Blog

Insights on time series foundation models, forecasting techniques, and the TSFM.ai platform.

Latestresearchllmcomparison

TSFM vs LLM Research, Compared

We compared TSFM research against LLM research end-to-end — anchoring TSFM at Oct 2023 against LLM at Oct 2018, pulling publication-volume curves, model-release tempo, theme-by-theme alignment, and the published bibliometric record on both sides. The 5-year offset is real but the comparison is genuinely multi-axis: TSFMs are ahead on model releases and open weights, behind on publication velocity and scaling laws, and missing a ChatGPT-style consumer moment entirely.

May 22, 202610 min read

2026

39 articles
researchpublication-trends

How TSFM Research Evolved: A Data-Driven Look at 2021–2026

679 papers, 43 release records, five years. We pulled the publication record from OpenAlex and assembled the model release record from primary sources to trace how the time-series foundation model field actually evolved — month by month, model by model.

May 21, 202613 min read
arfbenchbenchmarking

ARFBench: Time-Series Models Have to Answer Questions Now

ARFBench turns observability telemetry into multiple-choice anomaly reasoning questions, exposing a new gap between forecasting accuracy and time-series question answering.

May 19, 20268 min read
kairoshopeclassification

KairosHope: A Dual-Memory TSFM Built for Classification, Not Forecasting

KairosHope shifts the TSFM conversation from forecasting-first models to specialized classification, combining dual neural memory with classical time-series features, but public checkpoints are not available yet.

May 18, 20269 min read
kronosfinance

Kronos: A Domain-Specific Foundation Model for the Language of Financial Markets

Kronos is a decoder-only foundation model pre-trained on 12 billion K-line records from 45 global exchanges, with a specialized tokenizer that quantizes OHLCV bars into hierarchical coarse/fine subtokens. Accepted at AAAI 2026, the model reports 93% higher RankIC than the leading general-purpose TSFM on financial benchmarks and is open-sourced under MIT.

May 17, 20268 min read
scaling-lawsresearch

TSFM Scaling Laws in 2026: What Seven Families Tell Us About Bigger Time Series Models

For most of the time series foundation model era, bigger has not reliably meant better. By mid-2026 the empirical picture has changed: seven released TSFM families — from 1M-parameter Granite TTM up to 8.3B-parameter Timer-S1 — give the field enough scaling data points to talk seriously about scaling laws. Toto 2.0 and Xihe report monotonic scaling at five sizes each; TimesFM 2.5 went the other way and got smaller; Moirai held mostly at Base. This post walks through what each family proves, fits the data against the published TSFM scaling-law literature, and works out what 'compute-optimal' should actually mean when inference dominates total cost.

May 17, 202616 min read
xihemodel-release

Xihe: A Scaling Family Built Around Hierarchical Interleaved Block Attention

Xihe is a five-checkpoint TSFM family (9.5M → 1.5B parameters) built around Hierarchical Interleaved Block Attention (HIBA), a sparse multi-scale attention layout that alternates intra-block and inter-block attention at hierarchical block sizes. The paper reports new top-of-leaderboard zero-shot numbers on GIFT-Eval and a smallest-model line that already beats many incumbents.

May 13, 20267 min read
bvarbayesian-forecasting

BVARs vs. TSFMs: Priors, Shocks, and the New Forecasting Stack

Bayesian VARs and time series foundation models solve different forecasting problems: BVARs encode structural priors and scenarios; TSFMs scale zero-shot forecasts across heterogeneous series.

May 12, 20269 min read
totodatadog

Toto 2.0: Datadog Turns Observability Forecasting Into a Scaling Family

Datadog's Toto 2.0 release changes the Toto story from one 151M-parameter observability model into a scaling family. TSFM.ai hosts four launch checkpoints from 4M to 1B parameters, leaving 2.5B upstream-only for now, while the release adds u-muP scaling, alternating time/variate attention, and quantile forecasts.

May 8, 20267 min read
agriculturecommodity-prices

Agricultural Commodity Forecasting: When Zero-Shot TSFMs Beat Futures-Based USDA Baselines

A new agricultural price forecasting study compares 17 methods on USDA ERS commodity prices from 1997-2025. The surprising result: zero-shot TSFMs take the top five monthly forecasting ranks, and Time-MoE beats futures-based USDA benchmarks on wheat and corn despite using only historical cash prices.

