update publications

Author: apointa

content/publication/2023-hopcpt/index.md

@@ -6,7 +6,7 @@ authors: ["**Andreas Auer**, Martin Gauch, Daniel Klotz, Sepp Hochreiter "]
 publication_types: ["2"]
 abstract: "To quantify uncertainty, conformal prediction methods are gaining continuously more interest and have already been successfully applied to various domains. However, they are difficult to apply to time series as the autocorrelative structure of time series violates basic assumptions required by conformal prediction. We propose HopCPT, a novel conformal prediction approach for time series that not only copes with temporal structures but leverages them. We show that our approach is theoretically well justified for time series where temporal dependencies are present. In experiments, we demonstrate that our new approach outperforms state-of-the-art conformal prediction methods on multiple real-world time series datasets from four different domains."
 featured: true
-publication: "NeurIPS 2023"
+publication: "NeurIPS 2023 (Main Conference)"
 links:
   - icon_pack: ai
     icon: arxiv

content/publication/2024-xlstm/index.md

@@ -6,7 +6,7 @@ authors: ["Maximilian Beck, Korbinian Pöppel, Markus Spanring, **Andreas Auer**
 publication_types: ["2"]
 abstract: "In the 1990s, the constant error carousel and gating were introduced as the central ideas of the Long Short-Term Memory (LSTM). Since then, LSTMs have stood the test of time and contributed to numerous deep learning success stories, in particular they constituted the first Large Language Models (LLMs). However, the advent of the Transformer technology with parallelizable self-attention at its core marked the dawn of a new era, outpacing LSTMs at scale. We now raise a simple question: How far do we get in language modeling when scaling LSTMs to billions of parameters, leveraging the latest techniques from modern LLMs, but mitigating known limitations of LSTMs? Firstly, we introduce exponential gating with appropriate normalization and stabilization techniques. Secondly, we modify the LSTM memory structure, obtaining: (i) sLSTM with a scalar memory, a scalar update, and new memory mixing, (ii) mLSTM that is fully parallelizable with a matrix memory and a covariance update rule. Integrating these LSTM extensions into residual block backbones yields xLSTM blocks that are then residually stacked into xLSTM architectures. Exponential gating and modified memory structures boost xLSTM capabilities to perform favorably when compared to state-of-the-art Transformers and State Space Models, both in performance and scaling."
 featured: true
-publication: "NeurIPS 2024 (Spotlight)"
+publication: "[Spotlight] NeurIPS 2024 (Main Conference)"
 links:
   - icon_pack: ai
     icon: arxiv

content/publication/2025-tirex-workshop/index.md

@@ -0,0 +1,23 @@
+---
+title: "TiRex: Zero-Shot Forecasting Across Long and Short Horizons"
+date: 2025-06-01
+publishDate:  2025-06-01
+authors: ["**Andreas Auer**, Patrick Podest, Daniel Klotz, Sebastian Böck, Günter Klambauer, Sepp Hochreiter"]
+publication_types: ["2"]
+abstract: "In-context learning, the ability of large language models to perform tasks using only examples provided in the prompt, has recently been adapted for time series forecasting. This paradigm enables zero-shot prediction, where past values serve as context for forecasting future values, making powerful forecasting tools accessible to non-experts and increasing the performance when training data are scarce. Most existing zero-shot forecasting approaches rely on transformer architectures, which, despite their success in language, often fall short of expectations in time series forecasting, where recurrent models like LSTMs frequently have the edge. Conversely, while LSTMs are well-suited for time series modeling due to their state-tracking capabilities, they lack strong in-context learning abilities. We introduce TiRex that closes this gap by leveraging xLSTM, an enhanced LSTM with competitive in-context learning skills. Unlike transformers, state-space models, or parallelizable RNNs such as RWKV, TiRex retains state-tracking, a critical property for long-horizon forecasting. To further facilitate its state-tracking ability, we propose a training-time masking strategy called CPM. TiRex sets a new state of the art in zero-shot time series forecasting on the HuggingFace benchmarks GiftEval and Chronos-ZS, outperforming significantly larger models including TabPFN-TS (Prior Labs), Chronos Bolt (Amazon), TimesFM (Google), and Moirai (Salesforce) across both short- and long-term forecasts."
+featured: true
+publication: "[Spotlight] Workshop on Foundation Models for Structured Data @ ICML 2025."
+links:
+  - icon_pack: ai
+    icon: arxiv
+    name: Paper
+    url: 'https://openreview.net/pdf?id=cWrbpOZGRa'
+  - icon_pack: fab
+    icon: github
+    name: Code
+    url: 'https://github.com/NX-AI/tirex'
+  - icon_pack: fab
+    icon: square-binary
+    name: Model (HuggingFace)
+    url: 'https://huggingface.co/NX-AI/TiRex'
+---

