ChemFusion: A Multimodal Cross-Attention Network for Reaction Yield Prediction

• URL: http://arxiv.org/abs/2607.17033v1
• Date: Sun, 19 Jul 2026 02:31:29 GMT
• Title: ChemFusion: A Multimodal Cross-Attention Network for Reaction Yield Prediction
• Abstract summary: We present ChemFusion, a hybrid neural network that fuses conventional electronic features with explicit 3D atomic coordinates.<n>When benchmarked against a diverse library of cross-couplings, this approach delivers exceptional predictive performance.<n>This provides a physically grounded interpretability, demonstrating that spatially aware networks can navigate complex reaction sterics.
• Score: 0.8092815324198175
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Forecasting the outcomes of transition-metal-catalyzed reactions is notoriously complex due to the interplay of diverse physical and chemical variables. A persistent computational bottleneck has been effectively merging broad electronic descriptors with the localized, three-dimensional geometry of the reactive site. To bridge this representation gap, we present ChemFusion, a hybrid neural network that fuses conventional electronic features with explicit 3D atomic coordinates. Using a cross-attention mechanism, the model enables global electronic states to dynamically attend to specific spatial constraints within un-pooled molecular point clouds. When benchmarked against a diverse library of cross-couplings, this approach delivers exceptional predictive performance, decisively surpassing traditional single-modality frameworks. Importantly, extracting the attention matrices reveals that the architecture autonomously learns to identify and penalize restrictive steric hindrances. This provides a physically grounded interpretability, demonstrating that spatially aware networks can navigate complex reaction sterics that standard statistical models typically miss.

