Related papers: SIGMA: Structure-Invariant Generative Molecular Al…
Graph representation learning (GRL) on attribute-missing graphs, which is a common yet challenging problem, has recently attracted considerable attention. We observe that existing literature: 1) isolates the learning of attribute and…
Multimodal knowledge graph link prediction aims to improve the accuracy and efficiency of link prediction tasks for multimodal data. However, for complex multimodal information and sparse training data, it is usually difficult to achieve…
Graph State Space Models (SSMs) have recently been introduced to enhance Graph Neural Networks (GNNs) in modeling long-range interactions. Despite their success, existing methods either compromise on permutation equivariance or limit their…
Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image. However, semantic mismatch between an image and sentences usually happens in finer…
We present SIGMA-GEN, a unified framework for multi-identity preserving image generation. Unlike prior approaches, SIGMA-GEN is the first to enable single-pass multi-subject identity-preserved generation guided by both structural and…
Medical image segmentation driven by free-text clinical instructions is a critical frontier in computer-aided diagnosis. However, existing multimodal and foundation models struggle with the semantic ambiguity of clinical reports and fail to…
Drug-target binding affinity prediction plays an important role in the early stages of drug discovery, which can infer the strength of interactions between new drugs and new targets. However, the performance of previous computational models…
In this work, we analyze the optimization dynamics of generative fine-tuning. We observe that under the Flow Matching framework, the standard MSE objective can be formulated as a Quadratic Form governed by a dynamically evolving Neural…
Abstract Meaning Representation (AMR) parsing aims to extract an abstract semantic graph from a given sentence. The sequence-to-sequence approaches, which linearize the semantic graph into a sequence of nodes and edges and generate the…
Structure-based drug discovery faces the dual challenge of accurately capturing 3D protein-ligand interactions while navigating ultra-large chemical spaces to identify synthetically accessible candidates. In this work, we present a unified…
Event temporal graphs have been shown as convenient and effective representations of complex temporal relations between events in text. Recent studies, which employ pre-trained language models to auto-regressively generate linearised graphs…
The quest for accurate prediction of drug molecule properties poses a fundamental challenge in the realm of Artificial Intelligence Drug Discovery (AIDD). An effective representation of drug molecules emerges as a pivotal component in this…
Generative graph self-supervised learning (SSL) aims to learn node representations by reconstructing the input graph data. However, most existing methods focus on unsupervised learning tasks only and very few work has shown its superiority…
Recent multimodal models such as Contrastive Language-Image Pre-training (CLIP) have shown remarkable ability to align visual and linguistic representations. However, domains where small visual differences carry large semantic significance,…
Learning medical visual representations from paired images and reports is a promising direction in representation learning. However, current vision-language pretraining methods in the medical domain often simplify clinical reports into…
Domain Adaptive Object Detection (DAOD) leverages a labeled domain to learn an object detector generalizing to a novel domain free of annotations. Recent advances align class-conditional distributions by narrowing down cross-domain…
Molecular representation learning is a crucial task in predicting molecular properties. Molecules are often modeled as graphs where atoms and chemical bonds are represented as nodes and edges, respectively, and Graph Neural Networks (GNNs)…
Text-driven image editing has advanced rapidly, but reliably localizing these manipulations requires image manipulation localization (IML) models trained on large pixel-annotated datasets, and there is still no low-cost way to obtain such…
There has been exciting progress in generating images from natural language or layout conditions. However, these methods struggle to faithfully reproduce complex scenes due to the insufficient modeling of multiple objects and their…
Recent advances in Diffusion Transformers (DiTs) demonstrate that aligning noisy latent states with well-trained semantic features-as pioneered by Representation Alignment (REPA)-can substantially accelerate training and improve generation…