:: Library Catalog

Imatge de la portada

Guardat en:

Dades bibliogràfiques
Autors principals:	Chen, Ziheng, Wu, Xiao-Jun, Schölkopf, Bernhard, Sebe, Nicu
Format:	Preprint
Publicat:	2025
Matèries:	Machine Learning Artificial Intelligence
Accés en línia:	https://arxiv.org/abs/2509.07115
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!

Ítems similars

A Lie Group Approach to Riemannian Batch Normalization
per: Chen, Ziheng, et al.
Publicat: (2024)

Riemannian Networks over Full-Rank Correlation Matrices
per: Chen, Ziheng, et al.
Publicat: (2026)

Hyperbolic Busemann Neural Networks
per: Chen, Ziheng, et al.
Publicat: (2026)

Intrinsic Lorentz Neural Network
per: Shi, Xianglong, et al.
Publicat: (2026)

RMLR: Extending Multinomial Logistic Regression into General Geometries
per: Chen, Ziheng, et al.
Publicat: (2024)

Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry
per: Chen, Ziheng, et al.
Publicat: (2024)

Discriminative Anchor Learning for Efficient Multi-view Clustering
per: Qin, Yalan, et al.
Publicat: (2024)

Fast and Stable Riemannian Metrics on SPD Manifolds via Cholesky Product Geometry
per: Chen, Ziheng, et al.
Publicat: (2024)

An Efficient Learning-based Solver Comparable to Metaheuristics for the Capacitated Arc Routing Problem
per: Guo, Runze, et al.
Publicat: (2024)

Riemannian Multinomial Logistics Regression for SPD Neural Networks
per: Chen, Ziheng, et al.
Publicat: (2023)

A Probabilistic Model Behind Self-Supervised Learning
per: Bizeul, Alice, et al.
Publicat: (2024)

Causality can systematically address the monsters under the bench(marks)
per: Leeb, Felix, et al.
Publicat: (2025)

Out-of-Variable Generalization for Discriminative Models
per: Guo, Siyuan, et al.
Publicat: (2023)

Computational Arbitrage in AI Model Markets
per: Olmedo, Ricardo, et al.
Publicat: (2026)

Making Batch Normalization Great in Federated Deep Learning
per: Zhong, Jike, et al.
Publicat: (2023)

Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering
per: Kladny, Klaus-Rudolf, et al.
Publicat: (2024)

Batch Normalization Amplifies Memorization and Privacy Risks
per: Doan, Ngoc Phu, et al.
Publicat: (2026)

The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery
per: Zheng, Haiyang, et al.
Publicat: (2026)

Provable Privacy with Non-Private Pre-Processing
per: Hu, Yaxi, et al.
Publicat: (2024)

Identifying Intervenable and Interpretable Features via Orthogonality Regularization
per: Miller, Moritz, et al.
Publicat: (2026)

Preference Elicitation for Offline Reinforcement Learning
per: Pace, Alizée, et al.
Publicat: (2024)

Adaptive Log-Euclidean Metrics for SPD Matrix Learning
per: Chen, Ziheng, et al.
Publicat: (2023)

Masked Image Modeling: A Survey
per: Hondru, Vlad, et al.
Publicat: (2024)

Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization
per: Palenicek, Daniel, et al.
Publicat: (2025)

StableGrad: Backward Scale Control without Batch Normalization
per: Mestre, Jose I., et al.
Publicat: (2026)

GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations
per: Paischer, Fabian, et al.
Publicat: (2025)

Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints
per: Liu, Xinge, et al.
Publicat: (2026)

H$_{2}$OT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers
per: Li, Wenhao, et al.
Publicat: (2025)

Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation
per: Croitoru, Florinel-Alin, et al.
Publicat: (2026)

Curriculum Direct Preference Optimization for Diffusion and Consistency Models
per: Croitoru, Florinel-Alin, et al.
Publicat: (2024)

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation
per: Li, Wenhao, et al.
Publicat: (2023)

Learning Nonlinear Causal Reductions to Explain Reinforcement Learning Policies
per: Kekić, Armin, et al.
Publicat: (2025)

Natural Building Blocks for Structured World Models: Theory, Evidence, and Scaling
per: Da Costa, Lancelot, et al.
Publicat: (2025)

Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning
per: Reizinger, Patrik, et al.
Publicat: (2024)

Deep Backtracking Counterfactuals for Causally Compliant Explanations
per: Kladny, Klaus-Rudolf, et al.
Publicat: (2023)

Counterfactual reasoning: an analysis of in-context emergence
per: Miller, Moritz, et al.
Publicat: (2025)

Algorithmic causal structure emerging through compression
per: Wendong, Liang, et al.
Publicat: (2025)

Improving Large Language Model Safety with Contrastive Representation Learning
per: Simko, Samuel, et al.
Publicat: (2025)

GraphMLP: A Graph MLP-Like Architecture for 3D Human Pose Estimation
per: Li, Wenhao, et al.
Publicat: (2022)

Intrinsically Interpretable Attention via Sparse Post-Training
per: Draye, Florent, et al.
Publicat: (2025)