{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/geometric-trajectory-diffusion-models","title":"Geometric Trajectory Diffusion Models","arxiv_id":"2410.13027","date":"2024-10-16","proceeding":null,"authors":["Jiaqi Han","Minkai Xu","Aaron Lou","Haotian Ye","Stefano Ermon"],"abstract":"Generative models have shown great promise in generating 3D geometric systems, which is a fundamental problem in many natural science domains such as molecule and protein design. However, existing approaches only operate on static structures, neglecting the fact that physical systems are always dynamic in nature. In this work, we propose geometric trajectory diffusion models (GeoTDM), the first diffusion model for modeling the temporal distribution of 3D geometric trajectories. Modeling such distribution is challenging as it requires capturing both the complex spatial interactions with physical symmetries and temporal correspondence encapsulated in the dynamics. We theoretically justify that diffusion models with equivariant temporal kernels can lead to density with desired symmetry, and develop a novel transition kernel leveraging SE(3)-equivariant spatial convolution and temporal attention. Furthermore, to induce an expressive trajectory distribution for conditional generation, we introduce a generalized learnable geometric prior into the forward diffusion process to enhance temporal conditioning. We conduct extensive experiments on both unconditional and conditional generation in various scenarios, including physical simulation, molecular dynamics, and pedestrian motion. Empirical results on a wide suite of metrics demonstrate that GeoTDM can generate realistic geometric trajectories with significantly higher quality.","url_abs":"https://arxiv.org/abs/2410.13027v1","url_pdf":"https://arxiv.org/pdf/2410.13027v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"geometric-trajectory-diffusion-models","repo_url":"https://github.com/hanjq17/geotdm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"protein-design","task_name":"Protein Design"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.13027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13027"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hanjq17/geotdm","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_honours":3,"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":10,"ran":9,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"64d1fb56f7e05906","entry":"gaussian_log_likelihood","repo":"hanjq17/geotdm","repo_kind":"official","path":"diffusion/losses.py","file_url":"https://github.com/hanjq17/geotdm/blob/HEAD/diffusion/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"64d1fb56f7e05906"}},{"code_sha256_prefix":"a086d6286a40b889","entry":"get_named_beta_schedule","repo":"hanjq17/geotdm","repo_kind":"official","path":"diffusion/GeoTDM.py","file_url":"https://github.com/hanjq17/geotdm/blob/HEAD/diffusion/GeoTDM.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a086d6286a40b889"}},{"code_sha256_prefix":"9e697b0ccd832314","entry":"get_timestep_embedding","repo":"hanjq17/geotdm","repo_kind":"official","path":"models/EGTN.py","file_url":"https://github.com/hanjq17/geotdm/blob/HEAD/models/EGTN.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e697b0ccd832314"}},{"code_sha256_prefix":"d967154c60f2573c","entry":"lr_decay","repo":"hanjq17/geotdm","repo_kind":"official","path":"experiments/eth_train_new.py","file_url":"https://github.com/hanjq17/geotdm/blob/HEAD/experiments/eth_train_new.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d967154c60f2573c"}},{"code_sha256_prefix":"f6d7c009a8efb8b7","entry":"mean_flat","repo":"hanjq17/GeoTDM","repo_kind":"official","path":"diffusion/GeoTDM.py","file_url":"https://github.com/hanjq17/GeoTDM/blob/HEAD/diffusion/GeoTDM.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6d7c009a8efb8b7"}},{"code_sha256_prefix":"c5b66a6793505502","entry":"merge_time_dim","repo":"hanjq17/geotdm","repo_kind":"official","path":"models/layers.py","file_url":"https://github.com/hanjq17/geotdm/blob/HEAD/models/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c5b66a6793505502"}},{"code_sha256_prefix":"cf2798b666b231ca","entry":"normal_kl","repo":"hanjq17/geotdm","repo_kind":"official","path":"diffusion/losses.py","file_url":"https://github.com/hanjq17/geotdm/blob/HEAD/diffusion/losses.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf2798b666b231ca"}},{"code_sha256_prefix":"81a3074e9a1b7180","entry":"separate_time_dim","repo":"hanjq17/geotdm","repo_kind":"official","path":"models/layers.py","file_url":"https://github.com/hanjq17/geotdm/blob/HEAD/models/layers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"81a3074e9a1b7180"}},{"code_sha256_prefix":"b77621bc47b35e05","entry":"sum_flat","repo":"hanjq17/GeoTDM","repo_kind":"official","path":"diffusion/GeoTDM.py","file_url":"https://github.com/hanjq17/GeoTDM/blob/HEAD/diffusion/GeoTDM.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b77621bc47b35e05"}},{"code_sha256_prefix":"e86e37d63199f8fd","entry":"histogram_torch","repo":"hanjq17/geotdm","repo_kind":"official","path":"experiments/scores.py","file_url":"https://github.com/hanjq17/geotdm/blob/HEAD/experiments/scores.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e86e37d63199f8fd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}