Related papers: Bisecle: Binding and Separation in Continual Learn…

Recent Video-Language Models (VLMs) achieve promising results on long-video understanding, but their performance still lags behind that achieved on tasks involving images or short videos. This has led to great interest in improving the long…

The advent of Large Multimodal Models (LMMs) has significantly enhanced Large Language Models (LLMs) to process and interpret diverse data modalities (e.g., image and video). However, as input complexity increases, particularly with long…

The rapid development of Large Language Models (LLMs) has catalyzed significant advancements in video understanding technologies. This survey provides a comprehensive analysis of benchmarks and evaluation methodologies specifically designed…

With the recent success of the pre-training technique for NLP and image-linguistic tasks, some video-linguistic pre-training works are gradually developed to improve video-text related downstream tasks. However, most of the existing…

Large Vision-Language Models (LVLMs) have demonstrated strong multimodal reasoning capabilities on long and complex documents. However, their high memory footprint makes them impractical for deployment on resource-constrained edge devices.…

The integration of Large Language Models (LLMs) with visual encoders has recently shown promising performance in visual understanding tasks, leveraging their inherent capability to comprehend and generate human-like text for visual…

Speculative decoding is a widely adopted technique for accelerating inference in large language models (LLMs), yet its application to vision-language models (VLMs) remains underexplored, with existing methods achieving only modest speedups…

In this paper, we propose VideoLLaMA3, a more advanced multimodal foundation model for image and video understanding. The core design philosophy of VideoLLaMA3 is vision-centric. The meaning of "vision-centric" is two-fold: the…

Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors plasticity over the stability needed to retain prior knowledge. While existing approaches attempt to…

Visual Question Answering (VQA) is a multi-discipline research task. To produce the right answer, it requires an understanding of the visual content of images, the natural language questions, as well as commonsense reasoning over the…

Recent efforts in video reasoning segmentation (VRS) integrate large language models (LLMs) with perception models to localize and track objects via textual instructions, achieving barely satisfactory results in simple scenarios. However,…

Recent advances in Large Multi-modal Models (LMMs) have demonstrated their remarkable success as general-purpose multi-modal assistants, with particular focuses on holistic image- and video-language understanding. Conversely, less attention…

Video Large Language Models (Video-LLMs) have shown strong video understanding, yet their application to long-form videos remains constrained by limited context windows. A common workaround is to compress long videos into a handful of…

Vision-Language Models (VLMs) have demonstrated strong capabilities in multimodal understanding and generation tasks. However, their application to long video understanding remains hindered by the quadratic complexity of standard attention…

As multimodal large language models (MLLMs) advance, their large-scale architectures pose challenges for deployment in resource-constrained environments. In the age of large models, where energy efficiency, computational scalability and…

Video language models (VideoLMs) have made significant progress in multimodal understanding. However, temporal understanding, which involves identifying event order, duration, and relationships across time, still remains a core challenge.…

Recently, Large Vision-Language Models (LVLMs) have made significant strides across diverse multimodal tasks and benchmarks. This paper reveals a largely under-explored problem from existing video-involved LVLMs - language bias, where…

Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful…

Vision-Language Models (VLMs) have shown remarkable capabilities in a large number of downstream tasks. Nonetheless, compositional image understanding remains a rather difficult task due to the object bias present in training data. In this…

Reference-guided video editing takes a source video, a text instruction, and a reference image as inputs, requiring the model to faithfully apply the instructed edits while preserving original motion and unedited content. Existing methods…