May 5, 20266 min read
auroramultimodal

Aurora: What the First Multimodal Time Series Foundation Model Actually Does

Aurora (ICLR 2026) is the first pretrained TSFM to fuse text and visual structure at training time — and it benchmarks above Chronos, Moirai, and TimesFM on both deterministic and probabilistic metrics. Here's what the architecture actually does, what 'multimodal' means in practice, and how to run it today.

Apr 27, 20269 min read
iclr-2026research

ICLR 2026 TSFM Roundup: 87 Time Series Papers and What They Mean for the Field

ICLR 2026 accepted 87 time series papers — the first year with a dedicated TSALM workshop. Here's what the research community spent the year building: multimodal pretraining, elucidated diffusion, prototype-guided generation, and a renewed focus on rigorous evaluation.

Apr 27, 20269 min read
tedmdiffusion

TEDM: What Happens When You Apply Elucidated Diffusion Models to Time Series

TEDM (ICLR 2026) adapts Karras et al.'s Elucidated Diffusion Models to time series by replacing hand-crafted noise schedules with data-derived covariance estimates — achieving linear inference complexity in forecast horizon and the fastest training time among diffusion-based forecasters.

Apr 27, 20268 min read
energybenchmarks

CPU-Only Energy Load Forecasting: What a New ERCOT Benchmark Reveals About TSFMs Without GPUs

A new multi-dimensional benchmark runs four TSFMs on a consumer laptop—AMD Ryzen 7, 16 GB RAM, no GPU—against ERCOT hourly load data from 2020 to 2024. The headline finding: foundation models beat Prophet catastrophically at short context, cluster within statistical noise at 512-hour context, and diverge sharply on calibration. Here is what it means for practitioners who cannot assume GPU access.

Apr 21, 202611 min read
in-context-learningmulti-task

iAmTime: Instruction-Conditioned In-Context Learning for Multi-Task Time Series Foundation Models

A new foundation model shows that time series tasks — forecasting, classification, anomaly detection, imputation — can all be specified at inference time through structured input-output demonstrations, without task-specific heads or fine-tuning. The model, iAmTime, achieves best-in-class CRPS on fev-bench and competitive performance on GIFT-Eval using only zero-shot, instruction-conditioned in-context learning.

Apr 18, 20269 min read
benchmarkingevaluation

TIME: Why Task-Centric Zero-Shot Evaluation Changes How We Compare TSFMs

Most TSFM benchmarks recycle legacy datasets, apply mechanical horizon rules, and report model rankings by coarse domain label. TIME (arXiv:2602.12147, February 2026) breaks all three habits. Built from 50 fresh datasets and 98 operationally-aligned forecasting tasks, it evaluates 12 TSFMs under strict zero-shot conditions and introduces a 7-feature binary pattern encoding that replaces static domain labels with intrinsic temporal structure. The result is a leaderboard where model rankings are stable at the top but shift substantially by stationarity and aggregation level — and where the finding that newer TSFM generations genuinely outperform their predecessors can be verified on contamination-free ground.

Apr 15, 202614 min read
ciscomultiresolution

Cisco Time Series Model: Multiresolution Input as an Architecture Primitive

Cisco's CTSM 1.0 takes a different approach to long context: instead of extending the sequence length, it feeds the model two views of the same history at different resolutions — coarse hourly context for global patterns, fine minute-level context for local detail. On observability data the approach leads MASE by 16%, and on GIFT-Eval it lands third without test-set leakage.

Apr 13, 20269 min read
ibmgranite

IBM's March 2026 Time-Series Refresh: Four Models, Three Forecasters, and a Surprise

IBM dropped four time-series foundation models on March 31 — FlowState r1.1, TTM-r3, PatchTST-FM r1, and TSPulse r1. Between them they cover point forecasting, probabilistic forecasting, anomaly detection, classification, and imputation. Here is what changed architecturally and why it matters.

