DipGuava (Disentangled and Personalized Gaussian UV Avatar), a novel 3D Gaussian head avatar creation method that successfully generates avatars with personalized attributes from monocular video. DipGuava is the first method to explicitly disentangle facial appearance into two complementary components, trained in a structured two-stage pipeline that significantly reduces learning ambiguity and enhances reconstruction fidelity. In the first stage, we learn a stable geometry-driven base appearance that captures global facial structure and coarse expression-dependent variations. In the second stage, the personalized residual details not captured in the first stage are predicted, including high-frequency components and nonlinearly varying features such as wrinkles and subtle skin deformations. These components are fused via dynamic appearance fusion that integrates residual details after deformation, ensuring spatial and semantic alignment. This disentangled design enables DipGuava to generate photorealistic, identity-preserving avatars, consistently outperforming prior methods in both visual quality and quantitativeperformance, as demonstrated in extensive experiments.

Jeonghaeng Lee, Seok Keun Choi, Zhixuan Li +2

Yonsei University, Korea · Nanyang Technological University, Singapore

3D Avatar Generation3D Gaussian SplattingDisentangled Representation LearningMonocular 3D Reconstruction
AskPDF
Mar 29, 2026

MoViD: View-Invariant 3D Human Pose Estimation via Motion-View Disentanglement

3D human pose estimation is a key enabling technology for applications such as healthcare monitoring, human-robot collaboration, and immersive gaming, but real-world deployment remains challenged by viewpoint variations. Existing methods struggle to generalize to unseen camera viewpoints, require large amounts of training data, and suffer from high inference latency. We propose MoViD, a viewpoint-invariant 3D human pose estimation framework that disentangles viewpoint information from motion features. The key idea is to extract viewpoint information from intermediate pose features and leverage it to enhance both the robustness and efficiency of pose estimation. MoViD introduces a view estimator that models key joint relationships to predict viewpoint information, and an orthogonal projection module to disentangle motion and view features, further enhanced through physics-grounded contrastive alignment across views. For real-time edge deployment, MoViD employs a frame-by-frame inference pipeline with a view-aware strategy that adaptively activates flip refinement based on the estimated viewpoint. Evaluations on nine public datasets and newly collected multiview UAV and gait analysis datasets show that MoViD reduces pose estimation error by over 24.2% compared to state-of-the-art methods, maintains robust performance under severe occlusions with 60% less training data, and achieves real-time inference at 15 FPS on NVIDIA edge devices.

Yejia Liu, Hengle Jiang, Haoxian Liu +2

Department of Computer Science and Engineering, Hong Kong University of Science and Technology

3D Human Pose EstimationDisentangled Representation Learning
AskPDF
Mar 26, 2026

A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detection

3D anomaly detection targets the detection and localization of defects in 3D point clouds trained solely on normal data. While a unified model improves scalability by learning across multiple categories, it often suffers from Inter-Category Entanglement (ICE)-where latent features from different categories overlap, causing the model to adopt incorrect semantic priors during reconstruction and ultimately yielding unreliable anomaly scores. To address this issue, we propose the Semantically Disentangled Unified Model for 3D Anomaly Detection, which reconstructs features conditioned on disentangled semantic representations. Our framework consists of three key components: (i) Coarse-to-Fine Global Tokenization for forming instance-level semantic identity, (ii) Category-Conditioned Contrastive Learning for disentangling category semantics, and (iii) a Geometry-Guided Decoder for semantically consistent reconstruction. Extensive experiments on Real3D-AD and Anomaly-ShapeNet demonstrate that our method achieves state-of-the-art for both unified and category-specific models, improving object-level AUROC by 2.8% and 9.1%, respectively, while enhancing the reliability of unified 3D anomaly detection.

SuYeon Kim, Wongyu Lee, MyeongAh Cho

Kyung Hee University, Republic of Korea

Point Cloud Anomaly DetectionUnsupervised Anomaly DetectionReconstruction-Based Anomaly DetectionDisentangled Representation Learning
AskPDF
Mar 25, 2026

CGRL: Causal-Guided Representation Learning for Node-Level Out-of-Distribution Generalization

Graph Neural Networks (GNNs) deliver strong performance on graph tasks, but their accuracy drops significantly under out-of-distribution (OOD) scenarios. Under distribution shifts, GNNs often fit environmental noise and spurious correlations instead of stable causal mechanisms, leading to weak OOD robustness and unstable predictive representations. Existing solutions based on environment invariance or causal reasoning are insufficient for node classification, as they do not explicitly model the fine-grained latent geometry required by the task. We further observe a training instability named Info-Jitter, where the mutual information between predictive representations and ground-truth labels fluctuates throughout training. To address these issues, we construct a node-classification-specific causal graph derived from the task's geometric objective. Using do-calculus to block non-causal paths caused by environmental noise, we derive a deconfounded interventional objective and a variational lower bound to disentangle representations into intra-class and inter-class components. We then propose Causal-Guided Representation Learning (CGRL), a framework with two core modules. First, a multi-branch re-weighted representation learning (RRL) module learns a causal modulation matrix to amplify causal signals and suppress environmental noise during message passing. Second, an optimization strategy combining intra-class aggregation, inter-class separation, energy-based reconstruction and supervised prediction regularizes the latent space for robust node-level generalization. Experiments on multiple benchmark datasets show that CGRL outperforms strong baselines across various distribution shifts and effectively mitigates the Info-Jitter phenomenon.

