Skip to content
Log in
Sponsored AI Networking Cookbook: Practical recipes for AI-assisted network automation and development AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
#artificial intelligence Preprint

Timestral

Adrien Petralia A. Gavaudan Artjom Joosen Étienne Goffinet Richard Kurle Y. El Ouahidi Yassir Bendou Abdelaziz Bounhar Abhijeet Somani Aditi Kabra Adrian Valente Adrien Sadé Ahmed Djermani Alan Jeffares Albert Q. Jiang Alberto Bietti Aleksandr Timashov Alexandre Cahill A. Laval Alexandre Sablayrolles Alexandros Sanchez Vassopoulos A. Héliou Amos You André Jonasson Andreas Furst Andrew Bai Andrew Ehrenberg Andrew Zhao Andy Lo Angele Lenglemetz Anmol Agarwal Antonia Calvi Arata Suzuki Arjun Majumdar A. Fournier Ashwani Kumar Augustin Lombard Avinash Sooriyarachchi A. Akkus A. Karaduman Baptiste Bout Baptiste Rozière Barna Pásztor Baudouin De Monicault Benjamin J. Holzschuh Benjamin Tibi Benno Stein Bernhard Stadlbauer B. Bhaskar Bin-Bing Hou B. Osinski Boris van Breugel Camille Le Scao Chao-Ran Yu Charlotte Cronjager Chenkai Sun Chris Bamford Christian Wallenwein Christophe Renaudin Clémence Lanfranchi Colin Bonatti Corentin Barreau Corentin Sautier Cristiana-Diana Diaconu Cyprien Courtot Daniel Lopes Daniel Marczak Darius Dabert D. de Las Casas Dominik Nuss Dylan Rubini Dzmitry Soupel E. Demyanenko Elliot Chane-Sane Emilie Fugier E. Gottlob E. Aas Étienne Duchesne Fabian Paischer F. Schlager Faruk Ahmed Federico Baldassarre Félix Rosseeuw Filip Szatkowski Filippo Vicentini Florian Wiesner Gabrielle Berrada Gaetan Ecrepont Gaspard Blanchet Gaspard Donada-Vidal Gaurav Mahajan Gauthier Guinet G. Hayes Georgii Sergeevich Novikov Georgios Christoglou Giada Pistilli Gonzague de Carpentier Graeme Nail G. Breton Guillaume Kunsch Guillaume Lample Guillaume Martin Guillaume Raille Guillaume Richard Guillem Simeon Gunjan Dhanuka Gunshi Gupta Hamza Senhaji Rhazi Han Zhou Hédi Hadiji Himanshu Jaju Hope McGovern Hubert de Parseval Hugo Cisneros Hugo Germain Hugo Thimonier Hugo Venturini Hyeonju Lee Hyunwoo Oh Iliass Lasri Ilyas Oulkadda Jacques Sun Jan Ludziejewski Jason Rute J. de Becdelièvre Jean Quentin Jean-Malo Delignon Jessica Chudnovsky Jian-Chao Li Jie-Wen Zhang Jin-Bin Ou Joachim Studnia Joep Barmentlo J. Brandstetter John Harvill Jonas Amar Jonas Schweizer Jonathan Roberts Joséphine Delas Josselin Somerville Jules Depersin Julien Denize Julien Tauran Julien Verlaguet Kartik Khandelwal Khyathi Raghavi Chandu Kilian Tep Konstantin Mishchenko K. Szczepaniak Kush Jain Larissa Laich Laura Calem Laurence Aitchison L. Callot Laurent Fainsin Léo Cotteleer Léonard Blier Loïc Chadoutaud Loïck Chambon Lorenzo Proietti Louis Faucon L. Martin Louis Serrano Lu Li Luc Boudier Lucas Fernandes Martins Lucas Mebille Lucile Saulnier Ludovic Ho Fuh Luis Montero Lukasz Borchmann M. Buyl Malik Hassan Raza Manon Chossegros Marcin Możejko Margaret Jennings Markus Hennerbichler M. Alexandre Mathieu Poir'ee Mathieu Schmitt Mathilde Guillaumin Mathis Felardos M. André Matthieu Dinot Matthieu Futeral Maurits J. R. Bleeker Mauro Comi M. Mynter Maxim Berman Maxime Darrin Maxime Langelier Maxime Louis Maximilian Augustin Maximilian Müller Mehdi Bouaziz Melina Jingting Laimon Mert Unsal Mia Chiquier M. Pilcer Michal Pietruszka Michał Zając M. Seznec Mikhail Biriuchinskii Minh-Quang Pham Minchul Kang Mircea Lica Morgane Rivière Namit Katariya Natasha Ørregaard Klingenbrunn Nathan Bout Nathan Grinsztajn Nathan Simpson Neeraj Aggarwal Neil Ashton Neil Rohit Mallinar Nick Bührer Nicolas Moreau Nicolò Lucchesi Ola Mysiak Oliver Leicht O. Bousquet Olivier Koch Parag Jain Patricia Wang P. Blies Patrick von Platen Patryk Saffer Paul Jacob Paul Teiletche P. Wambergue Paula Kurylowicz P. K. Reddy P. Kuksa Philippe Formont Philippe Pinel Philomène Chagniot P. Glandon Pierre Stock Pierre-André Savalle Piotr Milos Poojan Shah Prateek Gupta Pravesh Agrawal Pui-Ki Chan Quentin Desreumaux Quentin Selle Quentin Torroba Quentin Wargnier Quercus Hernandez Ram Ramrakhya R. Isenhour Ranjit Parva Raphaël Balouka Raphaël Rialland Raúl P. Peláez Reinhard Sonnleitner Rémi Delacourt Rishi Shah Rob Romijnders Rohan Shah Rohin Arora Romain Sauvestre Roman Soletskyi Ronan Riochet R. Millner R. Menneer S. Vaze Samuel Barry Samuel Belkadi Samuel Humeau Samuele Papa Sanchit Gandhi S. Cranganore Sandeep Subramanian Sarthak Mittal Saskia Adaime Scott Matthews S. Cha Sebastian Kaltenbach Seungjae Jung Shashwat Verma S. Waly Shrimai Prabhumoye Siddhant Waghjale Siddharth Gandhi Simon Lepage Simon Sorg Soham Ghosh Sophie Marbach Srijan Mishra Stanislas Lange Steve Hong Sumukh K. Aithal Szymon Antoniak T. K. Vangani Teddy Turquet Teven Le Scao Théo Cachet Thibaut Lavril Thomas Chabal Thomas Coste Thomas Defard Thomas Foubert Thomas Loux Thomas Robert Thomas Wang Tian-Yu Zhang Tim Lawson Timothée Lacroix Timothy Wallis T. Kronlachner Tom Bewley Tom Edwards Tomas Hodan Triantafyllos Afouras Tuhin Das Tyler Wang Udit Saxena Ulrick Ble Umar Jamil Umberto M. Tomasini Valentin Macé V. Phụng V. Reddy Vibha Masti Victor Jouault Victor Letzelter Victor Paltz Victor Poucheret V. Maladière Vincent Pfister Virgile Richard Vladislav V. Bataev Wassim Bouaziz Wen-Ding Li William Flanagan William Havard William Marshall Witold Jedrzejewski Xinghui Li Xing-Ran Guo Xin-Yu Yang Xuan-Yu Zhang Yann Dréze Yann Viegas Yannic Neuhaus Yassine Turki Yessin Moakher Yi He Yi-Han Wang Yi-Mu Pan Yue-Ying Zhu Yves Martin Des Taillades Zaccharie Ramzi Zhen-Lin Xu Zsófia Csákány
Oct 2026 · 1 citation · 32 references
Computer Science

