Update README.md

README.md

@@ -6,38 +6,156 @@ tags:
 - foundation model
 - in-context learning
 - multivariate time series
+- univariate time series
+- training-free
 ---
 
 # ChorusTIC
 
-ChorusTIC is a classification-native foundation model for training-free univariate and multivariate time series classification. It uses labeled context examples to predict query labels without fitting a target-specific classifier or updating model parameters.
+**ChorusTIC** is a classification-native foundation model for **training-free univariate and multivariate time series classification**. Given labeled context examples, ChorusTIC directly predicts query labels through in-context learning, without fitting a target-specific classifier or updating model parameters.
 
-[Paper](https://arxiv.org/abs/2608.24033) · [Code](https://github.com/fangjuntao/ChorusTIC) · [Official benchmark results](https://tsc-fm.dmirlab.com/methods/chorustic)
+> 🏆 **#1 on the TSC-FM Standard Overall Leaderboard**, achieving an **Overall Average Accuracy of 78.56 across all 198 time series classification datasets**.
 
-## Benchmark and evaluation
+[📄 Paper](https://arxiv.org/abs/2608.24033) ·
+[💻 Code](https://github.com/DMIRLAB-Group/ChorusTIC) ·
+[🤗 Checkpoint](https://huggingface.co/DMIRLAB/ChorusTIC) ·
+[🏆 TSC-FM Leaderboard](https://tsc-fm.dmirlab.com/leaderboard) ·
+[📊 Benchmark Results](https://tsc-fm.dmirlab.com/methods/chorustic)
 
-ChorusTIC is evaluated in the [TSC-FM time series classification foundation model benchmark](https://tsc-fm.dmirlab.com/). Use the [time series classification leaderboard](https://tsc-fm.dmirlab.com/leaderboard) to compare matching Standard and low-shot settings, and read the [evaluation protocol](https://tsc-fm.dmirlab.com/evaluation) before interpreting aggregate accuracy, rank and coverage.
+---
+
+## Model Overview
+
+ChorusTIC is designed for support-conditioned time series classification, where predictions are made directly from a labeled context set and a set of query samples.
+
+The model combines two complementary levels of modeling:
+
+- **Signal-level Chorus**, which uses **Random Subchannel Slot Concatenation (RSSC)** together with a shared dual-axis time series encoder to capture temporal patterns and cross-channel interactions under heterogeneous channel configurations.
+- **Task-level Chorus**, which performs support-conditioned classification through **Column Distribution Modeling (CDM)**, **Row-wise Feature Interaction**, and **In-Context Learning (ICL)**.
+
+This design allows a single pretrained model to perform both **univariate and multivariate time series classification** without task-specific parameter optimization at inference time.
+
+### Key Characteristics
+
+- **Training-free inference:** no fine-tuning or target-specific classifier fitting.
+- **In-context classification:** predictions are conditioned directly on labeled support examples.
+- **Unified univariate and multivariate modeling:** the same pretrained model handles datasets with different channel configurations.
+- **Support-conditioned prediction:** the model adapts its predictions to the target task through the provided context set rather than parameter updates.
+- **Foundation-model evaluation:** evaluated across a large and heterogeneous collection of time series classification datasets.
+
+---
+
+## Benchmark Results
+
+ChorusTIC is evaluated on the **TSC-FM Time Series Classification Benchmark**, a unified benchmark covering **198 unique datasets** across both univariate and multivariate time series classification.
+
+On the **Standard Overall** evaluation, ChorusTIC achieves:
+
+| Metric | Result |
+| --- | ---: |
+| TSC-FM Standard Overall Rank | **#1** |
+| Overall Average Accuracy | **78.56** |
+| Dataset Coverage | **198 / 198** |
+| Inference Paradigm | **Training-free In-Context Learning** |
+
+The TSC-FM Overall score is computed with equal weighting across the evaluated datasets.
+
+For complete evaluation details, configurations, and dataset-level results, see:
+
+- [ChorusTIC benchmark results](https://tsc-fm.dmirlab.com/methods/chorustic)
+- [TSC-FM Leaderboard](https://tsc-fm.dmirlab.com/leaderboard)
+- [TSC-FM Evaluation Protocol](https://tsc-fm.dmirlab.com/evaluation)
+- [TSC-FM Benchmark Homepage](https://tsc-fm.dmirlab.com/)
+
+> Leaderboard rankings may evolve as new models and evaluation results are added. Please refer to the official TSC-FM leaderboard for the latest ranking.
+
+---
+
+## Released Checkpoint
+
+This repository provides the pretrained ChorusTIC checkpoint and its corresponding model configuration:
+
+```text
+ChorusTIC.ckpt
+model_hparams_latest.json
+```
+
+The checkpoint can be downloaded with the Hugging Face CLI:
+
+```bash
+pip install -U huggingface_hub
+
+hf download DMIRLAB/ChorusTIC \
+  --local-dir Checkpoints_ChorusTIC
+```
+
+The resulting directory should have the following structure:
+
+```text
+Checkpoints_ChorusTIC/
+├── ChorusTIC.ckpt
+└── model_hparams_latest.json
+```
+
+Model loading, preprocessing, inference, and UCR/UEA evaluation code are provided in the
+[official ChorusTIC GitHub repository](https://github.com/DMIRLAB-Group/ChorusTIC).
+
+---
+
+## Intended Use
+
+ChorusTIC is intended primarily for research on time series foundation models and training-free classification.
+
+Typical use cases include:
+
+- Training-free time series classification.
+- In-context classification with labeled support examples.
+- Univariate time series classification.
+- Multivariate time series classification.
+- Evaluation of foundation models on heterogeneous time series datasets.
+- Reproduction and extension of the experiments presented in the accompanying paper.
+
+---
+
+## Inputs and Inference Setting
 