Bowen Lu, Lianqiang Yang, Teng Li +1

Anhui University, Hefei, China · Carnegie Mellon University, Pittsburgh, Commonwealth of Pennsylvania, USA

OOD GeneralizationGraph Neural NetworksCausal Representation LearningNode ClassificationDisentangled Representation Learning
AskPDF
Mar 25, 2026

Causality-Driven Disentangled Representation Learning in Multiplex Graphs

Learning representations from multiplex graphs, i.e., multi-layer networks where nodes interact through multiple relation types, is challenging due to the entanglement of shared (common) and layer-specific (private) information, which limits generalization and interpretability. In this work, we introduce a causal inference-based framework that disentangles common and private components in a self-supervised manner. CaDeM jointly (i) aligns shared embeddings across layers, (ii) enforces private embeddings to capture layer-specific signals, and (iii) applies backdoor adjustment to ensure that the common embeddings capture only global information while being separated from the private representations. Experiments on synthetic and real-world datasets demonstrate consistent improvements over existing baselines, highlighting the effectiveness of our approach for robust and interpretable multiplex graph representation learning.

Saba Nasiri, Selin Aviyente, Dorina Thanou

EPFL, Lausanne, Switzerland · Department of Electrical and Computer Engineering at Michigan State University, East Lansing, MI

Graph Representation LearningDisentangled Representation LearningGraph SSLCausal Representation Learning
AskPDF
Mar 23, 2026

SelfTTS: cross-speaker style transfer through explicit embedding disentanglement and self-refinement using self-augmentation

This work presents SelfTTS, a text-to-speech (TTS) model designed for cross-speaker style transfer that eliminates the need for external pre-trained speaker or emotion encoders. The architecture achieves emotional expressivity in neutral speakers through an explicit disentanglement strategy utilizing Gradient Reversal Layers (GRL) combined with cosine similarity loss to decouple speaker and emotion information. We introduce Multi Positive Contrastive Learning (MPCL) to induce clustered representations of speaker and emotion embeddings based on their respective labels. Furthermore, SelfTTS employs a self-refinement strategy via Self-Augmentation, exploiting the model's voice conversion capabilities to enhance the naturalness of synthesized speech. Experimental results demonstrate that SelfTTS achieves superior emotional naturalness (eMOS) and robust stability in target timbre and emotion compared to state-of-the-art baselines.

Lucas H. Ueda, João G. T. Lima, Pedro R. Corrêa +3

Universidade Estadual de Campinas (UNICAMP), Brazil · CPQD, Brazil

Disentangled Representation LearningTTS SynthesisSpeech ProcessingControllable Speech GenerationText-to-SpeechEmotional Speech Synthesis
AskPDF
Mar 22, 2026

Evaluating Factor-Wise Auxiliary Dynamics Supervision for Latent Structure and Robustness in Simulated Humanoid Locomotion

We evaluate whether factor-wise auxiliary dynamics supervision produces useful latent structure or improved robustness in simulated humanoid locomotion. DynaMITE -- a transformer encoder with a factored 24-d latent trained by per-factor auxiliary losses during proximal policy optimization (PPO) -- is compared against Long Short-Term Memory (LSTM), plain Transformer, and Multilayer Perceptron (MLP) baselines on a Unitree G1 humanoid across four Isaac Lab tasks. The supervised latent shows no evidence of decodable or functionally separable factor structure: probe R^2 ~ 0 for all five dynamics factors, clamping any subspace changes reward by < 0.05, and standard disentanglement metrics (MIG, DCI, SAP) are near zero. An unsupervised LSTM hidden state achieves higher probe R^2 (up to 0.10). A 2x2 factorial ablation (n = 10 seeds) isolates the contributions of the tanh bottleneck and auxiliary losses: the auxiliary losses show no measurable effect on either in-distribution (ID) reward (+0.03, p = 0.732) or severe out-of-distribution (OOD) reward (+0.03, p = 0.669), while the bottleneck shows a small, consistent advantage in both regimes (ID: +0.16, p = 0.207; OOD: +0.10, p = 0.208). The bottleneck advantage persists under severe combined perturbation but does not amplify, indicating a training-time representation benefit rather than a robustness mechanism. LSTM achieves the best nominal reward on all four tasks (p < 0.03); DynaMITE degrades less under combined-shift stress (2.3% vs. 16.7%), but this difference is attributable to the bottleneck compression, not the auxiliary supervision. For locomotion practitioners: auxiliary dynamics supervision does not produce an interpretable estimator and does not measurably improve reward or robustness beyond what the bottleneck alone provides; recurrent baselines remain the stronger choice for nominal performance.

Chayanin Chamachot

Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, Thailand

Latent Dynamics ModelingDisentangled Representation LearningRL for Legged LocomotionRobust RL
AskPDF
Mar 17, 2026

Semi-supervised Latent Disentangled Diffusion Model for Textile Pattern Generation

Textile pattern generation (TPG) aims to synthesize fine-grained textile pattern images based on given clothing images. Although previous studies have not explicitly investigated TPG, existing image-to-image models appear to be natural candidates for this task. However, when applied directly, these methods often produce unfaithful results, failing to preserve fine-grained details due to feature confusion between complex textile patterns and the inherent non-rigid texture distortions in clothing images. In this paper, we propose a novel method, SLDDM-TPG, for faithful and high-fidelity TPG. Our method consists of two stages: (1) a latent disentangled network (LDN) that resolves feature confusion in clothing representations and constructs a multi-dimensional, independent clothing feature space; and (2) a semi-supervised latent diffusion model (S-LDM), which receives guidance signals from LDN and generates faithful results through semi-supervised diffusion training, combined with our designed fine-grained alignment strategy. Extensive evaluations show that SLDDM-TPG reduces FID by 4.1 and improves SSIM by up to 0.116 on our CTP-HD dataset, and also demonstrate good generalization on the VITON-HD dataset.

