Related papers: SugarCrepe: Fixing Hackable Benchmarks for Vision-…

Obtaining object response maps is one important step to achieve weakly-supervised semantic segmentation using image-level labels. However, existing methods rely on the classification task, which could result in a response map only attending…

Recent video question answering benchmarks indicate that state-of-the-art models struggle to answer compositional questions. However, it remains unclear which types of compositional reasoning cause models to mispredict. Furthermore, it is…

Symbolic music generation has seen rapid progress with artificial neural networks, yet remains underexplored in the biologically plausible domain of spiking neural networks (SNNs), where both standardized benchmarks and comprehensive…

Subtle semantic differences in retinal image and text data present great challenges for pre-training visual-language models. Moreover, false negative samples, i.e., image-text pairs having the same semantics but incorrectly regarded as…

Watermarking is an effective way to trace model-generated content. Current watermark methods cannot resist forgery attacks, such as a deceptive claim that the model-generated content is a response to a fabricated prompt. None of them can be…

This paper introduces MEBench, a novel benchmark for evaluating mutual exclusivity (ME) bias, a cognitive phenomenon observed in children during word learning. Unlike traditional ME tasks, MEBench further incorporates spatial reasoning to…

Vision-Language Models (VLMs) excel at photorealistic generation, yet often struggle to represent abstract meaning such as idiomatic interpretations of noun compounds. To study whether high visual fidelity interferes with idiomatic…

Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these…

Text classification models, especially neural networks based models, have reached very high accuracy on many popular benchmark datasets. Yet, such models when deployed in real world applications, tend to perform badly. The primary reason is…

The increasing realism of AI-generated images has raised serious concerns about misinformation and privacy violations, highlighting the urgent need for accurate and interpretable detection methods. While existing approaches have made…

Prior benchmarks have analyzed models' answers to questions about videos in order to measure visual compositional reasoning. Action Genome Question Answering (AGQA) is one such benchmark. AGQA provides a training/test split with balanced…

Evaluating text-to-image generative models remains a challenge, despite the remarkable progress being made in their overall performances. While existing metrics like CLIPScore work for coarse evaluations, they lack the sensitivity to…

We introduce CompareBench, a benchmark for evaluating visual comparison reasoning in vision-language models (VLMs), a fundamental yet understudied skill. CompareBench consists of 1000 QA pairs across four tasks: quantity (600), temporal…

The mismatch between close-set training and open-set testing usually leads to significant performance degradation for speaker verification task. For existing loss functions, metric learning-based objectives depend strongly on searching…

Vision-language models (VLMs) excel at image-text retrieval yet persistently fail at compositional reasoning, distinguishing captions that share the same words but differ in relational structure. We present, a unified evaluation and…

Visual language models (VLMs) have the potential to transform medical workflows. However, the deployment is limited by sycophancy. Despite this serious threat to patient safety, a systematic benchmark remains lacking. This paper addresses…

Reasoning has emerged as the next major frontier for language models (LMs), with rapid advances from both academic and industrial labs. However, this progress often outpaces methodological rigor, with many evaluations relying on…

As Vision-Language Models (VLMs) are increasingly deployed in split-DNN configurations--with visual encoders (e.g., ResNet, ViT) operating on user devices and sending intermediate features to the cloud--there is a growing privacy risk from…

The visual classification performance of vision-language models such as CLIP has been shown to benefit from additional semantic knowledge from large language models (LLMs) such as GPT-3. In particular, averaging over LLM-generated class…

Contrastive vision-language models continue to be the dominant approach for image and text retrieval. Contrastive Language-Image Pre-training (CLIP) trains two neural networks in contrastive manner to align their image and text embeddings…