Link model to paper and improve model card (#1)

- Link model to paper and improve model card (543f6c5ecf244fce57e8f4fbc4b7377ecc654e8c)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

README.md

@@ -1,32 +1,43 @@
 ---
-license: apache-2.0
-datasets:
-- ChilleD/MultiArith
 base_model:
 - optimum/mistral-1.1b-testing
+datasets:
+- ChilleD/MultiArith
+license: apache-2.0
 pipeline_tag: text-generation
+arxiv: 2510.24940
 tags:
 - model_hub_mixin
 - pytorch_model_hub_mixin
+- chain-of-thought
+- implicit-reasoning
 ---
 
 # SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens
+
 ## 🚀 Overview
-SemCoT is a framework that improves the efficiency of Chain-of-Thought (CoT) reasoning by encoding reasoning steps inside hidden representations instead of generating long textual explanations. This implicit reasoning greatly speeds up inference while keeping performance high. Specifically, we take optimum/mistral-1.1b-testing as the base model and fine tune using the SemCoT framework on ChilleD/MultiArith dataset. See [our paper](https://arxiv.org/abs/2510.24940) and [our code](https://github.com/YinhanHe123/SemCoT/). Please reference the code for how to load and use the model.
+**SemCoT** is a framework designed to accelerate Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs) by replacing verbose explicit reasoning with compact, semantically-aligned implicit tokens. Instead of generating long textual explanations, SemCoT encodes reasoning steps within hidden representations (implicit reasoning), which significantly speeds up inference while maintaining high performance.
 
-## 🎯 Key Features
-🗣️ Semantic Alignment: Uses a contrastively trained sentence transformer to ensure that implicit reasoning remains semantically consistent with human-readable CoT explanations.
+This specific checkpoint is a fine-tuned version of `optimum/mistral-1.1b-testing` using the SemCoT framework on the `ChilleD/MultiArith` dataset.
 
-⚡ Efficiency Optimization: Introduces a lightweight implicit reasoning generator, fine-tuned via knowledge distillation, to reduce token generation time and enhance inference speed.
+- **Paper:** [SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens](https://huggingface.co/papers/2510.24940)
+- **Authors:** Yinhan He, Wendy Zheng ([@wendyz123](https://huggingface.co/wendyz123)), Yaochen Zhu ([@yaochenzhu](https://huggingface.co/yaochenzhu)), Zaiyi Zheng, Lin Su, Sriram Vasudevan ([@sriramvasudevan](https://huggingface.co/sriramvasudevan)), Qi Guo, Liangjie Hong, Jundong Li.
+- **Code:** [Official GitHub Repository](https://github.com/YinhanHe123/SemCoT)
+
+## 🎯 Key Features
+- 🗣️ **Semantic Alignment**: Uses a contrastively trained sentence transformer to ensure that implicit reasoning remains semantically consistent with human-readable CoT explanations.
+- ⚡ **Efficiency Optimization**: Introduces a lightweight implicit reasoning generator, fine-tuned via knowledge distillation, to reduce token generation time and enhance inference speed.
+- 🧩 **Joint Optimization**: SemCoT is the first approach that enhances CoT efficiency by jointly optimizing token-level generation speed and preserving semantic alignment with ground-truth reasoning.
 
-🧩 Joint Optimization: SemCoT simultaneously optimizes for reasoning speed and semantic alignment.
+## 🛠️ Usage
+Please refer to the [official GitHub repository](https://github.com/YinhanHe123/SemCoT/) for instructions on environment setup, data generation, and how to run the evaluation scripts for this model.
 
 ## Citation
-```
-@article{he2025semcot,
+```bibtex
+@inproceedings{he2025semcot,
   title={SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens},
   author={He, Yinhan and Zheng, Wendy and Zhu, Yaochen and Zheng, Zaiyi and Su, Lin and Vasudevan, Sriram and Guo, Qi and Hong, Liangjie and Li, Jundong},
-  journal={arXiv preprint arXiv:2510.24940},
+  booktitle={39th Conference on Neural Information Processing Systems (NeurIPS 2025)},
   year={2025}
 }
 ```