Related papers: Git for Sketches: An Intelligent Tracking System f…
4D video control is essential in video generation as it enables the use of sophisticated lens techniques, such as multi-camera shooting and dolly zoom, which are currently unsupported by existing methods. Training a video Diffusion…
Generative recommendation commonly adopts a two-stage pipeline in which a learnable tokenizer maps items to discrete token sequences (i.e. identifiers) and an autoregressive generative recommender model (GRM) performs prediction based on…
AI systems must adapt to evolving visual environments, especially in domains where object appearances change over time. We introduce Car Models in Time (CaMiT), a fine-grained dataset capturing the temporal evolution of car models, a…
This paper presents a Generative RegIon-to-Text transformer, GRiT, for object understanding. The spirit of GRiT is to formulate object understanding as <region, text> pairs, where region locates objects and text describes objects. For…
A spike camera is a specialized high-speed visual sensor that offers advantages such as high temporal resolution and high dynamic range compared to conventional frame cameras. These features provide the camera with significant advantages in…
State-of-the-art differentially private synthetic tabular data has been defined by adaptive 'select-measure-generate' frameworks, exemplified by methods like AIM. These approaches iteratively measure low-order noisy marginals and fit…
All text-based language problems can be reduced to either generation or embedding. Current models only perform well at one or the other. We introduce generative representational instruction tuning (GRIT) whereby a large language model is…
Biological systems in nature have evolved for millions of years to adapt and survive the environment. Many features they developed can be inspirational and beneficial for solving technical problems in modern industries. This leads to a…
Git metadata contains rich information for developers to understand the overall context of a large software development project. Thus it can help new developers, managers, and testers understand the history of development without needing to…
We present a sketch-based CAD modeling system, where users create objects incrementally by sketching the desired shape edits, which our system automatically translates to CAD operations. Our approach is motivated by the close similarities…
Advancements in Artificial Intelligence, particularly with ChatGPT, have significantly impacted software development. Utilizing novel data from GitHub Innovation Graph, we hypothesize that ChatGPT enhances software production efficiency.…
Recent advances in vision-language models have facilitated progress in sketch generation. However, existing specialized methods primarily focus on generic synthesis and lack mechanisms for precise control over sketch styles. In this work,…
Recently, there have been several promising methods to generate realistic imagery from deep convolutional networks. These methods sidestep the traditional computer graphics rendering pipeline and instead generate imagery at the pixel level…
In the early stages of architectural design, shoebox models are typically used as a simplified representation of building structures but require extensive operations to transform them into detailed designs. Generative artificial…
Graphical User Interfaces (GUIs) are central to app development projects. App developers may use the GUIs of other apps as a means of requirements refinement and rapid prototyping or as a source of inspiration for designing and improving…
Visual design relies on seeing things in different ways, acting on them, and seeing results to act again. Parametric design tools are often not robust to design changes that result from sketching over the visualization of their output. We…
Advancements at the intersection of computer vision and natural language processing are crucial for applications like assistive tech, multimedia querying, and robotics. This dissertation proposes novel architectures to improve intelligent…
Large Reasoning Models (LRMs) achieve remarkable inference-time improvements through parallel thinking. However, existing methods rely on redundant sampling of reasoning trajectories, failing to effectively explore the reasoning space to…
We introduce GENIUS: a conditional text generation model using sketches as input, which can fill in the missing contexts for a given sketch (key information consisting of textual spans, phrases, or words, concatenated by mask tokens).…
Sketching out Graphical User Interface (GUI) layout is part of the pipeline of designing a GUI and a crucial task for the success of a software application. Arranging all components inside a GUI layout manually is a time-consuming task. In…