Kronos: A Foundation Model for the Language of Financial Markets

Kronos pre-trains a financial time-series foundation model on 12 billion K-line records via specialized tokenization, achieving major gains in zero-shot forecasting, volatility prediction, and synthetic data generation.

Yu Shi, Zongliang Fu, Shuo Chen, Bohan Zhao and 3 more

Published Aug 2, 2025 · ▲ 58 on Hugging Face · Code ★ 40,075

Tokenization and Architecture Jointly Allocate Component Roles in Time Series Transformers

Mingyu Kim, Doguk Kim

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

EEG-X: Toward Device-Agnostic and Noise-Robust Foundation Models for EEG

Navid Mohammadi Foumani, Soheila Ghane, Nam Nguyen, Mahsa Salehi and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction

Minsu Kim, Ye-Sung Kim, Hyeseong Jeon, Wooseok Hyung and 2 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Closing the Loop: Co-Evolving EM for Irregular Time Series Generation in Lifted Representations

Idan Arbiv, Gal Fadlon, Omri Azencot

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Observations Drift, Structures Remain: Structural Pretraining with Time Alignment for Electromagnetic Signals

Wenjin Gui, Junyu Shen, Haibo Xu, Yuchuang Sun and 6 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation

Onur Selim Kilic, Afra Nawar, Cem O Yaldiz, Michael J Cho and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Bridging Diffusion and Autoregression for Flexible Time Series Synthesis

Xin Wang, Xuan Zhang, Haipeng Zhang, Chunyu Wei and 1 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Temporal-Scale Sensitivity in Time-Series Tokenization and Scale-Robust Token Estimation by Gated Sum

Berken Utku Demirel, Christian Holz

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

Vibe-Spike: An Energy-Preserving EEG Foundation Model Through the Landscape of Neural Coherence

Jun Ye, yuting li, Tingting Dan, Guorong Wu

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

AmbientFM: A Foundation Model for Ambient Sensing

Guozhen Zhu, Yuqian Hu, Sakila S Jayaweera, Wei-Hsiang Wang and 5 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Process-conditioned Pretraining with Topographic Spatial Retrieval for Large EEG Models

Yi Ding, Muyun Jiang, Weibang Jiang, Shuailei Zhang and 5 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

FracTS: Hierarchical and Autoregressive Time Series Generation

Jiayu Li, Umair Afzal, Zilong Zhao, Milad Abdollahzadeh and 2 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

TSFM Meets LLM: Context as Covariate

Hemanth Ram Govindarajan Kirubaharan, Sai Shankar Narasimhan, Shubhankar Agarwal, Sandeep Chinchali

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

PhyTS: A Benchmark for Scientific Time Series

Benedict Armstrong, Jeroen Audenaert, Hannah P Binney, Alice Cheng and 22 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

What Does an Observability Forecasting Foundation Model Know?

Dhyey Mavani, Tairan Ji, Rian Atri

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Kairos: Toward Adaptive and Parameter-Efficient Time Series Foundation Models

Kun Feng, Shaocheng Lan, Yuchen Fang, Wenchao He and 5 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

NeuroRVQ: Multi-Scale Biosignal Tokenization for Generative Foundation Models

NeuroRVQ uses multi-scale temporal convolutions and hierarchical RVQ codebooks with a phase-aware loss to tokenize biosignals at high fidelity across modalities. NeuroRVQ-FM foundation models using these tokenizers achieve competitive or superior downstream performance, showing that high-fidelity to

Konstantinos Barmpas, Na Lee, Dimitrios Chalatsis, William Raftery and 6 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

OATS: Online Data Augmentation for Time Series Foundation Models

OATS dynamically generates training-stage-specific synthetic data guided by valuable samples via diffusion, consistently outperforming static augmentation for time series foundation models.

Junwei Deng, Chang Xu, Jiaqi Ma, Ming Jin and 4 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Calibrating Scientific Foundation Models with Inference-Time Stochastic Attention

Stochastic Attention randomizes attention weights at inference to generate calibrated predictive ensembles without retraining, achieving best native calibration with minimal tuning cost.

Akash Yadav, Taiwo Adebiyi, Ruda Zhang

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

TS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning

TS-ICL unifies time series forecasting and imputation via timestamp-aligned in-context regression, achieving state-of-the-art imputation and strong partially-observed forecasting results.

Etienne Le Naour, Tahar Nabil, Adrien Petralia

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting

FLAME is a lightweight time series foundation model using Legendre Memory and normalizing flows for efficient probabilistic forecasting with strong benchmark performance.

Xingjian Wu, Hanyin Cheng, Xiangfei Qiu, Zhengyu Li and 3 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation

PrismFlow uses Koopman-inspired dynamical experts with a confidence-aware winner-take-all objective to learn residual flow corrections that recover fine-grained temporal dynamics and mitigate spectral contraction in flow matching.

