Search

In the realm of vision models, the primary mode of representation is using pixels to rasterize the visual world. Yet this is not always the best or unique way to represent visual content, especially for designers and artists who depict the world using geometry primitives such as polygons. Vector graphics (VG), on the other hand, offer a textual representation of visual content, which can be more concise and powerful for content like cartoons, sketches and scientific figures. Recent studies have shown promising results on processing vector graphics with capable Large Language Models (LLMs). However, such works focus solely on qualitative results, understanding, or a specific type of vector graphics. We propose VGBench, a comprehensive benchmark for LLMs on handling vector graphics through diverse aspects, including (a) both visual understanding and generation, (b) evaluation of various vector graphics formats, (c) diverse question types, (d) wide range of prompting techniques, (e) under multiple LLMs and (f) comparison with VLMs on rasterized representations. Evaluating on our collected 4279 understanding and 5845 generation samples, we find that LLMs show strong capability on both aspects while exhibiting less desirable performance on low-level formats (SVG). Both data and evaluation pipeline will be open-sourced at https://vgbench.github.io., Comment: Project Page: https://vgbench.github.io

We develop a set of variable selection methods for the Cox model under interval censoring, in the ultra-high dimensional setting where the dimensionality can grow exponentially with the sample size. The methods select covariates via a penalized nonparametric maximum likelihood estimation with some popular penalty functions, including lasso, adaptive lasso, SCAD, and MCP. We prove that our penalized variable selection methods with folded concave penalties or adaptive lasso penalty enjoy the oracle property. Extensive numerical experiments show that the proposed methods have satisfactory empirical performance under various scenarios. The utility of the methods is illustrated through an application to a genome-wide association study of age to early childhood caries.

We propose CounterCurate, a framework to comprehensively improve the visio-linguistic compositional reasoning capability for both contrastive and generative multimodal models. In particular, we identify two critical under-explored problems: the neglect of the physically grounded reasoning (counting and position understanding) and the potential of using highly capable text and image generation models for semantic counterfactual fine-tuning. Our work pioneers an approach that addresses these gaps. We first spotlight the near-chance performance of multimodal models like CLIP and LLaVA in physically grounded compositional reasoning. We then apply simple data augmentation using grounded image generation model GLIGEN to generate fine-tuning data, resulting in significant performance improvements: +33% and +37% for CLIP and LLaVA, respectively, on our newly curated Flickr30k-Positions benchmark. Moreover, we exploit the capabilities of high-performing text generation and image generation models, specifically GPT-4V and DALLE-3, to curate challenging semantic counterfactuals, thereby further enhancing compositional reasoning capabilities on benchmarks such as SugarCrepe, where CounterCurate outperforms GPT-4V. To facilitate future research, we release our code, dataset, benchmark, and checkpoints at https://countercurate.github.io., Comment: 15 pages, 6 figures, 12 tables, Project Page: https://countercurate.github.io/

We develop a post-selection inference method for the Cox proportional hazards model with interval-censored data, which provides asymptotically valid p-values and confidence intervals conditional on the model selected by lasso. The method is based on a pivotal quantity that is shown to converge to a uniform distribution under local alternatives. The proof can be adapted to many other regression models, which is illustrated by the extension to generalized linear models and the Cox model with right-censored data. Our method involves estimation of the efficient information matrix, for which several approaches are proposed with proof of their consistency. Thorough simulation studies show that our method has satisfactory performance in samples of modest sizes. The utility of the method is illustrated via an application to an Alzheimer's disease study., Comment: 46 pages, 14 figures