TimesFM
PulseAugur coverage of TimesFM — every cluster mentioning TimesFM across labs, papers, and developer communities, ranked by signal.
- 2026-08-24 product_launch Google Research released TimesFM 3.0, a new time-series foundation model. source
- 2026-08-11 product_launch Google has developed and released the TimesFM forecasting model. source
- 2025-09-23 research_milestone Google Research presented a new method for time-series foundation models to perform few-shot learning at inference time. source
6 day(s) with sentiment data
-
Foundation models show mixed results for pedestrian crowd forecasting
A new study published on arXiv evaluates the effectiveness of time-series foundation models (FMs) for pedestrian crowd count forecasting. The research compares seven different forecasting approaches, including tradition…
-
Tabby: Open-Source Time Series Foundation Model Unveiled
Researchers have introduced Tabby, an open-source probabilistic time series foundation model designed for long contexts. Tabby utilizes an encoder-only patch Transformer architecture and was trained on a diverse corpus …
-
Time-series AI models excel due to pretraining familiarity, not forecasting skill
A new study has revealed that pretraining familiarity, rather than genuine forecasting ability, significantly influences the performance of time-series foundation models. Researchers created a hold-out test set with dat…
-
Google's TimesFM tested on e-commerce data via Kimi's Agent Swarm
A user tested Google Research's TimesFM model on a synthetic e-commerce dataset, utilizing the Agent Swarm platform from Kimi. The post provides details and results from this evaluation.
-
Google unveils TimesFM-3 for multivariate time-series forecasting
Google Research has unveiled TimesFM-3, an AI model capable of multivariate forecasting. This model can analyze multiple time-series data points simultaneously, such as sales figures, weather patterns, and foot traffic,…
-
Google AI releases TimesFM-3 for multivariate time series forecasting
Google AI has unveiled TimesFM-3, a 330 million parameter foundation model designed for multivariate time series forecasting. Unlike its predecessors, which were limited to univariate predictions, TimesFM-3 can jointly …
-
Google Research releases TimesFM 3.0 for time-series forecasting
Google Research has released TimesFM 3.0, a new time-series foundation model built on a Stacked Mixing Transformer architecture. This model is designed for time-series forecasting and utilizes a decoder-only approach. I…
-
Google's TimesFM challenges traditional forecasting methods
Google has developed TimesFM, a novel forecasting model that deviates from traditional workflows. The model's approach prompts a reevaluation of standard forecasting methodologies. This new tool offers a different persp…
-
TS-Mob framework enhances time series models for human mobility prediction
Researchers have developed TS-Mob, a new framework designed to improve time series foundation models for predicting human mobility. This framework integrates geographic and social signals, computed from open data like p…
-
Hybrid AI approach boosts stock prediction accuracy for foundation models
Researchers have developed a hybrid approach to improve the performance of frozen time series foundation models, specifically for high-frequency stock prediction. By combining neural correction architectures like AttnCo…
-
LLM as Forecasting Planner framework integrates LLMs with TSFMs for improved forecasting
Researchers have developed a novel framework called LLM as Forecasting Planner (LAFP) that integrates large language models (LLMs) with time-series foundation models (TSFMs) for improved forecasting. This training-free …
-
LLM as Forecasting Planner framework integrates LLMs with TSFMs for improved forecasting
Researchers have developed a novel framework called LLM as Forecasting Planner (rc) that integrates large language models (LLMs) with time-series foundation models (TSFMs) for improved text-conditioned forecasting. This…
-
Time Series Foundation Models show promise for wearable HRV forecasting
A new research paper explores the effectiveness of Time Series Foundation Models (TSFMs) for forecasting heart rate variability (HRV) from consumer wearable devices. The study evaluated TimesFM, Chronos, and MOIRAI agai…
-
New ApolloPFN model improves time series forecasting with exogenous variables
Researchers have developed ApolloPFN, a novel time-aware Prior Fitted Network designed to improve zero-shot forecasting by incorporating exogenous variables. Unlike existing foundation models that rely solely on histori…
-
New frameworks adapt foundation models for drought forecasting · 2 sources tracked
Researchers have developed novel inference-time frameworks, RGMR and SMR^2/MBB, to adapt pre-trained foundation models for regional climate forecasting, specifically for drought prediction. These methods allow for struc…
-
Simple models outperform LLMs in time series forecasting
A recent analysis highlights the significant challenges in time series forecasting, revealing that simple statistical models and zero-shot foundation models often outperform complex neural networks and even large langua…
-
LLM agents enhance HFMD forecasting with auditable, context-aware predictions
A new research paper introduces a two-agent neuro-symbolic framework designed for more auditable and context-aware forecasting of Hand, Foot, and Mouth Disease (HFMD). This system integrates an LLM-based Event Interpret…
-
TimesFM Foundation Model Ineffective for Multivariate Anomaly Detection
A recent study explored the application of TimesFM, a foundation model initially designed for univariate time series forecasting, to the complex task of multivariate time series anomaly detection (MTSAD). Researchers ev…
-
AI equity forecasting benchmark reveals LoRA-adapted TimesFM lacks directional skill
A new research paper challenges the effectiveness of large language models like TimesFM for equity forecasting, particularly when using LoRA adapters. The study introduces a base-rate-honest benchmark to expose how seem…
-
Student integrates Google's TabFM and TimesFM for local zero-shot ML tasks
A graduate student has developed Zer0Fit, a local server that integrates Google's TabFM and TimesFM foundation models. This tool allows users to perform zero-shot machine learning tasks such as forecasting, classificati…