Update README.md (#285)

README.md

@@ -77,6 +77,8 @@ TorchSparse-MLsys on cloud GPUs. It also improves the latency of SpConv 2.3.5 by
 
 TorchSparse achieves superior mixed-precision training speed compared with MinkowskiEngine, TorchSparse-MLSys and SpConv 2.3.5. Specifically, it is **1.16x** faster on Tesla A100, **1.27x** faster on RTX 2080 Ti than state-of-the-art SpConv 2.3.5. It also significantly outperforms MinkowskiEngine by **4.6-4.8x** across seven benchmarks on A100 and 2080 Ti. Measured with batch size = 2.
 
+You may find our benchmarks from [this link](https://zenodo.org/records/8311889). To access preprocessed datasets, please contact the authors. We cannot publicly release raw data from SemanticKITTI, nuScenes and Waymo due to license requirements.
+
 
 ## Team