Abstract

We introduce Timestral, a family of four time series foundation models for probabilistic forecasting, with 5M, 28M, 123M, and 209M parameters. Timestral sets a new state of the art on GIFT-Eval, TIME, and fev-bench, where Timestral-209M and Timestral-123M take the top two places on every metric. We achieve this with three ingredients: Decoupled Horizon Forecasting (DHF), which separates prediction tokens from the causally encoded context, so that longer horizons are trained without masking context and each observed value is both a forecast target and context for later forecasts; a covariate framework that natively supports known-future covariates within a causal architecture; and a two-stage pipeline that pretrains exclusively on a diverse, large-scale synthetic corpus before post-training on a mix of real and synthetic data with extended context. This report describes the model design and its benchmark results. Weights for all four models are available on Hugging Face and inference code on GitHub.

DOI arXiv Semantic Scholar
View source

Similar papers

#artificial intelligence Conference Open access Jun 2018

Gibson Env: Real-World Perception for Embodied Agents

This paper investigates developing real-world perception for active agents, proposes Gibson Environment for this purpose, and showcases a set of perceptual tasks learned therein.

F. Xia, Amir Zamir, Zhi-Yang He et al. · 1,069 citations · ⚡112
#artificial intelligence Open access May 2023

Evaluating the Performance of Large Language Models on GAOKAO Benchmark

GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations...

Xiaotian Zhang, Chun-yan Li, Yi Zong et al. · 216 citations · ⚡17
#artificial intelligence Feb 2024

KTO: Model Alignment as Prospect Theoretic Optimization

This work proposes a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, and suggests that the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.

Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff et al. · 195 citations · ⚡28
#artificial intelligence Open access Jul 2024

Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval

This work investigates the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection and finds that the MTEs are biased, significantly favoring White-associated names in 85% of cases and female-associated names in only 11.1% of cases.

Kyra Wilson, Aylin Caliskan · 131 citations · ⚡8
#artificial intelligence Review Nov 2024

How to Build a Quantum Supercomputer: Scaling from Hundreds to Millions of Qubits

This work shows that orders of magnitude enhancement in performance could be obtained by a combination of hardware improvements and tight quantum-HPC integration and introduces high-performance architectures for quantum-probabilistic computing with custom-designed accelerators to tackle today's industry-scale classical...

Masoud Mohseni, Artur Scherer, K. Johnson et al. · 121 citations · ⚡9

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.