R
Published on

ICLR 2026 — Graphs & Structured Data

Graphs & Structured Data

110 papers (0 oral)

TabStruct: Measuring Structural Fidelity of Tabular Data

BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic Interactions

CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Data

Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series

Beyond Entity Correlations: Disentangling Event Causal Puzzles in Temporal Knowledge Graphs

Prior-free Tabular Test-time Adaptation

DAMR: Efficient and Adaptive Context-Aware Knowledge Graph Question Answering with LLM-Guided MCTS

Tab-MIA: A Benchmark Dataset for Membership Inference Attacks on Tabular Data in LLMs

Multi-Scale Hypergraph Meets LLMs: Aligning Large Language Models for Time Series Analysis

Can we generate portable representations for clinical time series data using LLMs?

From Conversation to Query Execution: Benchmarking User and Tool Interactions for EHR Database Agents

Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting

Test-Time Efficient Pretrained Model Portfolios for Time Series Forecasting

Towards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed Interaction

Reliable Probabilistic Forecasting of Irregular Time Series through Marginalization-Consistent Flows

Aurora: Towards Universal Generative Multimodal Time Series Forecasting

DeNOTS: Stable Deep Neural ODEs for Time Series

TIMESLIVER : SYMBOLIC-LINEAR DECOMPOSITION FOR EXPLAINABLE TIME SERIES CLASSIFICATION

CoRA: Boosting Time Series Foundation Models for Multivariate Forecasting through Correlation-aware Adapter

When Foundation Models are One-Liners: Limitations and Future Directions for Time Series Anomaly Detection

TimeSeriesExamAgent: Creating Time Series Reasoning Benchmarks at Scale

Lost in the Non-convex Loss Landscape: How to Fine-tune the Large Time Series Model?

LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models

AutoDA-Timeseries: Automated Data Augmentation for Time Series

Plan-Answer-Refine-on-Graph: Structured Planning and Self-Refinement for Large Language Model Reasoning on Knowledge Graphs

Low Rank Transformer for Multivariate Time Series Anomaly Detection and Localization

Delta-XAI: A Unified Framework for Explaining Prediction Changes in Online Time Series Monitoring

CTBench: Cryptocurrency Time Series Generation Benchmark

MMPD: Diverse Time Series Forecasting via Multi-Mode Patch Diffusion Loss

COSA: Context-aware Output-Space Adapter for Test-Time Adaptation in Time Series Forecasting

SRT: Super-Resolution for Time Series via Disentangled Rectified Flow

ICDiffAD: Implicit Conditioning Diffusion Model for Time Series Anomaly Detection

Are Global Dependencies Necessary? Scalable Time Series Forecasting via Local Cross-Variate Modeling

UNDERSTANDING TRANSFORMERS FOR TIME SERIES FORECASTING: A CASE STUDY ON MOIRAI

Flock: A Knowledge Graph Foundation Model via Learning on Random Walks

ASTGI: Adaptive Spatio-Temporal Graph Interactions for Irregular Multivariate Time Series Forecasting

Designing Time Series Experiments in A/B Testing with Transformer Reinforcement Learning

TCD-Arena: Assessing Robustness of Time Series Causal Discovery Methods Against Assumption Violations

DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Series

Understanding Transformers for Time Series: Rank Structure, Flow-of-ranks, and Compressibility

A Bayesian Nonparametric Framework for Private, Fair, and Balanced Tabular Data Synthesis

MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection

Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs

CPiRi: Channel Permutation-Invariant Relational Interaction for Multivariate Time Series Forecasting

Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingness

PYRREGULAR: A Unified Framework for Irregular Time Series, with Classification Benchmarks

Beyond Accuracy: Are Time Series Foundation Models Well-Calibrated?

TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models

FACT: Fine-grained Across-variable Convolution for Multivariate Time Series Forecasting

SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning

MambaSL: Exploring Single-Layer Mamba for Time Series Classification

PhaseFormer: From Patches to Phases for Efficient and Effective Time Series Forecasting

Adaptive Conformal Anomaly Detection with Time Series Foundation Models for Signal Monitoring.

SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verification

Scaling Knowledge Graph Construction through Synthetic Data Generation and Distillation

FeDaL: Federated Dataset Learning for General Time Series Foundation Models

Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder Identification

Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph Reasoning

Conditionally Whitened Generative Models for Probabilistic Time Series Forecasting

GIT-BO: High-Dimensional Bayesian Optimization with Tabular Foundation Models

An Expanded Benchmark that Rediscovers and Affirms the Edge of Uncertainty Sampling for Active Learning in Tabular Datasets

2868. VideoNSA: Native Sparse Attention Scales Video Understanding

  • Topics: Computer Vision

Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion

VoG: Enhancing LLM Reasoning through Stepwise Verification on Knowledge Graphs

KGOT: Unified Knowledge Graph and Optimal Transport Pseudo-Labeling for Molecule-Protein Interaction Prediction

Online time series prediction using feature adjustment

Latent-to-Data Cascaded Diffusion Models for Unconditional Time Series Generation

Rating Quality of Diverse Time Series Data by Meta-learning from LLM Judgment

MixLinear: Extreme Low Resource Multivariate Time Series Forecasting with 0.1K0.1K Parameters

Characteristic Root Analysis and Regularization for Linear Time Series Forecasting

PINFDiT: Energy-Based Physics-Informed Diffusion Transformers for General-purpose Time Series Tasks

Understanding the Implicit Biases of Design Choices for Time Series Foundation Models

Numerion: A Multi-Hypercomplex Model for Time Series Forecasting

TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning

ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detection

Human-LLM Collaborative Feature Engineering for Tabular Data

Enhancing Multivariate Time Series Forecasting with Global Temporal Retrieval

Scaling Knowledge Editing in LLMs to 100,000 Facts with Neural KV Database

TEDM: Time Series Forecasting with Elucidated Diffusion Models

Flow-based Conformal Prediction for Multi-dimensional Time Series

HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature

Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities

Relatron: Automating Relational Machine Learning over Relational Databases

Adapt Data to Model: Adaptive Transformation Optimization for Domain-shared Time Series Foundation Models

Repurposing Foundation Model for Generalizable Medical Time Series Classification

Complexity- and Statistics-Guided Anomaly Detection in Time Series Foundation Models

SwiftTS: A Swift Selection Framework for Time Series Pre-trained Models via Multi-task Meta-Learning

Local Geometry Attention for Time Series Forecasting under Realistic Corruptions

xRFM: Accurate, scalable, and interpretable feature learning models for tabular data

CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context Engineering

Harnessing Temporal Databases for Systematic Evaluation of Factual Time-Sensitive Question-Answering in LLMs

AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM

Tabby: A Language Model Architecture for Tabular and Structured Data Synthesis

4923. What happens when generative AI models train recursively on each others' outputs?

  • Topics: Diffusion Models & Generative AI

HiMAE: Hierarchical Masked Autoencoders Discover Resolution-Specific Structure in Wearable Time Series

Routing Channel-Patch Dependencies in Time Series Forecasting with Graph Spectral Decomposition

ResCP: Reservoir Conformal Prediction for Time Series Forecasting

TAMMs: Change Understanding and Forecasting in Satellite Image Time Series with Temporal-Aware Multimodal Models

Learning Recursive Multi-Scale Representations for Irregular Multivariate Time Series Forecasting

ProtoTS: Learning Hierarchical Prototypes for Explainable Time Series Forecasting

UniCA: Unified Covariate Adaptation for Time Series Foundation Model

GCGNet: Graph-Consistent Generative Network for Time Series Forecasting with Exogenous Variables

GARLIC: Graph Attention-based Relational Learning of Multivariate Time Series in Intensive Care

Contextual and Seasonal LSTMs for Time Series Anomaly Detection

Unlocking the Value of Text: Event-Driven Reasoning and Multi-Level Alignment for Time Series Forecasting

Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling

PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecasting

The Forecast After the Forecast: A Post-Processing Shift in Time Series