Apr 12, 20268 min read
benchmarkingevaluation

TFRBench: The First Benchmark for Evaluating Reasoning in Forecasting Systems

Nearly every time series benchmark measures whether a model predicts the right numbers. TFRBench (arXiv:2604.05364, April 2026, Google Cloud AI Research) asks a different question: can the model explain *why*? According to its authors, TFRBench is the first benchmark designed to evaluate the reasoning capabilities of forecasting systems — covering cross-channel dependencies, trends, seasonality, and external events — finding that off-the-shelf LLMs consistently struggle with temporal reasoning, while models prompted with high-quality reasoning traces improve from about 40.2% to 56.6% on the share of series beating the naive baseline. The implications touch deployment design decisions across any organization asking forecasting systems to justify their outputs.

Apr 10, 202612 min read
benchmarkingevaluation

QuitoBench: What a Billion-Scale Benchmark Reveals About When to Use Foundation Models

Most time series benchmarks organize datasets by domain label — traffic, energy, weather — which says little about why a series is hard to forecast. QuitoBench (arXiv:2603.26017, March 2026) reorganizes evaluation around TSF regimes: eight combinations of trend strength, seasonality strength, and forecastability. Benchmarking 10 models across 232,200 instances on the Quito corpus, it reports a context-length crossover, a forecastability dominance finding, and practical model-selection guidance that domain-based benchmarks tend to blur.

Apr 6, 202611 min read
multivariateadapter

CoRA: A Plug-and-Play Adapter for Adding Cross-Channel Correlation to Any TSFM

Most time series foundation models treat each variate independently and miss the cross-channel dynamics that matter most in real multivariate workloads. CoRA — a Correlation-aware Adapter from East China Normal University and Huawei — is a lightweight plug-and-play module that adds three-type correlation modeling to any pretrained TSFM during fine-tuning, with linear inference complexity and consistent improvements across six base models on ten benchmark datasets.

Mar 31, 202613 min read
moiraisalesforce

Moirai-MoE: Token-Level Specialization for Time Series Foundation Models

Salesforce's Moirai-MoE replaces Moirai's frequency-specific projection layers with a sparse mixture of experts, enabling automatic token-level specialization. With only 11M activated parameters, Moirai-MoE-Small beats Moirai-Large across 29 Monash benchmarks, and Moirai-MoE-Base outperforms Chronos and TimesFM on zero-shot aggregate metrics.

Mar 28, 202610 min read
timesfmin-context-learning

TimesFM In-Context Fine-Tuning: Domain Adaptation Without Weight Updates

Google Research's In-Context Fine-Tuning (ICF) lets TimesFM adapt to new domains at inference time by prompting with related time series examples — no gradient updates, no training pipeline, roughly 7% better accuracy on aggregate across Monash benchmarks. Here's how it works and when to use it.

Mar 23, 20269 min read
causal-inferenceinterventions

Causal Reasoning in TSFMs: From Forecasting to Decision Support

TSFMs tell you what will happen. Decision-makers need to know what would happen under different actions. Two new research directions — interventional priors and activation transplantation — are giving TSFMs their first taste of causal reasoning, opening a path from passive prediction to active decision support.

Mar 19, 202612 min read
world-modelsJEPA

TSFMs vs World Models: Two Philosophies of Prediction

Yann LeCun's AMI Labs just raised $1B to build world models. DeepMind shipped Genie 3. Researchers are adapting JEPA for time series. Should practitioners care — or is this a different field solving a different problem? Here's a technical comparison of the two prediction paradigms.

Mar 18, 20264 min read
architectureencoder

Encoder-Only, Decoder-Only, and Encoder-Decoder: Architecture Tradeoffs in Time Series Foundation Models

Every major TSFM makes an architectural bet — encoder-only, decoder-only, or encoder-decoder. Each choice cascades into real differences in inference speed, horizon flexibility, and what the model can learn. Here's how to think about the tradeoffs.

Mar 17, 202611 min read
ibmflowstate

IBM FlowState: The First Sampling-Rate-Invariant Time Series Foundation Model

IBM Research's FlowState abandons transformer attention entirely in favor of a State Space Model encoder and a Functional Basis Decoder that produces continuous-time forecasts. Under 10M parameters, it reaches the top of the GIFT-Eval zero-shot leaderboard — and can adapt to any sampling rate without retraining.

Mar 17, 202611 min read
benchmarkingevaluation

Impermanent: The First Live Benchmark for Temporal Generalization in TSFMs

Static benchmarks contaminate themselves over time. Impermanent is the first live benchmark that scores TSFM forecasts sequentially on a continuously updated data stream, testing whether foundation-model generalization actually holds once real time passes.

