Related papers: SIGMA: Structure-Invariant Generative Molecular Al…

Causal inference is a crucial goal of science, enabling researchers to arrive at meaningful conclusions regarding the predictions of hypothetical interventions using observational data. Path models, Structural Equation Models (SEMs), and,…

Automatic delineation of organ-at-risk (OAR) and gross-tumor-volume (GTV) is of great significance for radiotherapy planning. However, it is a challenging task to learn powerful representations for accurate delineation under limited pixel…

We explore an ensembled $\Sigma$-net for fast parallel MR imaging, including parallel coil networks, which perform implicit coil weighting, and sensitivity networks, involving explicit sensitivity maps. The networks in $\Sigma$-net are…

Graph Self-Supervised Learning (GSSL) has emerged as a powerful paradigm for generating high-quality representations for graph-structured data. While multi-scale graph contrastive learning has received increasing attention, many existing…

Molecular machine learning has gained popularity with the advancements of geometric deep learning. In parallel, retrieval-augmented generation has become a principled approach commonly used with language models. However, the optimal…

Graphs are ubiquitous data structures for representing interactions between entities. With an emphasis on the use of graphs to represent chemical molecules, we explore the task of learning to generate graphs that conform to a distribution…

We present Autoregressive Representation Alignment (ARRA), a new training framework that unlocks global-coherent text-to-image generation in autoregressive LLMs without architectural modifications. Different from prior works that require…

Graphs serve as versatile data structures in numerous real-world domains-including social networks, molecular biology, and knowledge graphs-by capturing intricate relational information among entities. Among graph-based learning techniques,…

Semantically guided conditional Generative Adversarial Networks (cGANs) have become a popular approach for face editing in recent years. However, most existing methods introduce semantic masks as direct conditional inputs to the generator…

In multimodal graph learning, graph structures that integrate information from multiple sources, such as vision and text, can more comprehensively model complex entity relationships. However, the continuous growth of their data scale poses…

Recent data-efficient molecular generation approaches exploit graph grammars to introduce interpretability into the generative models. However, grammar learning therein relies on expert annotation or unreliable heuristics for algorithmic…

Graph neural networks (GNNs) have been used extensively for addressing problems in drug design and discovery. Both ligand and target molecules are represented as graphs with node and edge features encoding information about atomic elements…

One of the most powerful techniques to study protein structures is to look for recurrent fragments (also called substructures or spatial motifs), then use them as patterns to characterize the proteins under study. An emergent trend consists…

The Dynamical Graph Grammar (DGG) formalism can describe complex system dynamics with graphs that are mapped into a master equation. An exact stochastic simulation algorithm may be used, but it is slow for large systems. To overcome this…

Large Language Model (LLM)-based Automated Program Repair (APR) has shown strong potential on textual benchmarks, yet struggles in multimodal scenarios where bugs are reported with GUI screenshots. Existing methods typically convert images…

Molecular generative models often assume meaningful latent geometry, but apparent property predictability can reflect sequence-level shortcuts rather than chemical organization. We study this issue in an unsupervised autoregressive…

Masked image generation (MIG) has demonstrated remarkable efficiency and high-fidelity images by enabling parallel token prediction. Existing methods typically rely solely on the model itself to learn semantic dependencies among visual…

Despite the success of foundation models in language and vision, molecular graph generation still lacks a unified framework for heterogeneous design tasks with reliable controllability. While reinforcement learning (RL) offers a natural…

Deep Generative Models (DGMs) are versatile tools for learning data representations while adequately incorporating domain knowledge such as the specification of conditional probability distributions. Recently proposed DGMs tackle the…

Learning the causal structure behind data is invaluable for improving generalization and obtaining high-quality explanations. We propose a novel framework, Invariant Structure Learning (ISL), that is designed to improve causal structure…