Three papers from CharMLab researchers accepted at NeurIPS 2024

The 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024), a premier annual gathering that draws together researchers and practitioners in machine learning, computational neuroscience, and related fields, will take place from December 10-15, 2024 at the Vancouver Convention Centre in Vancouver, Canada. Shedding light on new optimization methods, more efficient vision algorithms and new architectures for time series analysis, CharMLab researchers will present exciting new findings of our lab with three papers presented during the poster presentations.

The following papers from the groups of Dr. Kümmerle, Dr. Zhang and Dr. Yang will be presented:

1. Sample-Efficient Geometry Reconstruction from Euclidean Distances using Non-Convex Optimization
   • Ipsita Ghosh, Abiy Tasissa, Christian Kümmerle
   • Paper
   • Code
2. Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification
   • Yihe Wang, Nan Huang, Taida Li, Yujun Yan, Xiang Zhang
   • Paper
   • Code
3. LP-3DGS: Learning to Prune 3D Gaussian Splatting
   • Zhaoliang Zhang, Tianchen Song, Yongjae Lee, Li Yang, Cheng Peng, Rama Chellappa, Deliang Fan
   • Paper
   • Code

Congratulations to Ipsita, Yihe, Nan and Taida!