Mar 14, 20267 min read
timer-s1tsinghua

Timer-S1: Billion-Scale Time Series Forecasting with Serial Scaling

Timer-S1 from Tsinghua University introduces Serial Token Prediction and a sparse MoE architecture with 8.3B total parameters to achieve state-of-the-art forecasting on the GIFT-Eval benchmark.

Mar 10, 202612 min read
enterpriseforecasting

Traditional Forecasting vs. TSFMs: The True Cost of Building and Maintaining Enterprise Forecast Pipelines

Enterprise forecasting pipelines take months to build, require specialized teams to maintain, and silently accumulate technical debt. Time series foundation models compress the entire lifecycle into an API call. Here's a honest comparison of both paths.

Feb 25, 202617 min read
lorapeft

LoRA and PEFT for Time Series Foundation Models: A Technical Guide

A deep technical guide to applying Low-Rank Adaptation and parameter-efficient fine-tuning to time series foundation models — covering architecture-specific strategies, rank selection, layer targeting, catastrophic forgetting, and practical results across Chronos-2, MOMENT, Moirai, TimesFM, and more.

Feb 23, 202621 min read
benchmarkingboom

BOOM: Datadog's Observability Forecasting Benchmark

BOOM evaluates time series models on 2,807 real-world production monitoring series from Datadog. Here's how it works and why observability data demands its own benchmark.

Feb 20, 20267 min read
streamingreal-time

Real-Time Streaming Inference with TSFMs: Moving from Batch to Continuous Forecasting

Most TSFM deployments run forecasts in hourly or daily batches, but a growing class of use cases demands continuous, low-latency predictions. Here's how to architect streaming inference pipelines for time series foundation models.

Feb 18, 20264 min read
benchmarkinggift-eval

GIFT-Eval: Salesforce's Comprehensive TSFM Benchmark

GIFT-Eval tests foundation models across 23 datasets, 7 domains, and both univariate and multivariate settings. Here's what makes it one of the most thorough TSFM benchmarks available.

Feb 15, 20267 min read
mcpclaude

Giving Claude Time-Series Superpowers with MCP

Large language models can't forecast time series — but they don't have to. With MCP tool use, Claude can call specialized foundation models and return calibrated probabilistic forecasts in a single conversation turn.

Feb 12, 20266 min read
guidemodels

The 2026 TSFM Toolkit: Which Foundation Model for Which Job?

With 18+ time series foundation models now available, choosing the right one for your workload is the real challenge. Here's a practitioner's decision framework.

Feb 10, 20267 min read
benchmarkingfev-bench

FEV Bench: The Zero-Shot Forecasting Benchmark Explained

FEV Bench from AutoGluon evaluates foundation models on pure zero-shot forecasting across 29 diverse datasets. Here's how it works, what it measures, and why it matters.

Feb 10, 20266 min read
multimodalllm

Multimodal Time Series: Combining Numerical Data with Text and Natural Language Context

What if forecast models could read a description of your data alongside the numbers? Multimodal time series research is exploring how natural language context — domain descriptions, known events, business constraints — can improve forecasts, especially in zero-shot settings.

Feb 5, 20265 min read
outlooktrends

The TSFM Landscape in 2026: Trends and Predictions

As we enter 2026, the time series foundation model ecosystem is maturing rapidly. Here are the trends shaping the next year.

Jan 22, 20265 min read
networktelecom

Network Traffic Forecasting and Telecom Capacity Planning with TSFMs

Telecom and network operators generate some of the richest time series data on earth — CDN throughput, cell tower load, DNS query rates — and time series foundation models can forecast it without per-metric training.

Jan 8, 20265 min read

2025

21 articles
inferencegpu

Scaling TSFM Inference: GPU Optimization

Serving TSFMs at scale requires careful GPU optimization. Here's how we achieve sub-100ms latency for batch forecasting.

Dec 1, 20255 min read
totodatadog

Toto: Datadog's Domain-Specific TSFM for Observability

Datadog's Toto is a 151M-parameter transformer trained on trillions of observability data points, purpose-built for forecasting infrastructure metrics like CPU utilization, error rates, and request latency.