Chenggong Hu, Yi Wang, Mengqi Xue +3

Zhejiang University · Hangzhou City University

Image GenerationLatent Diffusion ModelsDisentangled Representation Learning
AskPDF
Mar 16, 2026

Self-supervised Disentanglement of Disease Effects from Aging in 3D Medical Shapes

Disentangling pathological changes from physiological aging in 3D medical shapes is crucial for developing interpretable biomarkers and patient stratification. However, this separation is challenging when diagnosis labels are limited or unavailable, since disease and aging often produce overlapping effects on shape changes, obscuring clinically relevant shape patterns. To address this challenge, we propose a two-stage framework combining unsupervised disease discovery with self-supervised disentanglement of implicit shape representations. In the first stage, we train an implicit neural model with signed distance functions to learn stable shape embeddings. We then apply clustering on the shape latent space, which yields pseudo disease labels without using ground-truth diagnosis during discovery. In the second stage, we disentangle factors in a compact variational space using pseudo disease labels discovered in the first stage and the ground truth age labels available for all subjects. We enforce separation and controllability with a multi-objective disentanglement loss combining covariance and a supervised contrastive loss. On ADNI hippocampus and OAI distal femur shapes, we achieve near-supervised performance, improving disentanglement and reconstruction over state-of-the-art unsupervised baselines, while enabling high-fidelity reconstruction, controllable synthesis, and factor-based explainability. Code and checkpoints are available at https://github.com/anonymous-submission01/medical-shape-disentanglement

Jakaria Rabbi, Nilanjan Ray, Dana Cobzas

Department of Computing Science, University of Alberta, Edmonton, Canada · Department of Computer Science, MacEwan University, Edmonton, Canada

Representation DisentanglementDisentangled Representation Learning3D Medical ImagingStatistical Shape Modeling
AskPDF
Mar 14, 2026

U-Face: An Efficient and Generalizable Framework for Unsupervised Facial Attribute Editing via Subspace Learning

Latent space-based facial attribute editing methods have gained popularity in applications such as digital entertainment, virtual avatar creation, and human-computer interaction systems due to their potential for efficient and flexible attribute manipulation, particularly for continuous edits. Among these, unsupervised latent space-based methods, which discover effective semantic vectors without relying on labeled data, have attracted considerable attention in the research community. However, existing methods still encounter difficulties in disentanglement, as manipulating a specific facial attribute may unintentionally affect other attributes, complicating fine-grained controllability. To address these challenges, we propose a novel framework designed to offer an effective and adaptable solution for unsupervised facial attribute editing, called Unsupervised Facial Attribute Controllable Editing (U-Face). The proposed method frames semantic vector learning as a subspace learning problem, where latent vectors are approximated within a lower-dimensional semantic subspace spanned by a semantic vector matrix. This formulation can also be equivalently interpreted from a projection-reconstruction perspective and further generalized into an autoencoder framework, providing a foundation that can support disentangled representation learning in a flexible manner. To improve disentanglement and controllability, we impose orthogonal non-negative constraints on the semantic vectors and incorporate attribute boundary vectors to reduce entanglement in the learned directions. Although these constraints make the optimization problem challenging, we design an alternating iterative algorithm, called Alternating Iterative Disentanglement and Controllability (AIDC), with closed-form updates and provable convergence under specific conditions.

Bo Liu, Xuan Cui, Run Zeng +5

Chongqing Key Laboratory of Intelligent Sensing and Blockchain Technology, Chongqing Technology and Business University, Chongqing, China · School of Artificial Intelligence, Chongqing Technology and Business University, Chongqing, China · School of Software, Northwestern Polytechnical University, Xi’an, China

Image EditingDisentangled Representation LearningUnsupervised Representation Learning
AskPDF
Mar 13, 2026

SDF-Net: Structure-Aware Disentangled Feature Learning for Opticall-SAR Ship Re-identification

Cross-modal ship re-identification (ReID) between optical and synthetic aperture radar (SAR) imagery is fundamentally challenged by the severe radiometric discrepancy between passive optical imaging and coherent active radar sensing. While existing approaches primarily rely on statistical distribution alignment or semantic matching, they often overlook a critical physical prior: ships are rigid objects whose geometric structures remain stable across sensing modalities, whereas texture appearance is highly modality-dependent. In this work, we propose SDF-Net, a Structure-Aware Disentangled Feature Learning Network that systematically incorporates geometric consistency into optical--SAR ship ReID. Built upon a ViT backbone, SDF-Net introduces a structure consistency constraint that extracts scale-invariant gradient energy statistics from intermediate layers to robustly anchor representations against radiometric variations. At the terminal stage, SDF-Net disentangles the learned representations into modality-invariant identity features and modality-specific characteristics. These decoupled cues are then integrated through a parameter-free additive residual fusion, effectively enhancing discriminative power. Extensive experiments on the HOSS-ReID dataset demonstrate that SDF-Net consistently outperforms existing state-of-the-art methods. The code and trained models are publicly available at https://github.com/cfrfree/SDF-Net.

