相关论文: Clapper: Compact Learning and Video Representation…

In this paper, we propose a framework named OCSampler to explore a compact yet effective video representation with one short clip for efficient video recognition. Recent works prefer to formulate frame sampling as a sequential decision task…

Large language models (LLMs) increasingly rely on long-context modeling for tasks such as document understanding, code analysis, and multi-step reasoning. However, scaling context windows to the million-token level brings prohibitive…

Long videos, ranging from minutes to hours, present significant challenges for current Multi-modal Large Language Models (MLLMs) due to their complex events, diverse scenes, and long-range dependencies. Direct encoding of such videos is…

Large language models (LLMs) have demonstrated exceptional capabilities in text understanding, which has paved the way for their expansion into video LLMs (Vid-LLMs) to analyze video data. However, current Vid-LLMs struggle to…

Multimodal video summarization requires visual features that align semantically with language generation. Traditional approaches rely on CNN features trained for object classification, which represent visual concepts as discrete categories…

Implicit Neural representations (INRs) have emerged as a promising approach for video compression, and have achieved comparable performance to the state-of-the-art codecs such as H.266/VVC. However, existing INR-based methods struggle to…

Large Language Models (LLMs) have been widely used in various tasks, motivating us to develop an LLM-based assistant for videos. Instead of training from scratch, we propose a module to transform arbitrary well-trained image-based LLMs into…

Large Language Models (LLMs) have allowed recent LLM-based approaches to achieve excellent performance on long-video understanding benchmarks. We investigate how extensive world knowledge and strong reasoning skills of underlying LLMs…

Vision-language models (VLMs) are typically composed of a vision encoder, e.g. CLIP, and a language model (LM) that interprets the encoded features to solve downstream tasks. Despite remarkable progress, VLMs are subject to several…

Modern Large Language Models (LLMs) are increasingly trained to support very large context windows. We present Compactor, a training-free, query-agnostic KV compression strategy that uses approximate leverage scores to determine token…

Large vision-language contrastive models (VLCMs), such as CLIP, have become foundational, demonstrating remarkable success across a variety of downstream tasks. Despite their advantages, these models, akin to other foundational systems,…

While significant advancements have been made in compressed representations for text embeddings in large language models (LLMs), the compression of visual tokens in multi-modal LLMs (MLLMs) has remained a largely overlooked area. In this…

Large language models (LLMs) have shown promise in generating program workflows for visual tasks. However, previous approaches often rely on closed-source models, lack systematic reasoning, and struggle with long-form video question…

Large language models (LLMs) and their multimodal variants can now process visual inputs, including images of text. This raises an intriguing question: can we compress textual inputs by feeding them as images to reduce token usage while…

Multimodal large language models (MLLMs) have demonstrated remarkable potential for enhancing scene understanding in autonomous driving systems through powerful logical reasoning capabilities. However, the deployment of these models faces…

Long-form videos that span across wide temporal intervals are highly information redundant and contain multiple distinct events or entities that are often loosely related. Therefore, when performing long-form video question answering…

Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a family of open VLMs designed to jointly optimize efficiency…

Building models that comprehends videos and responds specific user instructions is a practical and challenging topic, as it requires mastery of both vision understanding and knowledge reasoning. Compared to language and image modalities,…

The rapid success of Vision Large Language Models (VLLMs) often depends on the high-resolution images with abundant visual tokens, which hinders training and deployment efficiency. Current training-free visual token compression methods…

The rapid growth of video content across domains such as surveillance, education, and social media has made efficient content understanding increasingly critical. Video summarization addresses this challenge by generating concise yet…