Related papers: Contextual Molecule Representation Learning from C…

Developing machine learning (ML) models for yield prediction of chemical reactions has emerged as an important use case scenario in very recent years. In this space, reaction datasets present a range of challenges mostly stemming from…

Multimodal molecular representation learning, which jointly models molecular graphs and their textual descriptions, enhances predictive accuracy and interpretability by enabling more robust and reliable predictions of drug toxicity,…

Text images are unique in their dual nature, encompassing both visual and linguistic information. The visual component encompasses structural and appearance-based features, while the linguistic dimension incorporates contextual and semantic…

We present Region Similarity Representation Learning (ReSim), a new approach to self-supervised representation learning for localization-based tasks such as object detection and segmentation. While existing work has largely focused on…

Training a deep neural network to maximize a target objective has become the standard recipe for successful machine learning over the last decade. These networks can be optimized with supervised learning, if the target objective is…

The task of chemical reaction predictions (CRPs) plays a pivotal role in advancing drug discovery and material science. However, its effectiveness is constrained by the vast and uncertain chemical reaction space and challenges in capturing…

Masked Image Modeling (MIM) has recently been established as a potent pre-training paradigm. A pretext task is constructed by masking patches in an input image, and this masked content is then predicted by a neural network using visible…

Referring Expression Comprehension (REC) is a crucial cross-modal task that objectively evaluates the capabilities of language understanding, image comprehension, and language-to-image grounding. Consequently, it serves as an ideal testing…

Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deformations of the same input. Essentially, the model captures the…

In the computational prediction of chemical compound properties, molecular descriptors and fingerprints encoded to low dimensional vectors are used. The selection of proper molecular descriptors and fingerprints is both important and…

Recent advances in self-supervised learning (SSL) using large models to learn visual representations from natural images are rapidly closing the gap between the results produced by fully supervised learning and those produced by SSL on…

In Magnetic Resonance Imaging (MRI), image acquisitions are often undersampled in the measurement domain to accelerate the scanning process, at the expense of image quality. However, image quality is a crucial factor that influences the…

Contextual representation models have achieved great success in improving various downstream tasks. However, these language-model-based encoders are difficult to train due to the large parameter sizes and high computational complexity. By…

Retrosynthesis involves determining a sequence of reactions to synthesize complex molecules from simpler precursors. As this poses a challenge in organic chemistry, machine learning has offered solutions, particularly for predicting…

While deep learning methods have achieved impressive success in many vision benchmarks, it remains difficult to understand and explain the representations and decisions of these models. Though vision models are typically trained on 2D…

Referring Expression Comprehension (REC) requires models to localize objects in images based on natural language descriptions. Research on the area remains predominantly English-centric, despite increasing global deployment demands. This…

Recent advances in language models have enabled framing molecule generation as sequence modeling. However, existing approaches often rely on single-objective reinforcement learning, limiting their applicability to real-world drug design,…

Current deep reinforcement learning (RL) approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency. \textit{Objects} provide a succinct and causal description of the world, and many…

Cross-modal retrieval methods have been significantly improved in last years with the use of deep neural networks and large-scale annotated datasets such as ImageNet and Places. However, collecting and annotating such datasets requires a…

Causal representation learning (CRL) models aim to transform high-dimensional data into a latent space, enabling interventions to generate counterfactual samples or modify existing data based on the causal relationships among latent…