Related papers: EvoCAD: Evolutionary CAD Code Generation with Visi…
We ask the question: to what extent can recent large-scale language and image generation models blend visual concepts? Given an arbitrary object, we identify a relevant object and generate a single-sentence description of the blend of the…
Recently, the remarkable advance of the Large Language Model (LLM) has inspired researchers to transfer its extraordinary reasoning capability to both vision and language data. However, the prevailing approaches primarily regard the visual…
Geometric Deep Learning techniques have become a transformative force in the field of Computer-Aided Design (CAD), and have the potential to revolutionize how designers and engineers approach and enhance the design process. By harnessing…
Recently, we have witnessed the rapid development of large language models, which have demonstrated excellent capabilities in the downstream task of code generation. However, despite their potential, LLM-based code generation still faces…
The discovery of symbolic solutions -- mathematical expressions, logical rules, and algorithmic structures -- is fundamental to advancing scientific and engineering progress. However, traditional methods often struggle with search…
Algorithms that use Large Language Models (LLMs) to evolve code arrived on the Genetic Programming (GP) scene very recently. We present LLM GP, a formalized LLM-based evolutionary algorithm designed to evolve code. Like GP, it uses…
Visual communication, dating back to prehistoric cave paintings, is the use of visual elements to convey ideas and information. In today's visually saturated world, effective design demands an understanding of graphic design principles,…
Score Distillation Sampling (SDS) enables high-quality text-to-3D generation by supervising 3D models through the denoising of multi-view 2D renderings, using a pretrained text-to-image diffusion model to align with the input prompt and…
Generating editable, parametric CAD models from a single image holds great potential to lower the barriers of industrial concept design. However, current multi-modal large language models (MLLMs) still struggle with accurately inferring 3D…
Language-based object detection (LOD) aims to align visual objects with language expressions. A large amount of paired data is utilized to improve LOD model generalizations. During the training process, recent studies leverage…
We propose associating language utterances to 3D visual abstractions of the scene they describe. The 3D visual abstractions are encoded as 3-dimensional visual feature maps. We infer these 3D visual scene feature maps from RGB images of the…
This work presents a comparative analysis of embedding-based and generative models for classifying geoscience technical documents. Using a multi-disciplinary benchmark dataset, we evaluated the trade-offs between model accuracy, stability,…
The generation of industrial Computer-Aided Design (CAD) models from user requests and specifications is crucial to enhancing efficiency in modern manufacturing. Traditional methods of CAD generation rely heavily on manual inputs and…
Integrating visual and linguistic information into a single multimodal representation is an unsolved problem with wide-reaching applications to both natural language processing and computer vision. In this paper, we present a simple method…
Progress in 3D vision-language learning has been hindered by the scarcity of large-scale 3D datasets. We introduce UniVLG, a unified architecture for 2D and 3D vision-language understanding that bridges the gap between existing 2D-centric…
Most existing approaches formulate action quality assessment and skill proficiency estimation as discriminative prediction tasks, typically producing discrete labels or scores without explicitly modeling the reasoning process underlying the…
Recent advances in data-driven evolutionary algorithms (EAs) have demonstrated the potential of leveraging historical data to improve optimization accuracy and adaptability. Despite these advancements, existing methods remain reliant on…
Optimization benchmarks play a fundamental role in assessing algorithm performance; however, existing artificial benchmarks often fail to capture the diversity and irregularity of real-world problem structures, while benchmarks derived from…
The dominant approach to generating from language models subject to some constraint is locally constrained decoding (LCD), incrementally sampling tokens at each time step such that the constraint is never violated. Typically, this is…
Advances in 3D generative AI have enabled the creation of physical objects from text prompts, but challenges remain in creating objects involving multiple component types. We present a pipeline that integrates 3D generative AI with…