Related papers

• Momentum-Space-Engineered Spatial Photonic Ising Machine for Long-Range Interactions [4.122417270093307]
  spatial photonic Ising machine (SPIM) exploits intrinsic optical parallelism for Ising computation.<n>We present a momentum-space-engineered SPIM framework that maps prescribed long-range coupling kernels onto momentum-space masks.<n>We reproduce diverse ordered states induced by complex competing long-range interactions.
  arXiv  Detail & Related papers  (2026-09-07T10:14:17Z)
• Generic Vision and Cross-Attention for Reaction Yield Prediction [0.8092815324198175]
  Vision Cross-Attention architecture is proposed, fusing physical-organic data with 2D molecular topologies.<n>It is demonstrated that a generic computer vision backbone processing simple 2D skeletal structures independently outperforms purely quantum-based baselines.
  arXiv  Detail & Related papers  (2026-08-01T17:14:26Z)
• Graph-Theoretic Neural Network Fragmentation with Covariant Direct Molecular Force Learning: Enabling Coupled-Cluster Accuracy AIMD for Fluxional Systems [1.476367559174889]
  We present a graph-theoretic molecular fragmentation framework integrated with machine learning to model post-Hartree-Fock nuclear forces.<n>Our framework successfully reproduced complex dynamical signatures and key structural characteristics.<n>Ultimately, this scalable, systematically improvable framework bridges the gap between high-level correlated wavefunction theories and long-timescale reactive sampling.
  arXiv  Detail & Related papers  (2026-07-23T19:49:22Z)
• Kirchhoff-Inspired Neural Networks for Evolving High-Order Perception [51.28469959548178]
  We propose the Kirchhoff-Inspired Neural Network (KINN), a state-variable-based network architecture constructed based on Kirchhoff's current law.<n>KINN derives numerically stable state updates from fundamental ordinary differential equations, enabling the explicit decoupling and encoding of higher-order evolutionary components.
  arXiv  Detail & Related papers  (2026-03-25T06:17:31Z)
• Engineering quantum criticality and dynamics on an analog-digital simulator [26.76525389323686]
  We use coherent mapping between the Rydberg and hyperfine qubits in a neutral atom array simulator to engineer and probe complex quantum dynamics.<n>We first demonstrate dynamical engineering of ring-exchange and particle hopping dynamics via Floquet driving.<n>We employ closed-loop optimization to target an out-of-equilibrium critical quantum spin liquid of the Rokhsar-Kivelson type.
  arXiv  Detail & Related papers  (2026-02-20T19:00:00Z)
• Tokenizing Electron Cloud in Protein-Ligand Interaction Learning [51.74909649330779]
  ECBind is a method for tokenizing electron cloud signals into quantized embeddings.<n>It helps uncover binding modes that cannot be fully represented by atom-level models.<n>To extend its applicability to a wider range of scenarios, we utilize knowledge distillation to develop an electron-cloud-agnostic prediction model.
  arXiv  Detail & Related papers  (2025-05-25T07:36:50Z)
• KITINet: Kinetics Theory Inspired Network Architectures with PDE Simulation Approaches [43.872190335490515]
  This paper introduces KITINet, a novel architecture that reinterprets feature propagation through the lens of non-equilibrium particle dynamics.<n>At its core, we propose a residual module that models update as the evolution of a particle system.<n>This formulation mimics particle collisions and energy exchange, enabling adaptive feature refinement via physics-informed interactions.
  arXiv  Detail & Related papers  (2025-05-23T13:58:29Z)
• AlphaNet: Scaling Up Local-frame-based Atomistic Interatomic Potential [24.9325296129376]
  We present AlphaNet, a local equi-frame-based model that simultaneously improves computational efficiency and predictive precision for interatomic interactions.<n>AlphaNet encodes atomic environments with enhanced representational capacity, achieving stateof-the-art in accuracy and force predictions.
  arXiv  Detail & Related papers  (2025-01-13T09:28:47Z)
• Explosive neural networks via higher-order interactions in curved statistical manifolds [43.496401697112695]
  We introduce curved neural networks as a class of prototypical models with a limited number of parameters.<n>We show that these curved neural networks implement a self-regulating process that can accelerate memory retrieval.<n>We analytically explore their memory-retrieval capacity using the replica trick near ferromagnetic and spin-glass phase boundaries.
  arXiv  Detail & Related papers  (2024-08-05T09:10:29Z)
• Inferring Relational Potentials in Interacting Systems [56.498417950856904]
  We propose Neural Interaction Inference with Potentials (NIIP) as an alternative approach to discover such interactions. NIIP assigns low energy to the subset of trajectories which respect the relational constraints observed. It allows trajectory manipulation, such as interchanging interaction types across separately trained models, as well as trajectory forecasting.
  arXiv  Detail & Related papers  (2023-10-23T00:44:17Z)
• Physics-inspired Equivariant Descriptors of Non-bonded Interactions [0.0]
  We present an extension of the long distance equivariant (LODE) framework that can handle diverse LR interactions in a consistent way. We provide a direct physical interpretation of these using the multipole expansion which allows for simpler and more efficient implementations.
  arXiv  Detail & Related papers  (2023-08-25T07:04:16Z)
• Message-Passing Neural Quantum States for the Homogeneous Electron Gas [41.94295877935867]
  We introduce a message-passing-neural-network-based wave function Ansatz to simulate extended, strongly interacting fermions in continuous space. We demonstrate its accuracy by simulating the ground state of the homogeneous electron gas in three spatial dimensions.
  arXiv  Detail & Related papers  (2023-05-12T04:12:04Z)
• Neural-network solutions to stochastic reaction networks [7.021105583098606]
  We propose a machine-learning approach using the variational autoregressive network to solve the chemical master equation. The proposed approach tracks the time evolution of the joint probability distribution in the state space of species counts. We demonstrate that it accurately generates the probability distribution over time in the genetic toggle switch and the early life self-replicator.
  arXiv  Detail & Related papers  (2022-09-29T07:27:59Z)
• Imaginary components of out-of-time correlators and information scrambling for navigating the learning landscape of a quantum machine learning model [0.0]
  We analytically illustrate that hitherto unexplored imaginary components of out-of-time correlators can provide unprecedented insight into the information scrambling capacity of a graph neural network. Such an analysis demystifies the training of quantum machine learning models by unraveling how quantum information is scrambled through such a network.
  arXiv  Detail & Related papers  (2022-08-29T06:17:28Z)
• Graph Neural Network for Hamiltonian-Based Material Property Prediction [56.94118357003096]
  We present and compare several different graph convolution networks that are able to predict the band gap for inorganic materials. The models are developed to incorporate two different features: the information of each orbital itself and the interaction between each other. The results show that our model can get a promising prediction accuracy with cross-validation.
  arXiv  Detail & Related papers  (2020-05-27T13:32:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.