| | --- |
| | license: cc-by-4.0 |
| | library_name: transformers |
| | pipeline_tag: table-question-answering |
| | --- |
| | |
| | The Table-R1 model, as presented in the paper [Table-R1: Inference-Time Scaling for Table Reasoning](https://huggingface.co/papers/2505.23621), explores inference-time scaling on table reasoning tasks. It uses distillation from frontier model reasoning traces and reinforcement learning with verifiable rewards (RLVR). The model matches or exceeds the performance of GPT-4.1 and DeepSeek-R1, while using only a 7B-parameter LLM. |
| |
|
| | - **Paper:** [Table-R1: Inference-Time Scaling for Table Reasoning](https://huggingface.co/papers/2505.23621) |
| | - **Code:** [Table-R1 Github Repository](https://github.com/Table-R1/Table-R1) |
| | - **Project Page:** [Table-R1 Hugging Face Organization](https://huggingface.co/Table-R1) |