Furui Chen, Han Wang, Yuhan Sun +5

Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing 100094, China · Key Laboratory of Space Utilization, Chinese Academy of Sciences, Beijing 100094, China · University of Chinese Academy of Sciences, Beijing 100049, China +1

Cross-Modal Representation LearningCross-Modal RetrievalDisentangled Representation LearningSynthetic Aperture Radar
AskPDF
Mar 12, 2026

Statistical and structural identifiability in representation learning

Representation learning models exhibit a surprising stability in their internal representations. Whereas most prior work treats this stability as a single property, we formalize it as two distinct concepts: statistical identifiability (consistency of representations across runs) and structural identifiability (alignment of representations with some unobserved ground truth). Recognizing that perfect pointwise identifiability is generally unrealistic for modern representation learning models, we propose new model-agnostic definitions of statistical and structural near-identifiability of representations up to some error tolerance εε. Leveraging these definitions, we prove a statistical εε-near-identifiability result for the representations of models with nonlinear decoders, generalizing existing identifiability theory beyond last-layer representations in e.g. generative pre-trained transformers (GPTs) to near-identifiability of the intermediate representations of a broad class of models including (masked) autoencoders (MAEs) and supervised learners. Although these weaker assumptions confer weaker identifiability, we show that independent components analysis (ICA) can resolve much of the remaining linear ambiguity for this class of models, and validate and measure our near-identifiability claims empirically. With additional assumptions on the data-generating process, statistical identifiability extends to structural identifiability, yielding a simple and practical recipe for disentanglement: ICA post-processing of latent representations. On synthetic benchmarks, this approach achieves state-of-the-art disentanglement using a vanilla autoencoder. With a foundation model-scale MAE for cell microscopy, it disentangles biological variation from technical batch effects, substantially improving downstream generalization.

Walter Nelson, Marco Fumero, Theofanis Karaletsos +1

Institute of Science and Technology Austria · Chan Zuckerberg Initiative

Representation IdentifiabilityDisentangled Representation Learning
AskPDF
Mar 12, 2026

Disentangled Representation Learning through Unsupervised Symmetry Group Discovery

Symmetry-based disentangled representation learning leverages the group structure of environment transformations to uncover the latent factors of variation. Prior approaches to symmetry-based disentanglement have required strong prior knowledge of the symmetry group's structure, or restrictive assumptions about the subgroup properties. In this work, we remove these constraints by proposing a method whereby an embodied agent autonomously discovers the group structure of its action space through unsupervised interaction with the environment. We prove the identifiability of the true symmetry group decomposition under minimal assumptions, and derive two algorithms: one for discovering the group decomposition from interaction data, and another for learning Linear Symmetry-Based Disentangled (LSBD) representations without assuming specific subgroup properties. Our method is validated on three environments exhibiting different group decompositions, where it outperforms existing LSBD approaches.

Barthélémy Dang-Nhu, Louis Annabi, Sylvain Argentieri

Sorbonne Universit´e, CNRS, Institut des Syst`emes Intelligents et de Robotique, ISIR, F-75005 Paris, France

Disentangled Representation LearningUnsupervised Representation LearningSymmetry DiscoveryEquivariant Representation Learning
AskPDF
Mar 12, 2026

CFD-HAR: User-controllable Privacy through Conditional Feature Disentanglement

Modern wearable and mobile devices are equipped with inertial measurement units (IMUs). Human Activity Recognition (HAR) applications running on such devices use machine-learning-based, data-driven techniques that leverage such sensor data. However, sensor-data-driven HAR deployments face two critical challenges: protecting sensitive user information embedded in sensor data in accordance with users' privacy preferences and maintaining high recognition performance with limited labeled samples. This paper proposes a technique for user-controllable privacy through feature disentanglement-based representation learning at the granular level for dynamic privacy filtering. We also compare the efficacy of our technique against few-shot HAR using autoencoder-based representation learning. We analyze their architectural designs, learning objectives, privacy guarantees, data efficiency, and suitability for edge Internet of Things (IoT) deployment. Our study shows that CFD-based HAR provides explicit, tunable privacy protection controls by separating activity and sensitive attributes in the latent space, whereas autoencoder-based few-shot HAR offers superior label efficiency and lightweight adaptability but lacks inherent privacy safeguards. We further examine the security implications of both approaches in continual IoT settings, highlighting differences in susceptibility to representation leakage and embedding-level attacks. The analysis reveals that neither paradigm alone fully satisfies the emerging requirements of next-generation IoT HAR systems. We conclude by outlining research directions toward unified frameworks that jointly optimize privacy preservation, few-shot adaptability, and robustness for trustworthy IoT intelligence.

Alex Gn, Fan Li, S Kuniyilh +1

Privacy-Preserving Representation LearningHuman Activity RecognitionPrivacy-Preserving MLDisentangled Representation LearningWearable SensingData-Efficient Learning
AskPDF
Mar 11, 2026

A Unified Latent Space Disentanglement VAE Framework with Robust Disentanglement Effectiveness Evaluation

Evaluating and interpreting latent representations, such as variational autoencoders (VAEs), remains a significant challenge for diverse data types, especially when ground-truth generative factors are unknown. To address this, we unify several state-of-the-art disentangled VAE approaches for latent space disentanglement into one framework -- bfVAE. To assess the effectiveness of a disentangled VAE model and enhance latent space interpretability, we propose Feature Variance Heterogeneity via Latent Traversal (FVH-LT) and Dirty Block Sparse Regression in Latent Space (DBSR-LS). To ensure robust interpretability of learned latent space, we develop a greedy alignment strategy (GAS) that mitigates label switching and aligns latent dimensions across runs to set the foundation of result aggregation. We also introduce a convenient scalar latent space separation index (LSSI) based on the GAS-aligned outputs of FVH-LT and DBSR-LS to summarize the overall latent structural separation without knowledge of the ground-truth generative factors. We compare bfVAE to five VAE models and validate the effectiveness FVH-LT, DBSR-LS, and LSSI in on seven tabular and image datasets. Under our examined experimental settings, bfVAE provides a more flexible disentanglement framework achieves more favorable overall trade-off between disentanglement and reconstruction than the benchmark VAE models; FVH-LT and DBSR-LS reliably uncover semantically meaningful and domain-relevant latent structures and generally yield consistent results; and LSSI makes an effective quantitative summary of latent structural separation.

