More details can be found in the slides that I will unload to indico 

•Two published papers: 

•One paper on accelerating temporal graphs, Learning on graphs’22 best paper award 

•Semi-supervised GNN for pileup mitigation, the European Physics Journal C 

•One top-1 rank at 3D object detection benchmark: BEVFusion 

•Submitted two papers: 

•FlatFormer, an efficient point cloud transformer model, submitted to CVPR’22 

•Interpretable Point cloud models, submitted to ICLR’23 

•On-going works: 

•FlatFormer, further improvements 

•Point-cloud OOD benchmarks 

•Graph OOD/ domain adaptation paper to be submitted to ICML’23