Related papers: Learning UI-to-Code Reverse Generator Using Visual…
UI-to-code technology has streamlined the front-end development process, reducing repetitive tasks for engineers. prior research mainly use design prototypes as inputs, with the effectiveness of the generated code heavily dependent on these…
Pretraining language models with next-token prediction on massive text corpora has delivered phenomenal zero-shot, few-shot, transfer learning and multi-tasking capabilities on both generative and discriminative language tasks. Motivated by…
Large Multimodal Models (LMMs) often face a modality representation gap during pretraining: while language embeddings remain stable, visual representations are highly sensitive to contextual noise (e.g., background clutter). To address this…
Agent systems powered by large language models (LLMs) have demonstrated impressive performance on repository-level code-generation tasks. However, for tasks such as website codebase generation, which depend heavily on visual effects and…
Chart-to-code generation demands strict visual precision and syntactic correctness from Vision-Language Models (VLMs). However, existing approaches are fundamentally constrained by data-centric limitations: despite the availability of…
Addressing the challenge of adapting pre-trained vision-language models for generating insightful explanations for visual reasoning tasks with limited annotations, we present ReVisE: a $\textbf{Re}$cursive $\textbf{Vis}$ual…
We consider the problem of ultra-low bit rate visual communication for remote vision analysis, human interactions and control in challenging scenarios with very low communication bandwidth, such as deep space exploration, battlefield…
We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. Our method leverages global context self-attention modules, joint with standard local…
Existing vision-language models (VLMs) mostly rely on vision encoders to extract visual features followed by large language models (LLMs) for visual-language tasks. However, the vision encoders set a strong inductive bias in abstracting…
Assembly code search is vital for reducing the burden on reverse engineers, allowing them to quickly identify specific functions using natural language within vast binary programs. Despite its significance, this critical task is impeded by…
Automatic perception of image quality is a challenging problem that impacts billions of Internet and social media users daily. To advance research in this field, we propose a no-reference image quality assessment (NR-IQA) method termed…
Text-to-image generation and text-guided image manipulation have received considerable attention in the field of image generation tasks. However, the mainstream evaluation methods for these tasks have difficulty in evaluating whether all…
We present VISTA (VIsual Spec-To-App Benchmark), a benchmark for evaluating the end-to-end web-app generation capabilities of LLM-based agents. Unlike prior code generation benchmarks that focus on algorithmic tasks, VISTA targets realistic…
Data visualizations are central to scientific communication, journalism, and everyday decision-making, yet they are frequently prone to errors that can distort interpretation or mislead audiences. Rule-based visualization linters can flag…
Generating longer textual sequences when conditioned on the visual information is an interesting problem to explore. The challenge here proliferate over the standard vision conditioned sentence-level generation (e.g., image or video…
In recent years, research on visual document understanding (VDU) has grown significantly, with a particular emphasis on the development of self-supervised learning methods. However, one of the significant challenges faced in this field is…
We present CV4Code, a compact and effective computer vision method for sourcecode understanding. Our method leverages the contextual and the structural information available from the code snippet by treating each snippet as a…
Visual relationship detection aims to identify objects and their relationships in images. Prior methods approach this task by adding separate relationship modules or decoders to existing object detection architectures. This separation…
Background and Context. Chat-based and inline-coding-based GenAI has already had substantial impact on the CS Education community. The recent introduction of ``vibe coding'' may further transform how students program, as it introduces a new…
Obtaining the human-like perception ability of abstracting visual concepts from concrete pixels has always been a fundamental and important target in machine learning research fields such as disentangled representation learning and scene…