Xiaoan Lang, Md Mostafizer Rahman, Fang Liu

Department of Applied and Computational Mathematics and Statistics University of Notre Dame, Notre Dame, IN, USA · Lucy Family Institute for Data & Society University of Notre Dame, Notre Dame, IN, USA

Variational AutoencodersDisentangled Representation LearningRepresentation DisentanglementNeural Network Interpretability
AskPDF
Mar 11, 2026

Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck

Large language models (LLMs) have become a standard for multilingual evaluation, yet they exhibit a severe systematic translationese bias. In this paper, translationese bias is characterized as LLMs systematically favoring machine-translated text over human-authored references, particularly in low-resource languages. We attribute this bias to spurious correlations with (i) latent manifold alignment with English and (ii) cross-lingual predictability. To mitigate this bias, we propose DIBJudge, a robust fine-tuning framework that learns a minimally sufficient, judgment-critical representation via variational information compression, while explicitly isolating spurious factors into the dedicated bias branch. Furthermore, we incorporate a cross-covariance penalty that explicitly suppresses statistical dependence between robust and bias representations, thereby encouraging effective disentanglement. Extensive evaluations on multilingual reward modeling benchmarks and a dedicated translationese bias evaluation suite demonstrate that the proposed DIBJudge consistently outperforms strong baselines and substantially mitigates translationese bias.

Hongbin Zhang, Kehai Chen, Xuefen Bai +4

Institute of Computing and Intelligence, Harbin Institute of Technology, Shenzhen, China · Pengcheng Laboratory, Shenzhen, China · Keeta AI, Meituan, Beijing, China

Bias in LLM-as-a-JudgeLinguistic Bias in Language ModelsMultilingual Language Model EvaluationDisentangled Representation Learning
AskPDF
Mar 5, 2026

Koopman Regularized Deep Speech Disentanglement for Speaker Verification

Human speech contains both linguistic content and speaker dependent characteristics making speaker verification a key technology in identity critical applications. Modern deep learning speaker verification systems aim to learn speaker representations that are invariant to semantic content and nuisance factors such as ambient noise. However, many existing approaches depend on labelled data, textual supervision or large pretrained models as feature extractors, limiting scalability and practical deployment, raising sustainability concerns. We propose Deep Koopman Speech Disentanglement Autoencoder (DKSD-AE), a structured autoencoder that combines a novel multi-step Koopman operator learning module with instance normalization to disentangle speaker and content dynamics. Quantitative experiments across multiple datasets demonstrate that DKSD-AE achieves improved or competitive speaker verification performance compared to state-of-the-art baselines while maintaining high content EER, confirming effective disentanglement. These results are obtained with substantially fewer parameters and without textual supervision. Moreover, performance remains stable under increased evaluation scale, highlighting representation robustness and generalization. Our findings suggest that Koopman-based temporal modelling, when combined with instance normalization, provides an efficient and principled solution for speaker-focused representation learning.

Nikos Chazaridis, Mohammad Belal, Rafael Mestre +2

School of Electronics and Computer Science, University of Southampton, SO17 1BJ Southampton, U.K. · Marine Geosciences, National Oceanography Centre, SO14 3ZH Southampton, U.K.

Speaker VerificationSpeaker DisentanglementAudio Representation LearningDisentangled Representation LearningKoopman Operator Learning
AskPDF
Mar 5, 2026

Mitigating Instance Entanglement in Instance-Dependent Partial Label Learning

Partial label learning is a prominent weakly supervised classification task, where each training instance is ambiguously labeled with a set of candidate labels. In real-world scenarios, candidate labels are often influenced by instance features, leading to the emergence of instance-dependent PLL (ID-PLL), a setting that more accurately reflects this relationship. A significant challenge in ID-PLL is instance entanglement, where instances from similar classes share overlapping features and candidate labels, resulting in increased class confusion. To address this issue, we propose a novel Class-specific Augmentation based Disentanglement (CAD) framework, which tackles instance entanglement by both intra- and inter-class regulations. For intra-class regulation, CAD amplifies class-specific features to generate class-wise augmentations and aligns same-class augmentations across instances. For inter-class regulation, CAD introduces a weighted penalty loss function that applies stronger penalties to more ambiguous labels, encouraging larger inter-class distances. By jointly applying intra- and inter-class regulations, CAD improves the clarity of class boundaries and reduces class confusion caused by entanglement. Extensive experimental results demonstrate the effectiveness of CAD in mitigating the entanglement problem and enhancing ID-PLL performance. The code is available at https://github.com/RyanZhaoIc/CAD.git.

Rui Zhao, Bin Shi, Kai Sun +1

School of Computer Science and Technology, Xi’an Jiaotong University · Shaanxi Province Key Laboratory of Big Data Knowledge Engineering, Xi’an Jiaotong University · School of Distance Education, Xi’an Jiaotong University

Weakly Supervised LearningDisentangled Representation Learning
AskPDF
Mar 4, 2026

Nearest-Neighbor Density Estimation for Dependency Suppression

The ability to remove unwanted dependencies from data is crucial in various domains, including fairness, robust learning, and privacy protection. In this work, we propose an encoder-based approach that learns a representation independent of a sensitive variable but otherwise preserving essential data characteristics. Unlike existing methods that rely on decorrelation or adversarial learning, our approach explicitly estimates and modifies the data distribution to neutralize statistical dependencies. To achieve this, we combine a specialized variational autoencoder with a novel loss function driven by non-parametric nearest-neighbor density estimation, enabling direct optimization of independence. We evaluate our approach on multiple datasets, demonstrating that it can outperform existing unsupervised techniques and even rival supervised methods in balancing information removal and utility.

