Related papers: Zero-Shot 3D Drug Design by Sketching and Generati…

Generating realistic images from arbitrary views based on a single source image remains a significant challenge in computer vision, with broad applications ranging from e-commerce to immersive virtual experiences. Recent advancements in…

Sketch-based 3D reconstruction remains a challenging task due to the abstract and sparse nature of sketch inputs, which often lack sufficient semantic and geometric information. To address this, we propose Sketch2Symm, a two-stage…

This paper presents the first exploration of text-to-image diffusion models for zero-shot sketch-based 3D shape retrieval (ZS-SBSR). Existing sketch-based 3D shape retrieval methods struggle in zero-shot settings due to the absence of…

De novo molecule generation often results in chemically unfeasible molecules. A natural idea to mitigate this problem is to bias the search process towards more easily synthesizable molecules using a proxy for synthetic accessibility.…

Drug discovery can be viewed as a combinatorial search over an immense chemical space, motivating the development of deep generative models for de novo molecular design. Among these, GPT-based molecular language models (MLM) have shown…

Drug repositioning (DR) refers to identification of novel indications for the approved drugs. The requirement of huge investment of time as well as money and risk of failure in clinical trials have led to surge in interest in drug…

With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to…

Structure-Based Drug Design (SBDD) has revolutionized drug discovery by enabling the rational design of molecules for specific protein targets. Despite significant advancements in improving docking scores, advanced 3D-SBDD generative models…

In this paper, we develop an efficient sketchy empirical natural gradient method (SENG) for large-scale deep learning problems. The empirical Fisher information matrix is usually low-rank since the sampling is only practical on a small…

In the early stages of engineering design, it is essential to know how a product behaves, especially how it moves. As designers must keep adjusting the motion until it meets the intended requirements, this process is often repetitive and…

Visual recognition of materials and their states is essential for understanding the physical world, from identifying wet regions on surfaces or stains on fabrics to detecting infected areas on plants or minerals in rocks. Collecting data…

Doodling is a useful and common intelligent skill that people can learn and master. In this work, we propose a two-stage learning framework to teach a machine to doodle in a simulated painting environment via Stroke Demonstration and deep…

Knowledge distillation (KD) is a successful approach for deep neural network acceleration, with which a compact network (student) is trained by mimicking the softmax output of a pre-trained high-capacity network (teacher). In tradition, KD…

The structural design of functional molecules, also called molecular optimization, is an essential chemical science and engineering task with important applications, such as drug discovery. Deep generative models and combinatorial…

When it comes to deploying deep vision models, the behavior of these systems must be explicable to ensure confidence in their reliability and fairness. A common approach to evaluate deep learning models is to build a labeled test set with…

Recent progress in 3D/4D scene generation emphasizes the importance of physical alignment throughout video generation and scene reconstruction. However, existing methods improve the alignment separately at each stage, making it difficult to…

Phase can be reliably estimated from a single diffracted intensity image, if a faithful prior information about the object is available. Examples include amplitude bounds, object support, sparsity in the spatial or a transform domain, deep…

In this paper, we study learning semantic representations for million-scale free-hand sketches. This is highly challenging due to the domain-unique traits of sketches, e.g., diverse, sparse, abstract, noisy. We propose a dual-branch CNNRNN…

In the generalized zero-shot learning, synthesizing unseen data with generative models has been the most popular method to address the imbalance of training data between seen and unseen classes. However, this method requires that the unseen…

Can a user create a deep generative model by sketching a single example? Traditionally, creating a GAN model has required the collection of a large-scale dataset of exemplars and specialized knowledge in deep learning. In contrast,…