Related papers: A Hitchhikers Guide to Fine-Grained Face Forgery D…

Face forgery by deepfake is widely spread over the internet and has raised severe societal concerns. Recently, how to detect such forgery contents has become a hot research topic and many deepfake detection methods have been proposed. Most…

Having revolutionized natural language processing (NLP) applications, large language models (LLMs) are expanding into the realm of multimodal inputs. Owing to their ability to interpret images, multimodal LLMs (MLLMs) have been primarily…

Medical vision-language models (VLMs) and AI agents have made significant progress in learning to analyze and reason about clinical images. However, existing medical visual question answering (VQA) benchmarks collapse model capabilities…

Face forgery detection is essential in combating malicious digital face attacks. Previous methods mainly rely on prior expert knowledge to capture specific forgery clues, such as noise patterns, blending boundaries, and frequency artifacts.…

Vision-Language Models (VLMs) have achieved strong performance on standard vision-language benchmarks, yet often rely on surface-level recognition rather than deeper reasoning. We propose visual word puzzles as a challenging alternative, as…

Recent advances in image generation models have led to models that produce synthetic images that are increasingly difficult for standard AI detectors to identify, even though they often remain distinguishable by humans. To identify this…

Large language models (LLMs) often hallucinate, yet most existing fact-checking methods treat factuality evaluation as a binary classification problem, offering limited interpretability and failing to capture fine-grained error types. In…

Face anti-spoofing (FAS) is crucial for protecting facial recognition systems from presentation attacks. Previous methods approached this task as a classification problem, lacking interpretability and reasoning behind the predicted results.…

Visual reasoning refers to the task of solving questions about visual information. Current visual reasoning methods typically employ pre-trained vision-language model (VLM) strategies or deep neural network approaches. However, existing…

Despite the remarkable progress of Vision-Language Models (VLMs) in adopting "Thinking-with-Images" capabilities, accurately evaluating the authenticity of their reasoning process remains a critical challenge. Existing benchmarks mainly…

Large Vision-Language Models (LVLMs) achieve strong performance on visual question answering benchmarks, yet often rely on spurious correlations rather than genuine causal reasoning. Existing evaluations primarily assess the correctness of…

Evaluating image editing models remains challenging due to the coarse granularity and limited interpretability of traditional metrics, which often fail to capture aspects important to human perception and intent. Such metrics frequently…

Deriving inference from heterogeneous inputs (such as images, text, and audio) is an important skill for humans to perform day-to-day tasks. A similar ability is desirable for the development of advanced Artificial Intelligence (AI)…

Vision-language models (VLMs) have shown significant potential for medical tasks; however, their general-purpose nature can limit specialized diagnostic accuracy, and their large size poses substantial inference costs for real-world…

Faithfulness hallucinations in VQA occur when vision-language models produce fluent yet visually ungrounded answers, severely undermining their reliability in safety-critical applications. Existing detection methods mainly fall into two…

The human face plays a central role in social communication, necessitating the use of performant computer vision tools for human-centered applications. We propose Face-LLaVA, a multimodal large language model for face-centered, in-context…

Large language models (LLMs) have shown remarkable performance in natural language processing (NLP) tasks. To comprehend and execute diverse human instructions over image data, instruction-tuned large vision-language models (LVLMs) have…

The evaluation of text-generative vision-language models is a challenging yet crucial endeavor. By addressing the limitations of existing Visual Question Answering (VQA) benchmarks and proposing innovative evaluation methodologies, our…

Puzzles have long served as compact and revealing probes of human cognition, isolating abstraction, rule discovery, and systematic reasoning with minimal reliance on prior knowledge. Leveraging these properties, visual puzzles have recently…

Large Vision-Language Models (LVLMs) have achieved remarkable performance in many vision-language tasks, yet their capabilities in fine-grained visual understanding remain insufficiently evaluated. Existing benchmarks either contain limited…