Related papers: PhAME: Phenotype-Aware Molecular Editing via Laten…

Low-light image enhancement (LLIE) is vital for safety-critical applications such as surveillance, autonomous navigation, and medical imaging, where visibility degradation can impair downstream task performance. Recently, diffusion models…

Deep neural networks achieve impressive performance but remain difficult to interpret and control. We present SALVE (Sparse Autoencoder-Latent Vector Editing), a unified "discover, validate, and control" framework that bridges mechanistic…

Leveraging the powerful capabilities of diffusion models has yielded quite effective results in medical image segmentation tasks. However, existing methods typically transfer the original training process directly without specific…

Production systems generate millions of log lines daily, yet most anomaly detectors operate at the session or window-level, flagging groups of lines rather than identifying the specific message responsible. This coarse granularity forces…

Large Language Models (LLMs) are increasingly used to brainstorm and evaluate research ideas, yet assessing such judgments is fundamentally difficult because the true impact of a new idea may take years to emerge. We address this challenge…

Molecular optimization seeks to improve a molecule through small structural edits while preserving similarity to the starting compound. Recent language-model approaches typically treat this task as prompt-conditioned sequence generation.…

Predicting spatial gene expression from routine H\&E enables large-scale molecular profiling, yet current models treat this as isolated pointwise tasks, thereby overlooking essential biological structures like gene coordination and spatial…

Diffusion models face a fundamental trade-off between generation quality and computational efficiency. Latent Diffusion Models (LDMs) offer an efficient solution but suffer from potential information loss and non-end-to-end training. In…

Computational modeling of single-cell gene expression is crucial for understanding cellular processes, but generating realistic expression profiles remains a major challenge. This difficulty arises from the count nature of gene expression…

Developing efficient multi-objective optimization methods to compute the Pareto set of optimal compromises between conflicting objectives remains a key challenge, especially for large-scale and expensive problems. To bridge this gap, we…

Topic Modeling refers to the problem of discovering the main topics that have occurred in corpora of textual data, with solutions finding crucial applications in numerous fields. In this work, inspired by the recent advancements in the…

We study the scaling properties of latent diffusion models (LDMs) with an emphasis on their sampling efficiency. While improved network architecture and inference algorithms have shown to effectively boost sampling efficiency of diffusion…

Generative models have achieved remarkable progress with the emergence of flow matching (FM). It has demonstrated strong generative capabilities and attracted significant attention as a simulation-free flow-based framework capable of…

Imaging of biological cells and tissues often relies on fluorescent labels, which offer high contrast with molecular specificity. The use of exogenous labeling agents, however, may alter the normal physiology of the bio-specimens.…

Prompt learning has emerged as a promising paradigm for adapting pre-trained vision-language models (VLMs) to few-shot whole slide image (WSI) classification by aligning visual features with textual representations, thereby reducing…

Image classification serves as the cornerstone of computer vision, traditionally achieved through discriminative models based on deep neural networks. Recent advancements have introduced classification methods derived from generative…

In this paper, we study the diffusability (learnability) of variational autoencoders (VAE) in latent diffusion. First, we show that pixel-space diffusion trained with an MSE objective is inherently biased toward learning low and mid spatial…

Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating…

Navigating the complex landscape of single-cell transcriptomic data presents significant challenges. Central to this challenge is the identification of a meaningful representation of high-dimensional gene expression patterns that sheds…

Diffusion models (DMs) have recently emerged as SoTA tools for generative modeling in various domains. Standard DMs can be viewed as an instantiation of hierarchical variational autoencoders (VAEs) where the latent variables are inferred…