Related papers: SlowFast-LLaVA: A Strong Training-Free Baseline fo…
Recent advancements in large vision-language models (LVLMs), such as GPT4-V and LLaVA, have been substantial. LLaVA's modular architecture, in particular, offers a blend of simplicity and efficiency. Recent works mainly focus on introducing…
Multimodal Large Language Models (MLLMs) have shown promising progress in understanding and analyzing video content. However, processing long videos remains a significant challenge constrained by LLM's context size. To address this…
Recent advances in video-large language models (Video-LLMs) have led to significant progress in video understanding. Current preference optimization methods often rely on proprietary APIs or human-annotated captions to generate preference…
In the video-language domain, recent works in leveraging zero-shot Large Language Model-based reasoning for video understanding have become competitive challengers to previous end-to-end models. However, long video understanding presents…
The machine learning community has witnessed impressive advancements since large language models (LLMs) first appeared. Yet, their massive memory consumption has become a significant roadblock to large-scale training. For instance, a 7B…
Current video-language models struggle with long-video understanding due to limited context lengths and reliance on sparse frame subsampling, often leading to information loss. This paper introduces $\infty$-Video, which can process…
The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods either compress visual embeddings or apply sparse attention…
Video anomaly detection (VAD) aims to temporally locate abnormal events in a video. Existing works mostly rely on training deep models to learn the distribution of normality with either video-level supervision, one-class supervision, or in…
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…
Vision-Language-Action (VLA) models have made substantial progress by leveraging the robust capabilities of Visual Language Models (VLMs). However, VLMs' significant parameter size and autoregressive (AR) decoding nature impose considerable…
Multimodal large language models (MLLMs) have demonstrated remarkable abilities in comprehending visual input alongside text input. Typically, these models are trained on extensive data sourced from the internet, which are sufficient for…
Multi-modal large language models (MLLMs) have made significant strides in various visual understanding tasks. However, the majority of these models are constrained to process low-resolution images, which limits their effectiveness in…
Recent methods have made notable progress in accelerating Large Vision-Language Models (LVLMs) by exploiting the inherent redundancy in visual inputs. Most existing approaches, however, focus narrowly on reducing image tokens before or…
Current Multimodal Large Language Models (MLLMs) often perform poorly in long video understanding, primarily due to resource limitations that prevent them from processing all video frames and their associated information. Efficiently…
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…
Multimodal large language models (MLLMs) enhance their perceptual capabilities by integrating visual and textual information. However, processing the massive number of visual tokens incurs a significant computational cost. Existing analysis…
Recent Large Language Models have been enhanced with vision capabilities, enabling them to comprehend images, videos, and interleaved vision-language content. However, the learning methods of these large multimodal models typically treat…
Recent advances in video-based multimodal large language models (Video-LLMs) have significantly improved video understanding by processing videos as sequences of image frames. However, many existing methods treat frames independently in the…
Conversation agents powered by large language models are revolutionizing the way we interact with visual data. Recently, large vision-language models (LVLMs) have been extensively studied for both images and videos. However, these studies…
In this paper, we present the VideoLLaMA 2, a set of Video Large Language Models (Video-LLMs) designed to enhance spatial-temporal modeling and audio understanding in video and audio-oriented tasks. Building upon its predecessor, VideoLLaMA…