Nov 15, 20255 min read
tirexnx-ai

TiRex: NX-AI's xLSTM Zero-Shot Forecasting Model

TiRex is NX-AI's 35M-parameter xLSTM forecasting model, built for strong zero-shot performance across short and long horizons with point and quantile outputs.

Oct 25, 20253 min read
model-routingtsfm-ai

Smart Model Routing: Choosing the Best TSFM

Not every time series needs the same model. TSFM.ai's routing engine automatically selects the best foundation model for each request.

Oct 12, 20255 min read
manufacturingpredictive-maintenance

Predictive Maintenance in Manufacturing with TSFMs

Time series foundation models enable predictive maintenance across thousands of machine types without training individual models, catching bearing degradation, tool wear, and compressor decay before costly failures occur.

Sep 5, 20255 min read
time-llmllm

LLM Reprogramming for Time Series: Time-LLM's Prompt-as-Prefix Approach

Time-LLM reprograms a frozen LLaMA-7B to forecast time series by mapping patches into the LLM's embedding space and prepending natural language task descriptions, raising a provocative question about what large language models actually learn.

Aug 25, 20254 min read
supply-chainlogistics

Supply Chain and Logistics Forecasting with TSFMs

Time series foundation models tackle the toughest supply chain forecasting problems, from the bullwhip effect to cold-start routes, enabling leaner inventory and fewer stockouts across complex logistics networks.

Aug 18, 20254 min read
retaildemand-planning

How Retailers Use TSFMs for Demand Planning

From inventory optimization to markdown pricing, time series foundation models are transforming how retailers forecast demand.

Aug 4, 20254 min read
healthcareuse-case

Healthcare Applications of Time Series Foundation Models

From ICU vital sign monitoring to hospital capacity planning, time series foundation models address healthcare's most pressing data challenges — starting with the chronic scarcity of labeled clinical data.

Jul 14, 20254 min read
momentcmu

MOMENT: CMU's Model for Time Series Understanding

MOMENT from Carnegie Mellon is a multi-task time series foundation model that handles forecasting, classification, anomaly detection, and imputation.

Jun 17, 20254 min read
foundation-modelsexplainer

The Founder's Crash Course on Time Series Foundation Models

You already ship forecasting in your product. Here's why time series foundation models change the economics, accuracy, and speed of everything you've built — and what to do about it.

Jun 15, 20257 min read
climateweather

Climate and Weather Forecasting with Time Series Foundation Models

Time series foundation models are finding a practical niche in climate and weather applications — not replacing physics-based models, but filling gaps they leave behind.

Jun 2, 20254 min read
context-lengtharchitecture

Context Length in TSFMs: How Much History Do Foundation Models Need?

Time series foundation models accept anywhere from 4K to 16K input time steps, but more context is not always better. We break down when longer history helps, when it hurts, and how to choose the right lookback for your data.

May 22, 20255 min read
multivariateforecasting

The State of Multivariate Forecasting in 2025

Multivariate time series forecasting remains one of the hardest problems in ML. Here's where foundation models stand in 2025.

May 8, 20256 min read
sundialdiffusion

Diffusion Models for Time Series: Inside Tsinghua's Sundial

Sundial applies flow-matching diffusion to time series forecasting, producing full predictive distributions from noise in fewer steps than standard diffusion models.

Apr 25, 20254 min read
covariatesforecasting

Covariates in Time Series Forecasting: A Practical Guide to Exogenous Regressors

Covariates like holidays, promotions, and weather can dramatically improve forecast accuracy. Here's how modern TSFMs handle them and when they actually help.

Apr 15, 20255 min read
fine-tuningzero-shot

Fine-Tuning vs. Zero-Shot: When to Customize

Zero-shot TSFMs are powerful out of the box, but sometimes fine-tuning on your data delivers a meaningful accuracy boost. Here's how to decide.

Mar 28, 20255 min read
granite-ttmibm

Tiny Models, Big Results: IBM's Granite TTM and the MLP-Mixer Architecture for Time Series

IBM's Granite TTM packs competitive forecasting accuracy into roughly 1 million parameters by replacing attention with MLP-Mixer layers, enabling sub-100ms inference on CPU and opening the door to edge and serverless deployment.

Mar 12, 20253 min read
chronosamazon

Chronos v2: What's New and Why It Matters

Amazon's Chronos-Bolt brings major improvements: direct multi-step forecasting, much lower latency than the original Chronos-T5 stack, and stronger benchmark results.

