<p>Molecular property prediction plays a vital role in drug discovery, materials science, and chemical biology. Although molecular data are intrinsically multimodal—comprising 1D sequences or fingerprints, 2D topological graphs, and 3D geometric conformations—conventional approaches often rely on single-modal inputs, thereby failing to leverage cross-modal complementarities and limiting predictive accuracy. To overcome this limitation, we propose TMolNet, a task-aware deep learning framework for adaptive multimodal fusion. The architecture integrates modality-specific feature extractors to learn distinct representations from 1D, 2D, and 3D inputs, reducing the bias caused by incomplete or under-represented modalities. A contrastive learning scheme aligns the representations across modalities within a shared latent space, enhancing semantic consistency. Furthermore, a novel task-aware gating module dynamically modulates the contribution of each modality based on both data characteristics and task requirements. To promote balanced modality usage during training, we introduce a modality entropy regularization loss, which encourages diversity and stability in learned representations. Comprehensive experimental results on multiple benchmark datasets show that TMolNet achieves competitive performance against existing advanced methods in predictive accuracy and generalization. These findings underscore the efficacy of our approach and advance the state-of-the-art in multimodal molecular property prediction.</p>