Related papers: SynthLens: Visual Analytics for Facilitating Multi…
Training multimodal large language models (MLLMs) for video understanding requires large-scale annotated data spanning diverse tasks such as object counting, question answering, and segmentation. However, collecting and annotating…
Proteins perform critical processes in all living systems: converting solar energy into chemical energy, replicating DNA, as the basis of highly performant materials, sensing and much more. While an incredible range of functionality has…
In the interaction between agents and their environments, agents expand their capabilities by planning and executing actions. However, LLM-based agents face substantial challenges when deployed in novel environments or required to navigate…
Efficiently reviewing scholarly literature and synthesizing prior art are crucial for scientific progress. Yet, the growing scale of publications and the burden of knowledge make synthesis of research threads more challenging than ever.…
From medicines to materials, small organic molecules are indispensable for human well-being. To plan their syntheses, chemists employ a problem solving technique called retrosynthesis. In retrosynthesis, target molecules are recursively…
Content creation, central to applications such as virtual reality, can be a tedious and time-consuming. Recent image synthesis methods simplify this task by offering tools to generate new views from as little as a single input image, or by…
Computer-aided synthesis planning (CASP) has long been envisioned as a complementary tool for synthetic chemists. However, existing frameworks often lack mechanisms to allow interaction with human experts, limiting their ability to…
In data management, and in particular in data integration, data exchange, query optimization, and data privacy, the notion of view plays a central role. In several contexts, such as data integration, data mashups, and data warehousing, the…
To evaluate end-to-end autonomous driving systems, a simulation environment based on Novel View Synthesis (NVS) techniques is essential, which synthesizes photo-realistic images and point clouds from previously recorded sequences under new…
A well-known pitfall of molecular generative models is that they are not guaranteed to generate synthesizable molecules. Existing solutions for this problem often struggle to effectively navigate exponentially large combinatorial space of…
Modern computer-assisted synthesis planning (CASP) systems show promises at generating chemically valid reaction steps but struggle to incorporate strategic considerations such as convergent assembly, protecting group minimization, and…
We introduce Synscapes -- a synthetic dataset for street scene parsing created using photorealistic rendering techniques, and show state-of-the-art results for training and validation as well as new types of analysis. We study the behavior…
The scarcity of data depicting dangerous situations presents a major obstacle to training AI systems for safety-critical applications, such as construction safety, where ethical and logistical barriers hinder real-world data collection.…
In this work we propose a deep learning pipeline to predict the visual future appearance of an urban scene. Despite recent advances, generating the entire scene in an end-to-end fashion is still far from being achieved. Instead, here we…
Despite significant progress on current state-of-the-art image generation models, synthesis of document images containing multiple and complex object layouts is a challenging task. This paper presents a novel approach, called DocSynth, to…
This paper introduces SynthDoc, a novel synthetic document generation pipeline designed to enhance Visual Document Understanding (VDU) by generating high-quality, diverse datasets that include text, images, tables, and charts. Addressing…
The past few years have witnessed vibrant efforts in discovering new two-dimensional (2D) semiconductor materials from both academia and the industry, due to their promising potential in resolving the severe performance deterioration of…
Skyline queries have wide-ranging applications in fields that involve multi-criteria decision making, including tourism, retail industry, and human resources. By automatically removing incompetent candidates, skyline queries allow users to…
Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored synthetic data generation to address this challenge, however, they suffer from data quality issues…
Recent studies in Vision-and-Language Navigation (VLN) train RL agents to execute natural-language navigation instructions in photorealistic environments, as a step towards robots that can follow human instructions. However, given the…