Feb 20, 20254 min read
conformal-predictionuncertainty

Conformal Prediction: Calibrated Uncertainty Intervals for Time Series Foundation Models

Model-native prediction intervals are often miscalibrated. Conformal prediction provides a distribution-free wrapper that turns any forecaster's output into intervals with guaranteed coverage.

Feb 5, 20255 min read
case-studyenergy

Case Study: Energy Demand Forecasting

How a European energy utility used TSFM.ai to improve demand forecasts by 23% compared to their existing gradient boosted tree pipeline.

Jan 15, 20254 min read

2024

15 articles
tsfm-aiproduct

Introducing TSFM.ai: The Unified API for Time Series

We're launching TSFM.ai — a single API that gives you access to every major time series foundation model with automatic routing and optimization.

Dec 3, 20243 min read
benchmarkingevaluation

The Challenges of Benchmarking TSFMs

Benchmarking time series foundation models is harder than it looks. Here's why results often conflict and what the field is doing about it.

Nov 5, 20245 min read
time-moexiaohongshu

Time-MoE: Xiaohongshu's Mixture-of-Experts Architecture for Time Series Forecasting

Xiaohongshu's Time-MoE brings sparse mixture-of-experts to time series forecasting, activating only a subset of parameters per input to achieve large-model capacity at lower inference cost.

Oct 28, 20244 min read
lag-llamaopen-source

Lag-Llama: The Open-Source Time Series Foundation Model

Lag-Llama brings the decoder-only LLM architecture to time series with lag-based tokenization and distributional outputs.

Oct 10, 20245 min read
probabilistic-forecastinguncertainty

Prediction Intervals vs. Point Forecasts

Why a single predicted number is rarely enough, and how prediction intervals help you make better decisions under uncertainty.

Sep 18, 20244 min read
synthetic-datatraining

Synthetic Training Data for TSFMs: KernelSynth and Gaussian Process Augmentation

How KernelSynth uses Gaussian process priors with composed kernels to generate synthetic time series, and why roughly half of Chronos's training data is artificially generated.

Sep 2, 20245 min read
productionmlops

Building Production Forecast Pipelines with TSFMs

A practical guide to moving time series foundation models from notebooks to production-grade forecasting systems.

Aug 30, 20244 min read
financevolatility

Financial Time Series: Volatility Modeling and Risk Forecasting with TSFMs

Financial markets produce some of the most challenging time series data. Here's how time series foundation models handle volatility clustering, tail risk estimation, and regulatory risk forecasting.

Aug 15, 20244 min read
moiraisalesforce

Moirai: Salesforce's Universal Forecasting Transformer

Moirai from Salesforce introduces a universal forecasting transformer that handles variable frequencies, prediction lengths, and multivariate inputs.

Jul 22, 20244 min read
tokenizationarchitecture

Tokenization Strategies Compared: Quantization vs Patching vs Lag-Based

Time series foundation models must bridge the gap between continuous signals and discrete transformer inputs. We compare three dominant tokenization strategies — quantization, patching, and lag-based — and when each one works best.

Jul 8, 20244 min read
anomaly-detectionforecasting

Anomaly Detection with Time Series Foundation Models

Foundation models aren't just for forecasting — they're surprisingly effective at detecting anomalies in time series data.

Jun 14, 20245 min read
timesfmgoogle

TimesFM: Google's Approach to Time Series Foundation Models

Google's TimesFM family is a decoder-only foundation model line for time series, spanning the original 200M release and newer 2.0/2.5 checkpoints with longer context and optional quantile support.

May 20, 20245 min read
zero-shotforecasting

Zero-Shot Forecasting: Why It Matters

Zero-shot forecasting lets you generate predictions on unseen time series without any training. Here's why that's a game-changer.

Apr 12, 20244 min read
chronosamazon

A Deep Dive into Amazon Chronos

How Amazon's Chronos turns time series forecasting into a language modeling problem using tokenized values and T5 architectures.

Mar 5, 20244 min read
foundation-modelsexplainer

What Are Time Series Foundation Models?

An introduction to time series foundation models — what they are, how they work, and why they represent a paradigm shift in forecasting.

Jan 18, 20243 min read