Kathleen Anderson, Thomas Martinetz

Institute for Neuro- and Bioinformatics, University of Lübeck, Germany

Privacy-Preserving MLUnsupervised Representation LearningDisentangled Representation Learning
AskPDF
Mar 3, 2026

Interpreting Speaker Characteristics in the Dimensions of Self-Supervised Speech Features

How do speech models trained through self-supervised learning structure their representations? Previous studies have looked at how information is encoded in feature vectors across different layers. But few studies have considered whether speech characteristics are captured within individual dimensions of SSL features. In this paper, we specifically look at speaker information using PCA on utterance-averaged representations. For a range of SSL models, we find that the principal dimension that explains most variance encodes pitch and associated characteristics like gender. Other individual principal dimensions correlate with intensity, noise levels, the second formant, and higher frequency characteristics. We then use synthesis analyses to show that the dimensions for most characteristics are isolated from each other's influence. We further show that characteristics can be changed by manipulating the corresponding dimensions.

Kyle Janse van Rensburg, Benjamin van Niekerk, Herman Kamper

Department of Electrical and Electronic Engineering, Stellenbosch University, South Africa · Concordia University, Canada

Self-Supervised Speech Representation LearningAudio Representation LearningDisentangled Representation Learning
AskPDF
Mar 1, 2026

Teacher-Guided Causal Interventions for Image Denoising: Orthogonal Content-Noise Disentanglement in Vision Transformers

Conventional image denoising models often inadvertently learn spurious correlations between environmental factors and noise patterns. Moreover, due to high-frequency ambiguity, they struggle to reliably distinguish subtle textures from stochastic noise, resulting in over-removed details or residual noise artifacts. We therefore revisit denoising via causal intervention, arguing that purely correlational fitting entangles intrinsic content with extrinsic noise, which directly degrades robustness under distribution shifts. Motivated by this, we propose the Teacher-Guided Causal Disentanglement Network (TCD-Net), which explicitly decomposes the generative mechanism via structured interventions on feature spaces within a Vision Transformer framework. Specifically, our method integrates three key components: (1) An Environmental Bias Adjustment (EBA) module projects features into a stable, de-centered subspace to suppress global environmental bias (de-confounding). (2) A dual-branch disentanglement head employs an orthogonality constraint to force a strict separation between content and noise representations, preventing information leakage. (3) To resolve structural ambiguity, we leverage Nano Banana Pro, Google's reasoning-guided AI image generation model, to guide a causal prior, effectively pulling content representations back onto the natural-image manifold. Extensive experiments demonstrate that TCD-Net outperforms mainstream methods across multiple benchmarks in both fidelity and efficiency, achieving a real-time speed of 104.2 FPS on a single RTX 5090 GPU.

Kuai Jiang, Zhaoyan Ding, Guijuan Zhang +2

China University of Mining and Technology · Shandong Normal University · Qilu University of Technology

Disentangled Representation LearningCausal Representation LearningImage Denoising
AskPDF
Mar 1, 2026

Decoupling Motion and Geometry in 4D Gaussian Splatting

High-fidelity reconstruction of dynamic scenes is an important yet challenging problem. While recent 4D Gaussian Splatting (4DGS) has demonstrated the ability to model temporal dynamics, it couples Gaussian motion and geometric attributes within a single covariance formulation, which limits its expressiveness for complex motions and often leads to visual artifacts. To address this, we propose VeGaS, a novel velocity-based 4D Gaussian Splatting framework that decouples Gaussian motion and geometry. Specifically, we introduce a Galilean shearing matrix that explicitly incorporates time-varying velocity to flexibly model complex non-linear motions, while strictly isolating the effects of Gaussian motion from the geometry-related conditional Gaussian covariance. Furthermore, a Geometric Deformation Network is introduced to refine Gaussian shapes and orientations using spatio-temporal context and velocity cues, enhancing temporal geometric modeling. Extensive experiments on public datasets demonstrate that VeGaS achieves state-of-the-art performance.

Yi Zhang, Yulei Kang, Jiangxin Sun +3

Sun Yat-sen University · University of Trento · Huazhong University of Science and Technology +1

4D ReconstructionDynamic Scene Reconstruction3D Gaussian SplattingDisentangled Representation Learning
AskPDF
Feb 27, 2026

Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations

Identifiability in representation learning is commonly evaluated using standard metrics (e.g., MCC, DCI, R^2) on synthetic benchmarks with known ground-truth factors. These metrics are assumed to reflect recovery up to the equivalence class guaranteed by identifiability theory. We show that this assumption holds only under specific structural conditions: each metric implicitly encodes assumptions about both the data-generating process (DGP) and the encoder. When these assumptions are violated, metrics become misspecified and can produce systematic false positives and false negatives. Such failures occur both within classical identifiability regimes and in post-hoc settings where identifiability is most needed. We introduce a taxonomy separating DGP assumptions from encoder geometry, use it to characterise the validity domains of existing metrics, and release an evaluation suite for reproducible stress testing and comparison.

