Add arxiv link and citation bibtex

README.md

@@ -13,7 +13,7 @@ license: apache-2.0
 
 This repository provides the pretrained TiRex-2 model and inference code for zero-shot
  multivariate forecasting with past and future-known covariates, as introduced in [TiRex-2:
- Generalizing TiRex to Multivariate Data and Streaming](ADD ARXIV LINK).
+ Generalizing TiRex to Multivariate Data and Streaming](https://arxiv.org/abs/2607.01204).
 
 TiRex-2 is a pretrained time series foundation model that forecasts one or many target
 variates directly from their history, optionally conditioned on past and future-known
@@ -64,12 +64,27 @@ For a more **interactive demo of TiRex-2**, we also provide a [quick-start](http
 
 ## Cite
 If you use TiRex-2 in your research, please cite our work:
-TBD
+```bibtex
+@misc{podest2026tirex2generalizingtirexmultivariate,
+      title={TiRex-2: Generalizing TiRex to Multivariate Data and Streaming}, 
+      author={Patrick Podest and Marco Pichler and Elias Bürger and Levente Zólyomi and Bernhard Voggenberger and Wilhelm Berghammer and Daniel Klotz and Sebastian Böck and Günter Klambauer and Sepp Hochreiter},
+      year={2026},
+      eprint={2607.01204},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/2607.01204}, 
+}
+```
 
 ## Other versions:
-Alongside this pretrained checkpoint we also provide three other versions:
-- [TiRex-2-g](https://huggingface.co/NX-AI/TiRex-2-gifteval-zs): we took care to exclude any overlap with the GiftEval
-datasets ([pretrain](https://huggingface.co/datasets/Salesforce/GiftEvalPretrain) and [evaluation](https://huggingface.co/datasets/Salesforce/GiftEval)). 
-- [TiRex-2-gp](https://huggingface.co/NX-AI/TiRex-2-gifteval-pretrain): here we included the [GiftEval-Pretrain collection](https://huggingface.co/datasets/Salesforce/GiftEvalPretrain) in our pretraining corpus. 
-- [TiRex-2-f](https://huggingface.co/NX-AI/TiRex-2-fevbench): for the fev-benchmark we took the same measures as for
-GiftEval and removed all [fev-bench eval datasets](https://huggingface.co/datasets/autogluon/fev_datasets) from our pretraining corpus to produce this checkpoint.
+Alongside this pretrained checkpoint, we release decontaminated versions to enable fair 
+zero-shot evaluation on specific benchmarks by excluding their data from pretraining:
+- [TiRex-2-g](https://huggingface.co/NX-AI/TiRex-2-gifteval-zs): excludes any overlap with 
+  the GiftEval datasets ([pretrain](https://huggingface.co/datasets/Salesforce/GiftEvalPretrain) 
+  and [evaluation](https://huggingface.co/datasets/Salesforce/GiftEval)) from pretraining.
+- [TiRex-2-gp](https://huggingface.co/NX-AI/TiRex-2-gifteval-pretrain): includes the 
+  [GiftEval-Pretrain collection](https://huggingface.co/datasets/Salesforce/GiftEvalPretrain) 
+  in the pretraining corpus (for comparison against TiRex-2-g).
+- [TiRex-2-f](https://huggingface.co/NX-AI/TiRex-2-fevbench): excludes all 
+  [fev-bench eval datasets](https://huggingface.co/datasets/autogluon/fev_datasets) 
+  from pretraining, using the same approach as for GiftEval.