Video World Models · 2026-11-09
BiLoGo: Reducing the smoothing of localised responses in Transformer-based neural operators for sheet forming
Yingxue Zhao, Haoran Li, Haosu Zhou, Tobias Pfaff, Nan Li
AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.
TL;DR
BiLoGo is an FE-guided learned simulator for sheet forming that reduces smoothing of localized thinning responses. It combines bidirectional node–element GraphSAGE (no interpolation), a dual-stream Transformer neural operator with separate tokens for blank deformation and tool contact, and gated residual fusion with element updates conditioned on element-node kinematics. The authors evaluate on dome and two corner cases and report lowest positional and threshold-based thinning errors, with higher rib-near smoothing index than token-only Transformer models.
Why it matters
Localized thinning near sharp radii and reinforcing ribs can determine formability. Transformer-based neural operators can smooth these localized responses, especially when contact information is averaged with the whole blank. BiLoGo’s local node–element processing plus dual-stream global propagation targets this failure mode while also being evaluated on memory use and across cases with different localization strengths.
Method
- BiLoGo uses a bidirectional node–element GraphSAGE on a bipartite graph, predicting each quantity on its native FE entity without interpolation.
- A dual-stream Transformer-based neural operator processes blank deformation and tool contact with separate token sets to avoid averaging localized contact with the whole-blank state; contact tokens query state tokens through cross-attention.
- A fusion and element update module combines global and local features via gated residual fusion and updates element features conditioned on relative positions/displacements of element nodes; BiLoGo-T and BiLoGo-U differ in tokeniser choice.
Abstract (from arXiv)
Trial-and-error FE simulation of sheet forming could be computationally expensive, neural-network-based learned simulators are used to accelerate design. These simulators should accurately capture localised responses, such as thinning around sharp radii or near ribs, which determine formability. Transformer-based neural operators propagate information efficiently across the mesh but tend to smooth such localised responses. This study develops BiLoGo, a Bipartite Local-Global learned simulator with an FE-guided design that connects local node-element message passing with a Transformer-based neural operator for long-range information exchange. BiLoGo has three modules: a bidirectional node-element GraphSAGE model that learns nodal-elemental coupling on a bipartite graph and predicts each quantity on its native FE entity without interpolation; a dual-stream Transformer-based neural operator that processes blank deformation and tool contact with separate token sets, preventing localised contact information from being averaged with the whole-blank state; and a fusion and element update module that combines global and local features via gated residual fusion and updates element features conditioned on element-node kinematics. Evaluated on a dome-shaped cold forming case and two corner-shaped hot stamping cases (one with ribs), BiLoGo achieves the lowest positional and threshold-based thinning errors on all three cases compared with single-level and hierarchical graph-based models and Transformer-based neural operators. Near the ribs, the smoothing index of predicted thinning increases from 0.41-0.56 for Transformer-based neural operators to 0.94 for BiLoGo-U. Compared with the hierarchical graph network CAtt-BiUGNN, BiLoGo-T reduces mean positional error by 15.5% on the Corner case and BiLoGo-U by 8.3% on the Corner+Rib case, with 66-69% less training memory.
Related papers
- CAD-WAM: Anticipating Geometry for Text-to-CAD Generation
- RiCo: Neural Simulation of Rigid-Body Interactions via Local Contact Reasoning
- Predicting Cable Dynamics with Physical Attention Bias
- In-Context Learning World Models for Robot Dual-Arm Manipulation of Soft Garment with Partial Observations
- Same Target, Different Origins: Aligning Latent Rollout for Consistent PDE Emulation
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First public release: 2026-11-06 · Indexed by Pub-AI: 2026-11-09 UTC
BiLoGo: Reducing the smoothing of localised responses in Transformer-based neural operators for sheet forming
Preprint posted: 2026-11-06 · Original record ↗
- arxiv
- 2611.09621
Explicit source versions (1)
- v1 · 2026-11-06
- Preprint available
Source date: 2026-11-06 · First detected: 2026-11-09 UTC · Historical baseline
Source evidence (2)
- Official evidence ↗ · RSS guid=oai:arXiv.org:2611.09621v1; arxiv:announce_type=new; item pubDate (official metadata)
- Official evidence ↗ · atom:published (official metadata)
Abstract · arxiv
Trial-and-error FE simulation of sheet forming could be computationally expensive, neural-network-based learned simulators are used to accelerate design. These simulators should accurately capture localised responses, such as thinning around sharp radii or near ribs, which determine formability. Transformer-based neural operators propagate information efficiently across the mesh but tend to smooth such localised responses. This study develops BiLoGo, a Bipartite Local-Global learned simulator with an FE-guided design that connects local node-element message passing with a Transformer-based neural operator for long-range information exchange. BiLoGo has three modules: a bidirectional node-element GraphSAGE model that learns nodal-elemental coupling on a bipartite graph and predicts each quantity on its native FE entity without interpolation; a dual-stream Transformer-based neural operator that processes blank deformation and tool contact with separate token sets, preventing localised contact information from being averaged with the whole-blank state; and a fusion and element update module that combines global and local features via gated residual fusion and updates element features conditioned on element-node kinematics. Evaluated on a dome-shaped cold forming case and two corner-shaped hot stamping cases (one with ribs), BiLoGo achieves the lowest positional and threshold-based thinning errors on all three cases compared with single-level and hierarchical graph-based models and Transformer-based neural operators. Near the ribs, the smoothing index of predicted thinning increases from 0.41-0.56 for Transformer-based neural operators to 0.94 for BiLoGo-U. Compared with the hierarchical graph network CAtt-BiUGNN, BiLoGo-T reduces mean positional error by 15.5% on the Corner case and BiLoGo-U by 8.3% on the Corner+Rib case, with 66-69% less training memory.