Shruti Joshi, Théo Saulus, Wieland Brendel +3

Mila - Québec AI Institute & Université de Montréal · Max-Planck-Institute for Intelligent Systems, ELLIS Institute Tübingen, University of Tübingen

Representation IdentifiabilityDisentangled Representation Learning
AskPDF
Feb 27, 2026

Disentangled Mode-Specific Representations for Tensor Time Series via Contrastive Learning

Multi-mode tensor time series (TTS) can be found in many domains, such as search engines and environmental monitoring systems. Learning representations of a TTS benefits various applications, but it is also challenging since the complexities inherent in the tensor hinder the realization of rich representations. In this paper, we propose a novel representation learning method designed specifically for TTS, namely MoST. Specifically, MoST uses a tensor slicing approach to reduce the complexity of the TTS structure and learns representations that can be disentangled into individual non-temporal modes. Each representation captures mode-specific features, which are the relationship between variables within the same mode, and mode-invariant features, which are in common in representations of different modes. We employ a contrastive learning framework to learn parameters; the loss function comprises two parts intended to learn representation in a mode-specific way and mode-invariant way, effectively exploiting disentangled representations as augmentations. Extensive experiments on real-world datasets show that MoST consistently outperforms the state-of-the-art methods in terms of classification and forecasting accuracy. Code is available at https://github.com/KoheiObata/MoST.

Kohei Obata, Taichi Murayama, Zheng Chen +2

SANKEN, Osaka University, Osaka, Japan · Yokohama National University, Kanagawa, Japan

Time Series Representation LearningDisentangled Representation LearningMultivariate Time Series ClassificationMultivariate Time Series Forecasting
AskPDF
Feb 26, 2026

Uncovering Physical Drivers of Dark Matter Halo Structures with Auxiliary-Variable-Guided Generative Models

Deep generative models (DGMs) compress high-dimensional data but often entangle distinct physical factors in their latent spaces. We present an auxiliary-variable-guided framework for disentangling representations of thermal Sunyaev-Zel'dovich (tSZ) maps of dark matter halos. We introduce halo mass and concentration as auxiliary variables and apply a lightweight alignment penalty to encourage latent dimensions to reflect these physical quantities. To generate sharp and realistic samples, we extend latent conditional flow matching (LCFM), a state-of-the-art generative model, to enforce disentanglement in the latent space. Our Disentangled Latent-CFM (DL-CFM) model recovers the established mass-concentration scaling relation and identifies latent space outliers that may correspond to unusual halo formation histories. By linking latent coordinates to interpretable astrophysical properties, our method transforms the latent space into a diagnostic tool for cosmological structure. This work demonstrates that auxiliary guidance preserves generative flexibility while yielding physically meaningful, disentangled embeddings, providing a generalizable pathway for uncovering independent factors in complex astronomical datasets.

Arkaprabha Ganguli, Anirban Samaddar, Florian Kéruzoré +4

Mathematics and Computer Science Division, Argonne National Laboratory, Lemont, IL 60439 · High Energy Physics Division, Argonne National Laboratory, Lemont, IL 60439, USA · Computational Science Division, Argonne National Laboratory, Lemont, IL 60439 +1

Disentangled Representation LearningPhysics-Informed Generative ModelingLatent Space AlignmentConditional Flow Matching
AskPDF
Feb 26, 2026

SFL-Net: Source-Factorized Latent Representation Learning for Multi-Contrast MRI to Tau-PET Synthesis

Tau positron emission tomography supports Alzheimer's disease staging but is difficult to scale because of tracer, scanner, and radiation constraints. Synthesis from structural MRI is therefore attractive, but it is a particularly difficult setting. T1-weighted and FLAIR MRI provide anatomy and disease correlated morphology, but they do not directly measure Tau-PET relevant signal. We introduce SFL-Net, a multi-input synthesis framework that predicts Tau-PET from T1-weighted and FLAIR MRI. SFL-Net factorizes the latent representation into shared, T1-specific, FLAIR-specific, and complementary pathways and preserves anatomical detail through latent structural conditioning rather than direct encoder-decoder connections. We evaluated SFL-Net and baseline models using 605 training and 83 validation subjects from ADNI-3 and OASIS-3 datasets. Evaluation included raw image fidelity, standardized uptake value ratio agreement, high uptake overlap, regional Bland-Altman bias, braak derived stage agreement, non-inferiority sensitivity analysis, and latent component Shapley attribution. SFL-Net performed competitively on both clinically relevant and reconstruction metrics, while also delivering explicit source level auditability that conventional UNet derived models lack.

Agamdeep S. Chopra, Caitlin Neher, Tianyi Ren +3

Department of Mechanical Engineering, University of Washington, Seattle, WA, USA · Department of Radiology, University of Washington, Seattle, WA, USA

Disentangled Representation LearningMultimodal Disentangled Representation LearningMagnetic Resonance ImagingMedical Image SynthesisExplainable Medical Image Analysis
AskPDF
Feb 25, 2026

Disentangling Shared and Target-Enriched Topics via Background-Contrastive Non-negative Matrix Factorization

Biological signals of interest in high-dimensional data are often masked by dominant variation shared across conditions. This variation, arising from baseline biological structure or technical effects, can prevent standard dimensionality reduction methods from resolving condition-specific structure. The challenge is that these confounding topics are often unknown and mixed with biological signals. Existing background correction methods are either unscalable to high dimensions or not interpretable. We introduce background contrastive Non-negative Matrix Factorization (\model), which extracts target-enriched latent topics by jointly factorizing a target dataset and a matched background using shared non-negative bases under a contrastive objective that suppresses background-expressed structure. This approach yields non-negative components that are directly interpretable at the feature level, and explicitly isolates target-specific variation. \model is learned by an efficient multiplicative update algorithm via matrix multiplication such that it is highly efficient on GPU hardware and scalable to big data via minibatch training akin to deep learning approach. Across simulations and diverse biological datasets, \model reveals signals obscured by conventional methods, including disease-associated programs in postmortem depressive brain single-cell RNA-seq, genotype-linked protein expression patterns in mice, treatment-specific transcriptional changes in leukemia, and TP53-dependent drug responses in cancer cell lines.

