Inductive Bias

Follow this topic Ask about this topic

Recent momentum

-67%

3 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

3 new papers

A weekly snapshot of new work published in Inductive Bias.

Period ending 2026-09-07

1 new paper

A weekly snapshot of new work published in Inductive Bias.

80 papers

Latest in Inductive Bias

Open your feed →

Inductive Biases in Field-Level Cosmological Inference from Galaxy Catalogs
Sep 8, 2026James O. Baldwin, Shy Genel, Francisco Villaescusa-NavarroCosmology Inductive Bias
Neither Adversarial Training Nor Purification: Emergent Adversarial Robustness from Oscillatory Predictive Learning
Sep 8, 2026Mohammed-Yassine Habibi, Klea Ziu, Martin Takáč +1Adversarial Transferability Parameter-Efficient Adaptation
Learning the Geometry of Admissible Hypotheses through Inductive Bias in Training Distributions
Aug 31, 2026James Crowley, Faez Ahmed, Anton van BeekPartial Differential Equations Inductive Bias
M-Net: Integrating Spectral Features and Physical Field Operators into Deep Learning for Medical Image Segmentation
Aug 12, 2026Jing Zhu, Ye Wang, Fumin WangMedical Image Segmentation U-Net
Rethinking Data Efficiency in Industrial Dense Prediction: Pretraining Coherence, Not Inductive Bias, Determines ViTs Low-Data Advantage
Aug 11, 2026Haoran Sui, Yaoyuan JiaVision Transformer Model Pretraining
Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and Tracking
Aug 10, 2026Liying Yang, Hao Mo, Jialun Liu +74D Reconstruction Multi-Object Tracking
Graph Machine: Exploring Edge Mechanisms as an Inductive Bias
Aug 7, 2026Lintai HouMultiplex Graph Transformers Graph Structure
Mask-Based Priors Are More Persistent than Query-Key Initializations
Aug 1, 2026Mingze Ma, Hemanth Saratchandran, Cameron Gordon +1Inductive Bias Priors
Conservation laws determine what physical learning remembers
Jul 30, 2026Bijaya DangolConservatism Inductive Bias
Inverse Learning of Latent Risk-Neutral Densities from Irregular Option Quotes
Jul 29, 2026Lennon J. Shikhman, Michael Galarnyk, Aadi Dash +1Derivative Pricing Neural-Network Approximation
3D-Aware VLMs with Implicit and Explicit Geometries
Jul 23, 2026Wenhao Li, Xueying Jiang, Quanhao Qian +43D Spatial Reasoning 3D
Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks
Jul 20, 2026Damien Teney, Liangze Jiang, Hemanth Saratchandran +1Inductive Bias Neural Architectures
The Information Shadow: Measuring Structural Limits on What Language Models Can Learn
Jul 17, 2026Priyansh Srivastava, Romit ChatterjeeFundamental Limits Information Gap
Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models
Jul 14, 2026Yubo Wang, Jiarong Liang, Yuxuan Zhang +5Coding Agents Post-Training Pipelines
The RG-Flow Transformer: Encoding Scale-Free Dynamics in Scarce EEG
Jul 11, 2026Dibakar SigdelSleep Stage Classification Multiplex Graph Transformers
Language Re-generation: An investigation into information locality effects on reconstruction
Jul 11, 2026Amirhossein Mohammadi, Laurence E. Frank, Albert Gatt +1Protein Language Model Rewrite
Are We Ready for AI-Driven Discovery? AI Verification Before the Next Fundamental Physics Breakthrough
Jul 10, 2026Gaia Grosso, Vinicius Mikuni, Lukas HeinrichVerification Physics
RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting
Jul 9, 2026Sumit Satishrao Shevtekar, Chandresh Kumar MauryaTime Series Forecasting Long-Horizon Forecasting
Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study
Jul 6, 2026Yoshiyuki OotaniFew-Shot Learning Inductive Bias
A Multi-Resolution Finite-Volume Inspired Deep Learning Framework for Spatiotemporal Dynamics Prediction
Jul 1, 2026Xin-Yang Liu, Xiantao Fan, Jian-Xun WangShallow Water Equations Physics-Informed Deep Learning
The FIL Hypothesis: Inductive Biases Help with Kernel Engineering
Jun 29, 2026Nikolai Rozanov, Subhabrata Dutta, Preslav Nakov +1Inductive Bias Feedback Loop
RenderFormer++: Scalable and Physically Grounded Feed-Forward Neural Rendering
Jun 29, 2026Huangsheng Du, Haoran Zhu, Youcheng Cai +2Neural Rendering Visual Geometry Grounded Transformer
Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoning
Jun 29, 2026Xin Zou, Haolin Deng, Yibo Yan +6Multimodal Reasoning Cross-View
Are Humans Evolved Instruction Followers? An Underlying Inductive Bias Enables Rapid Instructed Task Learning
Jun 29, 2026Anjishnu KumarInstruction Local Inductive Bias
Mass Conservation as an Inductive Bias for Self-Organized Criticality in NCA Reservoirs
Jun 22, 2026Tong Zhang, Etienne Guichard, Sidney Pontes-Filho +1Reservoir Computing Neural Cellular Automata
Statistical Properties of Training & Generalization
Jun 18, 2026Itay Lavie, Noam Levi, Yonatan KahnScaling Laws Architectural Inductive Biases
When, Where, and How: Adaptive Binning for Tabular Self-Supervised Learning
Jun 18, 2026Daehwan Kim, Haejun Chung, Ikbeom JangTabular Learning Self-Supervised Learning
ITNet: A Learnable Integral Transform That Subsumes Convolution, Attention, and Recurrence
Jun 17, 2026Ashim Dhor, Rasel Mondal, Pin-Yu ChenConvolutional Neural Networks Convolutional
Anomaly Detection for Sparse and Irregular Multivariate Time Series with Latent SDEs
Jun 17, 2026Martin Uray, Dominik Geng, Florian Graf +2Time-Series Anomaly Detection Anomaly Detection
