no code implementations • 1 Mar 2024 • Jiaqi Han, Jiacheng Cen, Liming Wu, Zongzhao Li, Xiangzhe Kong, Rui Jiao, Ziyang Yu, Tingyang Xu, Fandi Wu, Zihe Wang, Hongteng Xu, Zhewei Wei, Yang Liu, Yu Rong, Wenbing Huang
Geometric graph is a special kind of graph with geometric features, which is vital to model many scientific problems.
1 code implementation • 23 Feb 2024 • Zui Chen, Yezeng Chen, Jiaqi Han, Zhijie Huang, Ji Qi, Yi Zhou
Large language models (LLMs) are displaying emergent abilities for math reasoning tasks, and there is a growing attention on enhancing the ability of open-source LLMs through supervised fine-tuning (SFT). In this paper, we aim to explore a general data strategy for supervised data to help optimize and expand math reasoning ability. Firstly, we determine the ability boundary of reasoning paths augmentation by identifying these paths' minimal optimal set. Secondly, we validate that different abilities of the model can be cumulatively enhanced by Mix of Minimal Optimal Sets of corresponding types of data, while our models MMOS achieve SOTA performance on series base models under much lower construction costs. Besides, we point out GSM-HARD is not really hard and today's LLMs no longer lack numerical robustness. Also, we provide an Auto Problem Generator for robustness testing and educational applications. Our code and data are publicly available at https://github. com/cyzhh/MMOS.
Ranked #2 on Math Word Problem Solving on ASDiv-A (using extra training data)
no code implementations • 19 Jan 2024 • Minkai Xu, Jiaqi Han, Aaron Lou, Jean Kossaifi, Arvind Ramanathan, Kamyar Azizzadenesheli, Jure Leskovec, Stefano Ermon, Anima Anandkumar
Modeling the complex three-dimensional (3D) dynamics of relational systems is an important problem in the natural sciences, with applications ranging from molecular simulations to particle mechanics.
1 code implementation • NeurIPS 2023 • Rui Jiao, Wenbing Huang, Peijia Lin, Jiaqi Han, Pin Chen, Yutong Lu, Yang Liu
To be specific, DiffCSP jointly generates the lattice and atom coordinates for each crystal by employing a periodic-E(3)-equivariant denoising model, to better model the crystal geometry.
no code implementations • 21 Jun 2023 • Jiaqi Han, Wenbing Huang, Yu Rong, Tingyang Xu, Fuchun Sun, Junzhou Huang
Regarding the layer-dependent sampler, we interestingly find that increasingly sampling edges from the bottom layer yields superior performance than the decreasing counterpart as well as DropEdge.
1 code implementation • 30 May 2023 • Runfa Chen, Jiaqi Han, Fuchun Sun, Wenbing Huang
Learning a shared policy that guides the locomotion of different agents is of core interest in Reinforcement Learning (RL), which leads to the study of morphology-agnostic RL.
no code implementations • 24 May 2023 • Zefan Cai, Xin Zheng, Tianyu Liu, Xu Wang, Haoran Meng, Jiaqi Han, Gang Yuan, Binghuai Lin, Baobao Chang, Yunbo Cao
In the constant updates of the product dialogue systems, we need to retrain the natural language understanding (NLU) model as new data from the real users would be merged into the existent data accumulated in the last updates.
no code implementations • 13 Oct 2022 • Jiaqi Han, Wenbing Huang, Hengbo Ma, Jiachen Li, Joshua B. Tenenbaum, Chuang Gan
Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics.
2 code implementations • 18 Jul 2022 • Rui Jiao, Jiaqi Han, Wenbing Huang, Yu Rong, Yang Liu
Pretraining molecular representation models without labels is fundamental to various applications.
1 code implementation • 15 Mar 2022 • Runfa Chen, Yu Rong, Shangmin Guo, Jiaqi Han, Fuchun Sun, Tingyang Xu, Wenbing Huang
After the great success of Vision Transformer variants (ViTs) in computer vision, it has also demonstrated great potential in domain adaptive semantic segmentation.
Ranked #7 on Semantic Segmentation on SYNTHIA-to-Cityscapes
1 code implementation • 12 Mar 2022 • Wenbing Huang, Jiaqi Han, Yu Rong, Tingyang Xu, Fuchun Sun, Junzhou Huang
The core of GMN is that it represents, by generalized coordinates, the forward kinematics information (positions and velocities) of a structural object.
1 code implementation • 22 Feb 2022 • Jiaqi Han, Wenbing Huang, Tingyang Xu, Yu Rong
Equivariant Graph neural Networks (EGNs) are powerful in characterizing the dynamics of multi-body physical systems.
no code implementations • 15 Feb 2022 • Jiaqi Han, Yu Rong, Tingyang Xu, Wenbing Huang
Many scientific problems require to process data in the form of geometric graphs.
no code implementations • ICLR 2022 • Wenbing Huang, Jiaqi Han, Yu Rong, Tingyang Xu, Fuchun Sun, Junzhou Huang
In this manner, the geometrical constraints are implicitly and naturally encoded in the forward kinematics.
no code implementations • 29 Sep 2021 • Junwei Su, Jiaqi Han, Chuan Wu
In this paper, we study how the training set in the input graph effects the performance of GNN.