Yixuan Li, Archer Y. Yang, Yue Li

Department of Mathematics and Statistics, McGill University, Montreal, QC, Canada · Mila – Quebec AI Institute, Montreal, QC, Canada · School of Computer Science, McGill University, Montreal, QC, Canada

Non-Negative Matrix FactorizationDisentangled Representation LearningContrastive Learning
AskPDF
Feb 24, 2026

Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation

Generating realistic 3D Human-Human Interaction (HHI) requires coherent modeling of the physical plausibility of the agents and their interaction semantics. Existing methods compress all motion information into a single latent representation, limiting their ability to capture fine-grained actions and inter-agent interactions. This often leads to semantic misalignment and physically implausible artifacts, such as penetration or missed contact. We propose Disentangled Hierarchical Variational Autoencoder (DHVAE) based latent diffusion for structured and controllable HHI generation. DHVAE explicitly disentangles the global interaction context and individual motion patterns into a decoupled latent structure by employing a CoTransformer module. To mitigate implausible and physically inconsistent contacts in HHI, we incorporate contrastive learning constraints with our DHVAE to promote a more discriminative and physically plausible latent interaction space. For high-fidelity interaction synthesis, DHVAE employs a DDIM-based diffusion denoising process in the hierarchical latent space, enhanced by a skip-connected AdaLN-Transformer denoiser. Extensive evaluations show that DHVAE achieves superior motion fidelity, text alignment, and physical plausibility with greater computational efficiency.

Zichen Geng, Zeeshan Hayder, Bo Miao +3

Department of CSSE, The University of Western Australia, Crawley WA 6009, Australia · Data61, CSIRO, Acton ACT 2601, Australia · Australian Institute for Machine Learning, The University of Adelaide, Adelaide SA 5000, Australia +1

Human Motion GenerationVariational AutoencodersDiffusion Models for Motion GenerationDisentangled Representation Learning
AskPDF
Feb 22, 2026

Controlled Face Manipulation and Synthesis for Data Augmentation

Deep learning vision models excel with abundant supervision, but many applications face label scarcity and class imbalance. Controllable image editing can augment scarce labeled data, yet edits often introduce artifacts and entangle non-target attributes. We study this in facial expression analysis, targeting Action Unit (AU) manipulation where annotation is costly and AU co-activation drives entanglement. We present a facial manipulation method that operates in the semantic latent space of a pre-trained face generator (Diffusion Autoencoder). Using lightweight linear models, we reduce entanglement of semantic features via (i) dependency-aware conditioning that accounts for AU co-activation, and (ii) orthogonal projection that removes nuisance attribute directions (e.g., glasses), together with an expression neutralization step to enable absolute AU edit. We use these edits to balance AU occurrence by editing labeled faces and to diversify identities/demographics via controlled synthesis. Augmenting AU detector training with the generated data improves accuracy and yields more disentangled predictions with fewer co-activation shortcuts, outperforming alternative data-efficient training strategies and suggesting improvements similar to what would require substantially more labeled data in our learning-curve analysis. Compared to prior methods, our edits are stronger, produce fewer artifacts, and preserve identity better.

Joris Kirchner, Amogh Gudi, Marian Bittner +1

Vicarious Perception Technologies (VicarVision) · Delft University of Technology

Synthetic Data AugmentationImage EditingControllable Image GenerationFacial Action Unit DetectionDisentangled Representation Learning
AskPDF
Feb 22, 2026

Automated Disentangling Analysis of Skin Colour for Lesion Images

Machine-learning models applied to skin images often have degraded performance when the skin colour captured in images (SCCI) differs between training and deployment. These discrepancies arise from a combination of entangled environmental factors (e.g., illumination, camera settings) and intrinsic factors (e.g., skin tone) that cannot be accurately described by a single "skin tone" scalar -- a simplification commonly adopted by prior work. To mitigate such colour mismatches, we propose a skin-colour disentangling framework that adapts disentanglement-by-compression to learn a structured, manipulable latent space for SCCI from unlabelled dermatology images. To prevent information leakage that hinders proper learning of dark colour features, we introduce a randomized, mostly monotonic decolourization mapping. To suppress unintended colour shifts of localized patterns (e.g., ink marks, scars) during colour manipulation, we further propose a geometry-aligned post-processing step. Together, these components enable faithful counterfactual editing and answering an essential question: "What would this skin condition look like under a different SCCI?", as well as direct colour transfer between images and controlled traversal along physically meaningful directions (e.g., blood perfusion, camera white balance), enabling educational visualization of skin conditions under varying SCCI. We demonstrate that dataset-level augmentation and colour normalization based on our framework achieve competitive lesion classification performance. Ultimately, our work promotes equitable diagnosis through creating diverse training datasets that include different skin tones and image-capturing conditions.

Wenbo Yang, Eman Rezk, Walaa M. Moursi +1

University of Waterloo, Waterloo, ON, Canada, N2L 3G1

Disentangled Representation LearningRepresentation DisentanglementDermatologyCounterfactual Data Augmentation
AskPDF