Investigating Inductive Biases for Machine Learning Emulation of Sudden Stratospheric Warmings in Idealised Isca Simulations
Jun 17, 2026Oskar Bohn Lassen, Simon Driscoll, Stephen I. Thomson +2Neural Network Emulator Global Climate Models
You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences
Jun 14, 2026Ninad Daithankar, Alexi Gladstone, Yann LeCun +1Visual Representation Learning Self-Supervised Learning
Hierarchical Modeling of ICD Codes in EHR Foundation Models
Jun 13, 2026Megha Thukral, Dong Gyun Kang, Rudra Pratap Singh +3International Classification Of Disease Codes Electronic Health Record Foundation Models
Rethinking Structural Anomaly Detection: From Decision Boundaries to Projection Operators
Jun 13, 2026Alexander BauerAnomaly Detection Projection
Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks
Jun 12, 2026Mo Shakiba, Rana Rokni, Mohammad Mohammadi +1Functional Networks Human Visual Cortex
Exposure Bias as Epistemic Underidentification in Recursive Forecasting
Jun 11, 2026Riku Green, Zahraa S. Abdallah, Telmo M Silva FilhoInductive Bias Epistemic Uncertainty Artificial Intelligence Act
Encoding the Euler Characteristic Transform
Jun 9, 2026Nello Blaser, Odin Hoff Gardaa, Lars M. Salbu +2Neural Representations Convolutional Neural Networks
Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning
Jun 5, 2026Paarth Gulati, Ilya NemenmanInductive Bias
Adaptive Oscillatory-State Alignment for Time Series Forecasting
Jun 4, 2026Zhangyao Song, Chaofeng Qu, Chao Zha +3Oscillatory Dynamics Temporal Dynamics
The Loss Is Not Enough: Sampling Conditions and Inductive Bias in Contrastive Representation Learning
Jun 2, 2026Justinas Zaliaduonis, Patrick Putzky, Till Richter +1Contrastive Learning Latent Cluster Geometry
Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG
May 31, 2026Francielle Vargas, João Robiatti, Diego Alves +6Hievi-Rag Retrieval-Augmented Generation
A Fiber Criterion for Representation Identifiability in Supervised Learning
May 31, 2026Vasileios SevetlidisIdentifiability Supervised Learning
Measuring the Symmetry--Data Exchange Rate
May 31, 2026Ahmed M. AdlyEquivariance Asymmetry
Oscillatory State-Space Models as Inductive Biases for Physics-Informed Neural PDE Solvers
May 29, 2026Abhishek Chandra, Taniya KapoorNeural Partial Differential Equation Solvers Partial Differential Equations
Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias
May 27, 2026Mohua Das, Pierfrancesco Beneventano, Shibshankar Dey +2Learning Rates Deep Neural Network
Benchmarking Inductive Biases for Multivariate Time-Series Anomaly Detection with a Robust Multi-View Channel-Graph Detector
May 27, 2026Junhao Wei, Yanxiao Li, Bidong Chen +9Time-Series Anomaly Detection Anomaly Detection
Energy-Gated Attention and Wavelet Positional Encoding: Complementary Inductive Biases for Transformer Attention
May 25, 2026Athanasios ZerisTransformer Attention Positional Encoding
On the Role of Inductive Bias in Time-Series Pretraining: A Case Study in Learning Generalizable Representations for Clinical Time Series
May 25, 2026Sharmita Dey, Diego Paez-GranadosModel Pretraining Representation Learning
Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers
May 25, 2026Shyam Sankaran, Hanwen Wang, Paris PerdikarisNeural Partial Differential Equation Solvers Neural Architectures
DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual Reinforcement
May 25, 2026Renjie Lu, Xulong Zhang, Xiaoyang Qu +2Inductive Bias
The Cognitive Categorical Transformer: Category-Theoretic Inductive Biases for Language Modeling
May 22, 2026Al KariLanguage Model Perplexity Inductive Bias
Graph Alignment Topology as an Inductive Bias for Grounding Detection
May 21, 2026Paul Landes, Pranav Herur, Adam Cross +1Large Language Model Hallucination Large Language Model Alignment
Energy-Gated Attention: Spectral Salience as an Inductive Bias for Transformer Attention
May 21, 2026Athanasios ZerisTransformer Attention Inductive Bias
Gaussian Sheaf Neural Networks
May 20, 2026André Ribeiro, Ana Luiza Tenório, Tiago da Silva +1Graph Neural Networks Graph Learning
Data-Efficient Neural Operator Training via Physics-Based Active Learning
May 20, 2026Alicja Polanska, Lorenzo Zanisi, Vignesh Gopakumar +1Neural Operators Active Learning
A Mechanistic Study of Tabular Foundation Models
May 20, 2026Marin Biloš, James T. Wilson, Anderson Schneider +1Tabular Foundation Models Inductive Bias
Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations
May 20, 2026Kin Whye Chew, Jingxian WangActive Learning Meta-Learning
When Irregularity Helps: A Subclass Analysis of Inductive Bias in Neural Morphology
May 19, 2026Wen ZhangMorphology Mismatch
Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases
May 19, 2026Jingwen Liu, Ezra Edelman, Surbhi Goel +1Table Reasoning Datasets Inductive Bias
Temporal Task Diversity: Inductive Biases Under Non-Stationarity in Synthetic Sequence Modelling
May 18, 2026Afiq Abdillah Effiezal Aswadi, Oliver Britton, Ross Baker +1Inductive Bias Sequence Modeling
PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting
May 16, 2026Yangyou Liu, Zezhi Shao, Xinyu Chen +3Non-Stationarity Time Series Forecasting

