SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.12467 · ICLR · 2024

Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer

Noseong Park, Jeongwhan Choi, Kookjin Lee, Youn-Yeol Yu, Woojin Cho, Nayong Kim, Kiseok Chang, Chang-Seung Woo, Ilho Kim, Seok-Woo Lee, Joon-Young Yang, Sooyoung Yoon

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 17 functions out of this paper's own repositories and ran 12 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
google-deepmind/deepmind-research canonical 7 of 11
yuyudeep/hcmt canonical 5 of 6
FunctionStatusWhere it lives
add_targets Ran yuyudeep/hcmt/dataset.py
pointer only (licence: NONE) · get_code("0f74786d92f7b6a0")
build_crops_biases Ran google-deepmind/deepmind-research/alphafold_casp13/contacts_network.py
code served (permissive licence) · get_code("c2695f5eb1e963a3")
call_on_tuple Ran google-deepmind/deepmind-research/alphafold_casp13/contacts_network.py
code served (permissive licence) · get_code("2a0b71f3e9b5a0d7")
conv2d Ran google-deepmind/deepmind-research/alphafold_casp13/two_dim_convnet.py
code served (permissive licence) · get_code("27c6606148980218")
equal32 Ran google-deepmind/deepmind-research/galaxy_mergers/losses.py
code served (permissive licence) · get_code("892496844acc7df6")
get_check_point_num Ran yuyudeep/hcmt/util.py
pointer only (licence: NONE) · get_code("a951207c022a9c79")
get_mask_impact_normal Ran yuyudeep/hcmt/util.py
pointer only (licence: NONE) · get_code("7182e4b73a148e4c")
mse_loss Ran google-deepmind/deepmind-research/galaxy_mergers/losses.py
code served (permissive licence) · get_code("b914b7fa073cd865")
normalize_regression_loss Ran google-deepmind/deepmind-research/galaxy_mergers/losses.py
code served (permissive licence) · get_code("f8ad297adc94df7d")
pairwise_dist Ran yuyudeep/hcmt/model.py
pointer only (licence: NONE) · get_code("7872fb172aaec6b0")
relative_shift Ran google-deepmind/deepmind-research/enformer/attention_module.py
code served (permissive licence) · get_code("cb4b6e4277150f01")
triangles_to_edges Ran yuyudeep/hcmt/util.py
pointer only (licence: NONE) · get_code("3fc3d053754bcdfb")
bias_variable Not yet run google-deepmind/deepmind-research/alphafold_casp13/two_dim_convnet.py
code served (permissive licence) · get_code("3bf8634c88f6bebc")
get_positional_feature_function Not yet run google-deepmind/deepmind-research/enformer/attention_module.py
code served (permissive licence) · get_code("6ee8170a2950ea7c")
load_dataset Not yet run yuyudeep/hcmt/dataset.py
pointer only (licence: NONE) · get_code("ace670d545ed0b9d")
positional_features_all Not yet run google-deepmind/deepmind-research/enformer/attention_module.py
code served (permissive licence) · get_code("6a7819159276d4e5")
weight_variable Not yet run google-deepmind/deepmind-research/alphafold_casp13/two_dim_convnet.py
code served (permissive licence) · get_code("7d7dfab4bbd647b3")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recently, many mesh-based graph neural network (GNN) models have been proposed for modeling complex high-dimensional physical systems. Remarkable achievements have been made in significantly reducing the solving time compared to traditional numerical solvers. These methods are typically designed to i) reduce the computational cost in solving physical dynamics and/or ii) propose techniques to enhance the solution accuracy in fluid and rigid body dynamics. However, it remains under-explored whether they are effective in addressing the challenges of flexible body dynamics, where instantaneous collisions occur within a very short timeframe. In this paper, we present Hierarchical Contact Mesh Transformer (HCMT), which uses hierarchical mesh structures and can learn long-range dependencies (occurred by collisions) among spatially distant positions of a body -two close positions in a higher-level mesh correspond to two distant positions in a lower-level mesh. HCMT enables long-range interactions, and the hierarchical mesh structure quickly propagates collision effects to faraway positions. To this end, it consists of a contact mesh Transformer and a hierarchical mesh Transformer (CMT and HMT, respectively). Lastly, we propose a flexible body dynamics dataset, consisting of trajectories that reflect experimental settings frequently used in the display industry for product designs. We also compare the performance of several baselines using well-known benchmark datasets. Our results show that HCMT provides significant performance improvements over existing methods. Our code is available at https://github.com/yuyudeep/hcmt.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2312.12467")
get_code_for_paper("2312.12467")
have("2312.12467")

Connect an agent — have() is free.