BiMol-Diff: A Unified Diffusion Framework for Molecular Generation and Captioning
Bridging molecular structures and natural language is essential for controllable design. Autoregressive models struggle with long-range dependencies, while standard diffusion processes apply uniform corruption across positions, which can distort structurally informative tokens. We present BiMol-Diff, a unified diffusion framework for the paired tasks of text-conditioned molecule generation and molecule captioning. Our key component is a token-aware noise schedule that assigns position-dependent corruption based on token recovery difficulty, preserving harder-to-recover substructures during the forward process. On ChEBI-20 and M3-20M, BiMol-Diff improves molecule reconstruction with a 15.4% relative gain in Exact Match and achieves strong captioning results, attaining best BLEU and BERTScore among compared baselines. These results indicate token-aware noising improves fidelity in molecular structure-language modelling.
Code (0)
등록된 구현이 없습니다.
Tasks
Molecule CaptioningLanguage ModellingSimilar Papers 제목 키워드 기반
Integral feedback in synthetic biology: Negative-equilibrium catastrophe
A central goal of synthetic biology is the design of molecular controllers that can manipulate the dynamics of intracellular networks in a stable and accurate manner. To address the fact that detailed knowledge about int…
Unsupervised Machine Learning Based on Non-Negative Tensor Factorization for Analyzing Reactive-Mixing
Analysis of reactive-diffusion simulations requires a large number of independent model runs. For each high-fidelity simulation, inputs are varied and the predicted mixing behavior is represented by changes in species co…
BIG-bench Machine LearningClusteringInstruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model
Recent advancements in computational chemistry have increasingly focused on synthesizing molecules based on textual instructions. Integrating graph generation with these instructions is complex, leading most current meth…
Computational chemistryDenoisingGraph GenerationMolecular Graph GenerationUnified Guidance for Geometry-Conditioned Molecular Generation
Effectively designing molecular geometries is essential to advancing pharmaceutical innovations, a domain, which has experienced great attention through the success of generative models and, in particular, diffusion mode…
Drug DesignSurface reaction-diffusion kinetics on lattice at the microscopic scale
Microscopic models of reaction-diffusion processes on the cell membrane can link local spatiotemporal effects to macroscopic self-organized patterns often observed on the membrane. Simulation schemes based on the microsc…