Related papers: ViLCo-Bench: VIdeo Language COntinual learning Ben…

Counting in long videos remains a fundamental yet underexplored challenge in computer vision. Real-world recordings often span tens of minutes or longer and contain sparse, diverse events, making long-range temporal reasoning particularly…

Vision Language Models (VLMs) achieved rapid progress in the recent years. However, despite their growth, VLMs development is heavily grounded on English, leading to two main limitations: (i) the lack of multilingual and multimodal datasets…

Temporal Awareness, the ability to reason dynamically based on the timestamp when a question is raised, is the key distinction between offline and online video LLMs. Unlike offline models, which rely on complete videos for static, post hoc…

While vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, their mastery in a few languages like English restricts their applicability in broader communities. To this end, there is an increasing…

Continual learning in real-world scenarios is a major challenge. A general continual learning model should have a constant memory size and no predefined task boundaries, as is the case in semi-supervised Video Object Segmentation (VOS),…

This work investigates a fundamental question: Do Video-Language Models (VidLMs) robustly account for video content, temporal sequence, and motion? Our investigation shows that, surprisingly, they often do not. We introduce REVEAL{}, a…

Large Vision-Language Models (LVLMs) have demonstrated outstanding performance across various multimodal tasks. However, they suffer from a problem known as language prior, where responses are generated based solely on textual patterns…

Recent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We introduce V-ReasonBench, a benchmark designed to assess video…

Vision-language models (VLMs) have demonstrated remarkable progress in multimodal reasoning. However, existing benchmarks remain limited in terms of high-quality, human-verified examples. Many current datasets rely on synthetically…

Vision-language navigation (VLN) is a critical domain within embedded intelligence, requiring agents to navigate 3D environments based on natural language instructions. Traditional VLN research has focused on improving environmental…

Comparing vision language models on videos is particularly complex, as the performances is jointly determined by the model's visual representation capacity and the frame-sampling strategy used to construct the input. Current video…

Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content, but significant challenges persist in tasks requiring cross-viewpoint understanding and spatial reasoning. We…

We introduce a new benchmark designed to advance the development of general-purpose, large-scale vision-language models for remote sensing images. Although several vision-language datasets in remote sensing have been proposed to pursue this…

Vision-language models (VLMs) have made significant progress in recent visual-question-answering (VQA) benchmarks that evaluate complex visio-linguistic reasoning. However, are these models truly effective? In this work, we show that VLMs…

Vision-Language Models (VLMs) have demonstrated remarkable capabilities in general video understanding, yet they often struggle with the fine-grained comprehension crucial for real-world applications requiring nuanced interpretation of…

Multimodal Large Language Models (MLLMs) have shown remarkable capabilities in video content understanding but still struggle with fine-grained motion comprehension. To comprehensively assess the motion understanding ability of existing…

Modeling discourse -- the linguistic phenomena that go beyond individual sentences, is a fundamental yet challenging aspect of natural language processing (NLP). However, existing evaluation benchmarks primarily focus on the evaluation of…

The sequential structure of videos poses a challenge to the ability of multimodal large language models (MLLMs) to locate multi-frame evidence and conduct multimodal reasoning. However, existing video benchmarks mainly focus on…

Class-incremental learning requires a learning system to continually learn knowledge of new classes and meanwhile try to preserve previously learned knowledge of old classes. As current state-of-the-art methods based on Vision-Language…

In recent years, image editing models have made significant progress, enabling users to manipulate visual content in a flexible and interactive manner through natural language instructions. However, an important yet underexplored research…