Cover Image

Compositional Generalization via Forced Rendering of Disentangled Latents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liang, Qiyao, Qian, Daoyuan, Ziyin, Liu, Fiete, Ila
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Modular connectivity in neural networks emerges from Poisson noise-motivated regularisation, and promotes robustness and compositional generalisation
by: Qian, Daoyuan, et al.
Published: (2025)

Do Diffusion Models Learn Semantically Meaningful and Efficient Representations?
by: Liang, Qiyao, et al.
Published: (2024)

How Diffusion Models Learn to Factorize and Compose
by: Liang, Qiyao, et al.
Published: (2024)

The Blessing of Dimensionality in LLM Fine-tuning: A Variance-Curvature Perspective
by: Liang, Qiyao, et al.
Published: (2026)

Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination
by: Liang, Qiyao, et al.
Published: (2026)

Key-value memory in the brain
by: Gershman, Samuel J., et al.
Published: (2025)

Permutation Invariant Learning with High-Dimensional Particle Filters
by: Boopathy, Akhilan, et al.
Published: (2024)

Fundamental performance bounds on time-series generation using reservoir computing
by: Qian, Daoyuan, et al.
Published: (2024)

Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning
by: Hwang, Jaedong, et al.
Published: (2025)

Three Mechanisms of Feature Learning in a Linear Network
by: Xu, Yizhou, et al.
Published: (2024)

Unified Neural Network Scaling Laws and Scale-time Equivalence
by: Boopathy, Akhilan, et al.
Published: (2024)

Understanding the Emergence of Multimodal Representation Alignment
by: Tjandrasuwita, Megan, et al.
Published: (2025)

Sculpting Latent Spaces With MMD: Disentanglement With Programmable Priors
by: Fruytier, Quentin, et al.
Published: (2025)

Reflections on Disentanglement and the Latent Space
by: Schaerf, Ludovica
Published: (2024)

Disentangling Genotype and Environment Specific Latent Features for Improved Trait Prediction using a Compositional Autoencoder
by: Powadi, Anirudha, et al.
Published: (2024)

Remove Symmetries to Control Model Expressivity and Improve Optimization
by: Ziyin, Liu, et al.
Published: (2024)

Noise Balance and Stationary Distribution of Stochastic Gradient Descent
by: Ziyin, Liu, et al.
Published: (2023)

Disentangled Generative Graph Representation Learning
by: Hu, Xinyue, et al.
Published: (2024)

Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models
by: Jun, Youngjun, et al.
Published: (2024)

Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation
by: Prokopiou, Ioannis, et al.
Published: (2026)

Annealed Co-Generation: Disentangling Variables via Progressive Pairwise Modeling
by: Zhang, Hantao, et al.
Published: (2026)

Multiple Invertible and Partial-Equivariant Function for Latent Vector Transformation to Enhance Disentanglement in VAEs
by: Jung, Hee-Jun, et al.
Published: (2025)

Latent Concept Disentanglement in Transformer-based Language Models
by: Hong, Guan Zhe, et al.
Published: (2025)

LatentTrack: Sequential Weight Generation via Latent Filtering
by: Haq, Omer
Published: (2026)

Learning Domain- and Class-Disentangled Prototypes for Domain-Generalized EEG Emotion Recognition
by: Li, Guangli, et al.
Published: (2025)

Disentanglement of Variations with Multimodal Generative Modeling
by: Zhang, Yijie, et al.
Published: (2025)

Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models
by: Chen, Danchun, et al.
Published: (2026)

CFASL: Composite Factor-Aligned Symmetry Learning for Disentanglement in Variational AutoEncoder
by: Jung, Hee-Jun, et al.
Published: (2024)

Graph VQ-Transformer (GVT): Fast and Accurate Molecular Generation via High-Fidelity Discrete Latents
by: Zheng, Haozhuo, et al.
Published: (2025)

Disentangling Causal Substructures for Interpretable and Generalizable Drug Synergy Prediction
by: Luo, Yi, et al.
Published: (2025)

Adversarial Graph Disentanglement
by: Zheng, Shuai, et al.
Published: (2021)

Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations
by: Li, Zhonghao, et al.
Published: (2026)

Learning Disentangled Equivariant Representation for Explicitly Controllable 3D Molecule Generation
by: Liu, Haoran, et al.
Published: (2024)

JTreeformer: Graph-Transformer via Latent-Diffusion Model for Molecular Generation
by: Shi, Ji, et al.
Published: (2025)

Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning
by: Wang, Xiangmeng, et al.
Published: (2026)

Deconstructing Generative Diversity: An Information Bottleneck Analysis of Discrete Latent Generative Models
by: Wu, Yudi, et al.
Published: (2025)

Disentanglement in Difference: Directly Learning Semantically Disentangled Representations by Maximizing Inter-Factor Differences
by: Zhang, Xingshen, et al.
Published: (2025)

XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision
by: Myara, Alexandre, et al.
Published: (2026)

Latent Process Generator Matching
by: Billera, Lukas, et al.
Published: (2026)

Structural Equation-VAE: Disentangled Latent Representations for Tabular Data
by: Zhang, Ruiyu, et al.
Published: (2025)