Sep 8, 2026 · astro-ph.COJ/K move · Enter open · S save

Inductive Biases in Field-Level Cosmological Inference from Galaxy Catalogs

James O. Baldwin, Shy Genel, Francisco Villaescusa-Navarro

We perform field-level likelihood-free inference of the matter density parameter

Ω_m

from simulated galaxy catalogs using machine learning models with differing inductive biases. Using hydrodynamic simulations from CAMELS, we examine how observable choice and architecture govern cosmological information extraction. We consider galaxy positions and line-of-sight peculiar velocities, separately and jointly, and compare permutation-invariant Deep Sets, implemented with either multilayer perceptrons (MLPs) or Kolmogorov-Arnold Networks (KANs), to graph neural networks (GNNs), which explicitly encode spatial relations. We test in-distribution and out-of-distribution (OOD) performance across simulations with different subgrid galaxy-formation prescriptions. Deep Sets infer

Ω_m

from velocities alone with mean relative errors of approximately

18\%

in-distribution and

\sim25\%

OOD, with KANs and MLPs achieving comparable performance. In contrast, the same set-based approach does not yield useful

σ_8

predictions in either in-distribution or cross-suite tests. Adding positions does not improve Deep Sets, while GNNs infer

Ω_m

with mean relative errors of about

10\%

in-distribution and

10

17\%

OOD. These results indicate that peculiar velocities provide the dominant source of

Ω_m

information for set-based models in this setting, while spatial information is most effectively used by architectures that explicitly encode galaxy-galaxy relations. Because the velocity inputs are exact simulated peculiar velocities, applications to survey data will require validation under realistic velocity-measurement noise, selection effects, and survey geometry.

Cosmology Inductive Bias

Open paper Ask about it PDF