Related papers: TextEditBench: Evaluating Reasoning-aware Text Edi…

Evaluating code generation models for 3D spatial reasoning requires executing generated code in realistic environments and assessing outputs beyond surface-level correctness. We introduce a platform VoxelCode, for analyzing code generation…

With the rapid advancement of Multimodal Large Language Models (MLLMs), they have demonstrated exceptional capabilities across a variety of vision-language tasks. However, current evaluation benchmarks predominantly focus on objective…

Steering or intervening on model representations at inference time to correct predictions is essential for AI interpretability and safety, yet existing evaluation protocols are limited to ambiguous language modeling tasks. To address this…

Recent advances in large language models (LLMs) and vision-language models (LVLMs) have shown promise across many tasks, yet their scientific reasoning capabilities remain untested, particularly in multimodal settings. We present…

As Vision-Language Models (VLMs) increasingly gain traction in medical applications, clinicians are progressively expecting AI systems not only to generate textual diagnoses but also to produce corresponding medical images that integrate…

The correspondence between input text and the generated image exhibits opacity, wherein minor textual modifications can induce substantial deviations in the generated image. While, text embedding, as the pivotal intermediary between text…

The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control…

Large Language Models have demonstrated remarkable reasoning capability in complex textual tasks. However, multimodal reasoning, which requires integrating visual and textual information, remains a significant challenge. Existing…

Text-to-image (T2I) models have advanced considerably in generating high-quality images from textual descriptions. However, their ability to associate colors with concepts remains largely constrained to explicit color names or codes, while…

Recent methods in text-to-3D leverage powerful pretrained diffusion models to optimize NeRF. Notably, these methods are able to produce high-quality 3D scenes without training on 3D data. Due to the open-ended nature of the task, most…

Multimodal Large Language Models have advanced visual reasoning, yet a purely textual chain of thought remains a bottleneck for questions that require fine-grained focus or view transformations. The ''think with images'' paradigm narrows…

Text-to-image models often struggle to generate images that precisely match textual prompts. Prior research has extensively studied the evaluation of image-text alignment in text-to-image generation. However, existing evaluations primarily…

Recent advancements in image editing have utilized large-scale multimodal models to enable intuitive, natural instruction-driven interactions. However, conventional methods still face significant challenges, particularly in spatial…

Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing benchmarks predominantly focus on pure-text queries. In real-world scenarios, language also…

Building on recent advances in language-based reasoning models, we explore multimodal reasoning that integrates vision and text. Existing multimodal benchmarks primarily test visual extraction combined with text-based reasoning, lacking…

Multimodal Large Language Models (MLLMs) are increasingly applied in real-world scenarios where user-provided images are often imperfect, requiring active image manipulations such as cropping, editing, or enhancement to uncover salient…

With collective endeavors, multimodal large language models (MLLMs) are undergoing a flourishing development. However, their performances on image aesthetics perception remain indeterminate, which is highly desired in real-world…

Humans naturally communicate through abstract concepts like "mood". However, current image editing benchmarks focus primarily on explicit, literal commands, leaving abstract instructions largely underexplored. In this work, we first…

Significant progress has been made in the field of Instruction-based Image Editing (IIE). However, evaluating these models poses a significant challenge. A crucial requirement in this field is the establishment of a comprehensive evaluation…

Recent advancements in Large Vision-Language Models (LVLMs) have significantly enhanced their ability to integrate visual and linguistic information, achieving near-human proficiency in tasks like object recognition, captioning, and visual…