content/publication/2025-tirex/index.md

@@ -1,12 +1,12 @@
 ---
 title: "TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning"
-date: 2025-05-30
-publishDate:  2025-05-30
+date: 2025-08-01
+publishDate:  2025-08-01
 authors: ["**Andreas Auer**, Patrick Podest, Daniel Klotz, Sebastian Böck, Günter Klambauer, Sepp Hochreiter"]
 publication_types: ["2"]
 abstract: "In-context learning, the ability of large language models to perform tasks using only examples provided in the prompt, has recently been adapted for time series forecasting. This paradigm enables zero-shot prediction, where past values serve as context for forecasting future values, making powerful forecasting tools accessible to non-experts and increasing the performance when training data are scarce. Most existing zero-shot forecasting approaches rely on transformer architectures, which, despite their success in language, often fall short of expectations in time series forecasting, where recurrent models like LSTMs frequently have the edge. Conversely, while LSTMs are well-suited for time series modeling due to their state-tracking capabilities, they lack strong in-context learning abilities. We introduce TiRex that closes this gap by leveraging xLSTM, an enhanced LSTM with competitive in-context learning skills. Unlike transformers, state-space models, or parallelizable RNNs such as RWKV, TiRex retains state-tracking, a critical property for long-horizon forecasting. To further facilitate its state-tracking ability, we propose a training-time masking strategy called CPM. TiRex sets a new state of the art in zero-shot time series forecasting on the HuggingFace benchmarks GiftEval and Chronos-ZS, outperforming significantly larger models including TabPFN-TS (Prior Labs), Chronos Bolt (Amazon), TimesFM (Google), and Moirai (Salesforce) across both short- and long-term forecasts."
 featured: true
-publication: "Under Review"
+publication: "NeurIPS 2025 (Main Conference)"
 links:
   - icon_pack: ai
     icon: arxiv

content/publication/2025-zs-classification/index.md

@@ -0,0 +1,15 @@
+---
+title: "Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification"
+date: 2025-09-01
+publishDate:  2025-09-01
+authors: ["**Andreas Auer**, Daniel Klotz, Sebastian Böck, Sepp Hochreiter"]
+publication_types: ["2"]
+abstract: "Recent research on time series foundation models has primarily focused on forecasting, leaving it unclear how generalizable their learned representations are. In this study, we examine whether frozen pre-trained forecasting models can provide effective representations for classification. To this end, we compare different representation extraction strategies and introduce two model-agnostic embedding augmentations. Our experiments show that the best forecasting models achieve classification accuracy that matches or even surpasses that of state-of-the-art models pre-trained specifically for classification. Moreover, we observe a positive correlation between forecasting and classification performance. These findings challenge the assumption that task-specific pre-training is necessary, and suggest that learning to forecast may provide a powerful route toward constructing general-purpose time series foundation models."
+featured: true
+publication: "Recent Advances in Time Series Foundation Models (BERT2S) @ NeurIPS 2025."
+links:
+  - icon_pack: ai
+    icon: arxiv
+    name: Paper
+    url: 'https://openreview.net/pdf?id=vhngjDHyB0'
+---