-## Model description
+ChorusTIC operates under an **in-context classification** setting.
 
-ChorusTIC combines Random Subchannel Slot Concatenation with a shared dual-axis encoder to model temporal and cross-channel interactions across heterogeneous channel configurations. Context-derived feature calibration and leakage-protected in-context learning are then used to infer query labels.
+For a target classification task, the model receives:
 
-The released repository contains `ChorusTIC.ckpt`. Model loading, preprocessing and UCR/UEA evaluation code are available in the [official GitHub repository](https://github.com/fangjuntao/ChorusTIC).
+1. A set of **labeled context examples**, which defines the target task and its class structure.
+2. One or more **unlabeled query examples** to be classified.
 
-## Intended use
+The model predicts the labels of the query examples directly from the provided context, without updating the pretrained model parameters or fitting an additional task-specific classifier.
 
-- Research on training-free time series classification.
-- In-context classification of univariate and multivariate sequences.
-- Reproduction and extension of the accompanying paper’s experiments.
+The quality and composition of the context set can therefore affect prediction performance.
+
+---
 
 ## Limitations
 
-- Predictions require labeled context examples with adequate class coverage.
-- Performance outside the evaluated data domains and channel configurations is not guaranteed.
-- This checkpoint is a research artifact and should be validated independently before high-stakes use.
+- ChorusTIC requires labeled context examples with sufficient class coverage to define the target classification task.
+- Performance may depend on the number, quality, and representativeness of the provided context examples.
+- Performance outside the time series domains, sequence characteristics, and channel configurations represented by the evaluated benchmarks has not been established.
+- The released checkpoint is intended as a research artifact and has not been validated for safety-critical or other high-stakes applications.
+- Users should independently evaluate the model on their target domain before deployment.
+
+---
+
+## Resources
+
+- **Paper:** [ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning](https://arxiv.org/abs/2608.24033)
+- **Official Code:** [DMIRLAB-Group/ChorusTIC](https://github.com/DMIRLAB-Group/ChorusTIC)
+- **Model Checkpoint:** [DMIRLAB/ChorusTIC](https://huggingface.co/DMIRLAB/ChorusTIC)
+- **TSC-FM Benchmark:** [tsc-fm.dmirlab.com](https://tsc-fm.dmirlab.com/)
+- **Benchmark Results:** [ChorusTIC on TSC-FM](https://tsc-fm.dmirlab.com/methods/chorustic)
+
+---
 
 ## Citation
 
+If you use ChorusTIC in your research, please cite:
+
 ```bibtex
 @article{fang2026chorustic,
   title   = {ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning},
@@ -46,3 +164,9 @@ The released repository contains `ChorusTIC.ckpt`. Model loading, preprocessing
   year    = {2026}
 }
 ```
+
+---
+
+## License
+
+ChorusTIC is released under the **Apache License 2.0**.