Time Series papers, 2023–2026

Key findings

• Time Series went from 272 papers in 2023 to 876 in 2026, roughly 3.2x in three years.
• NeurIPS publishes the most Time Series work: 757 papers from 2023 to 2026, 35% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 6 in 2023 to 85 in 2026.
• Among the 5 topics under Graph and Structured Data, it ranks #1 by 2026 paper count; the fastest grower in the group, Molecular Modeling, is up 2.7x versus 3.2x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Batched Hartigan's $k$-Means Clustering
• ICML 2026A Control-Theoretic View of Mamba on Stability and Robustness
• ICLR 2026A Single Architecture for Representing Invariance Under Any Space Group
• CVPR 2026Activation Matters Test-time Activated Negative Labels for OOD Detection with
• NeurIPS 2025Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency
• ICML 2025$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting
• ICLR 2025A deep inverse-mapping model for a flapping robotic wing
• CVPR 2025Beyond Single-Modal Boundary: Cross-Modal Anomaly Detection through Visual Prototype and Harmonization
• NeurIPS 2024A Continuous-time Stochastic Gradient Descent Method for Continuous Data
• ICML 2024$S^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting
• ICLR 2024ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning
• CVPR 2024Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentation
• NeurIPS 2023A Sublinear-Time Spectral Clustering Oracle with Improved Preprocessing Time
• ICML 2023Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Time
• ICLR 2023A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
• CVPR 2023ActMAD: Activation Matching To Align Distributions for Test-Time-Training
• NeurIPS 2026A Locally Tokenized Generative Model for Robust Time-Series Watermarking
• ICML 2026ADHD Disease Detection Based on Short- and Long-Term Brain Function Encoding and Memory Graph Network
• ICLR 2026A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systems
• CVPR 2026Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis

All Time Series papers

757 papers, page 4 of 16

151. NeurIPS 2026Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and Direction
152. NeurIPS 2026Neural Fractional Stochastic Differential Equations
153. NeurIPS 2026Neural Neural Scaling Laws
154. NeurIPS 2026Neural Optimal Transport in Hilbert Spaces
155. NeurIPS 2026Neurosymbolic Learning for Inference-Time Argumentation
156. NeurIPS 2026NOCE-Net: Representation Learning for Battery Operational Context via Nested Sequence Modelling
157. NeurIPS 2026NPUsper: Eliminating Redundant Computation for Real-Time Whisper on Mobile NPUs
158. NeurIPS 2026OATS: Online Data Augmentation for Time Series Foundation Models
159. NeurIPS 2026Observable Neural ODEs for Identifiable Causal Forecasting in Continuous Time
160. NeurIPS 2026Observations Drift, Structures Remain: Structural Pretraining with Time Alignment for Electromagnetic Signals
161. NeurIPS 2026ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
162. NeurIPS 2026OHATP: Graph Anomaly Detection with Orthogonal-Hyperspherical Augmentation and Topology Perception
163. NeurIPS 2026On the Complexity of Discounted Robust MDPs with $L_p$ Uncertainty Sets
164. NeurIPS 2026On the Origin of Algorithmic Progress in AI: Evidence from Language Model Pre-Training
165. NeurIPS 2026One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection
166. NeurIPS 2026One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models
167. NeurIPS 2026One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective
168. NeurIPS 2026One-Time Soft Alignment Enables Resilient Learning without Weight Transport
169. NeurIPS 2026Online Change-point Detection using Foundation Probabilistic Forecasting Models
170. NeurIPS 2026Optimal Contextual Pricing under Agnostic Non-Lipschitz Demand
171. NeurIPS 2026Ordinary Least Squares as an Attention Mechanism
172. NeurIPS 2026PAC-Bayesian Bounds for Learning Partially Observed Stochastic Linear Time-Invariant State-Space Systems with Inputs and Sub-Gaussian Noise
173. NeurIPS 2026PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
174. NeurIPS 2026Paloma: Phase-Conditioned Residual Modulation for Time Series Forecasting
175. NeurIPS 2026PAMod: Modeling Cyclical Shifts via Phase-Amplitude Modulation for Non-stationary Time Series Forecasting
176. NeurIPS 2026PhyTS: A Benchmark for Scientific Time Series
177. NeurIPS 2026Polynomial-Time Algorithm for Thiele Voting Rules with Voter Interval Preferences
178. NeurIPS 2026Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals
179. NeurIPS 2026Position: Robust Reasoning Requires Internal Time, Not Scale Alone
180. NeurIPS 2026Precision-Pyramid: Towards real-time neural decoding for fault-tolerant quantum computing
181. NeurIPS 2026Predictive Surprise as Self-Grounding Concept Bottleneck for Interpretable Time Series
182. NeurIPS 2026Prior as Geometry, Not Generator: Weak-Diffusion Test-Time Reconstruction for Dynamic MRI
183. NeurIPS 2026PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
184. NeurIPS 2026Problem-Dependent Dynamic Regret over a Predictor Class with One-Gradient Feedback
185. NeurIPS 2026ProCTI: Prototype-Refined Global Conditioning for Diffusion-Based Time Series Imputation
186. NeurIPS 2026Progressive Memory Transformer: Memory-Aware Attention for Time-Series
187. NeurIPS 2026Prompt–Activation Duality: Improving Activation Steering via Attention-Level Interventions
188. NeurIPS 2026Proper Agnostic Learning of Functions of Halfspaces
189. NeurIPS 2026Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks
190. NeurIPS 2026Provable Test-Time Scaling for Beam Search in LLM Reasoning
191. NeurIPS 2026ProxySearch: Decoupled Inference-Time Scaling for Diffusion Models via Asymmetric Noise-Rank Transfer
192. NeurIPS 2026QWaveNet: Quantum-Enhanced Wavelet Network for Time Series Forecasting
193. NeurIPS 2026Raw-Routed Mixture of Adapters: A Causal Intervention for Routing Collapse in Time Series Foundation Models
194. NeurIPS 2026Reference-Guided Training: Adaptive Gradient Scaling via Per-Sample Loss Comparisons
195. NeurIPS 2026Resolving Time-Frequency Ridge Crossings via Frequency-Rate Lifting
196. NeurIPS 2026Response Time Enhances Alignment with Heterogeneous Preferences
197. NeurIPS 2026Rethinking Expressivity and Efficiency in Test-Time Training
198. NeurIPS 2026Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting
199. NeurIPS 2026Rethinking Time Series Tokenization from a Frequency Perspective
200. NeurIPS 2026Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection

FAQ

How many Time Series papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

2,157 in total: 272 in 2023, 424 in 2024, 585 in 2025, 876 in 2026.

How many Time Series papers are at NeurIPS 2026?

NeurIPS 2026 has 298 Time Series papers, versus 221 the year before.

How many Time Series papers are at ICLR 2026?

ICLR 2026 has 220 Time Series papers, versus 131 the year before.

How many Time Series papers are at ICML 2026?

ICML 2026 has 264 Time Series papers, versus 159 the year before.

How many Time Series papers are at CVPR 2026?

CVPR 2026 has 94 Time Series papers, versus 74 the year before.

Which conference publishes the most Time Series papers?

NeurIPS, with 757 papers from 2023 to 2026.