ZHANG JUNRU, Lang Feng, Jinbo Wang, Xu Guo and 5 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems

DynaBase, a two-parameter model blending latent states with nearest in-context neighbors, achieves competitive zero-shot dynamical reconstruction with orders-of-magnitude fewer parameters.

Christoph Jürgen Hemmer, Florian Plaswig, Daniel Durstewitz

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization

TimeTok introduces hierarchical tokenization for multiscale time-series generation with explicit granularity control from coarse inputs, achieving state-of-the-art results and cross-dataset transfer.

Seokhyun Lee, Jaeho Kim, Changjun Oh, Mihaela van der Schaar and 1 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons

A parameter-efficient plugin extends frozen 10-second ECG foundation models to long, variable-length recordings via compatible long-sequence processing and semantically informed temporal modeling, outperforming sliding-window and pooling baselines.

Wei Tang, Jinpei Han, Kangning Cui, Mattia Carletti and 9 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Progressive Memory Transformer: Memory-Aware Attention for Time-Series

Progressive Memory Transformer adds window-aligned memory to transformers, enforcing local, mid-range, and global time-series objectives for strong low-label classification and forecasting.

Tord S Stangeland, Andreas Köhler, Steffen Maeland, Adín Ramírez Rivera

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

A Locally Tokenized Generative Model for Robust Time-Series Watermarking

L-VQVAE locally tokenizes time series so each token depends on a bounded window, and LVQMark stabilizes watermark detection against post-editing attacks without sacrificing quality.

Dongbin Kim, Geonwoo Shin, Yujin Choi, Soyeon Park and 1 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Handwriting decoding as a challenging motor task for EEG Foundation Models

Handwriting decoding evaluates EEG foundation models, revealing confounded datasets and inferior performance versus smaller specialist models despite scaling.

Srinivas Ravishankar, Ishayu Ghosh, Nora Zajzon, Teng (Simon) Fei and 1 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Inertia-1: An Open Exploration of Wearable Motion Foundation Models

Inertia-1 explores wearable motion foundation models via 18.2M hours of accelerometer data, yielding state-of-the-art recipes and open design principles for diverse sensing tasks.

Zongzhe Xu, Aakarsh Anand, Sarah Jiang, Chuntung Zhuang and 3 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 1 on Hugging Face · Code ★ 35

E4GEN: Event-level Explainable Extreme-Enhanced Time-series Generation

E4GEN is an explainable diffusion framework that learns adaptive extreme-control signals for time-series generation, outperforming state-of-the-art models in overall fidelity, extreme-event fidelity, and downstream utility.

Lin Jiang, Dahai Yu, Ximiao Li, Guang Wang

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Universal Time Series Generation with Neural Controlled Differential Equations

Structured Linear Controlled Differential Equations are universal time-series generators that approximate induced path laws on compact latent sets, and Generative SLiCEs improve probabilistic forecasting and downstream task performance on irregular grids.

Torben Berndt, Elyes Farjallah, Leif Seute, RAEID SAQUR and 2 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

AME-TS: Anchored Mixture-of-Experts for Time Series Forecasting

AME-TS guides sparse mixture-of-experts routing via temporal structure descriptors to improve forecasting accuracy and specialization stability with fewer activated parameters.

Rui Wang, Renhao Xue, Ray Razi, Huan Song and 1 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Continuity Laws for Sequential Models

State-space sequential models vary in temporal continuity, with continuous behavior aligning to task structure and enabling efficient subsampling.

Annan Yu, Dongwei Lyu, N. Benjamin Erichson

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts

Environment-induced diffusion shifts identify latent SDE coordinates and drift-Jacobian causal graphs up to permutation and scaling without sparsity assumptions.

Yuanyuan Wang, Wenjie Wang, Haoxuan Li, Mingming Gong and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios

RADAR improves stochastic discount factor portfolio optimization via retrieval-augmented diffusion that learns state-dependent market representations, achieving state-of-the-art risk-adjusted performance.

Kelvin J Koa, XinYang Li, Ke-Wei Huang

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling

Falcon-X maps heterogeneous time series variates into a unified latent prototype space using diff-attention and latent entity attention to enable cross-variate modeling and zero-shot structural transfer with strong forecasting results.

Yiding Liu, Yifan Hu, Hongjie Xia, Peiyuan Liu and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face

Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning

DYSCO uses multi-view contrastive learning to recover latent dynamics and governing equations from noisy high-dimensional data, with theoretical identification guarantees and empirical validation across diverse regimes.

Paolo Muratore, Mackenzie Mathis

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Revisiting the Generic Transformer: Deconstructing a Strong Baseline for Time Series Foundation Models

A generic patch Transformer achieves state-of-the-art zero-shot time series forecasting via simple training, with scaling and data ablations isolating key performance drivers.

Yunshi Wen, Wesley M Gifford, Chandra Reddy, Lam Nguyen and 2 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026