相关论文: ReWind: Understanding Long Videos with Instructed …

Long-form video understanding remains challenging for Vision-Language Models (VLMs) due to the inherent tension between computational constraints and the need to capture information distributed across thousands of frames. Existing…

While autoregressive Large Vision-Language Models (LVLMs) demonstrate remarkable proficiency in multimodal tasks, they face a "Visual Signal Dilution" phenomenon, where the accumulation of textual history expands the attention partition…

Recent advances in AI-generated content (AIGC) have led to the emergence of powerful text-to-video generation models. Despite these successes, evaluating the quality of AIGC-generated videos remains challenging due to limited…

Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…

Recent advances in video large language models have demonstrated strong capabilities in understanding short clips. However, scaling them to hours- or days-long videos remains highly challenging due to limited context capacity and the loss…

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…

In recent years, online lecture videos have become an increasingly popular resource for acquiring new knowledge. Systems capable of effectively understanding/indexing lecture videos are thus highly desirable, enabling downstream tasks like…

While Large Vision-Language Models (LVLMs) have achieved substantial progress in video understanding, their application to long video reasoning is hindered by uniform frame sampling and static textual reasoning, which are inefficient and…

Existing MLLMs encounter significant challenges in modeling the temporal context within long videos. Currently, mainstream Agent-based methods use external tools to assist a single MLLM in answering long video questions. Despite such…

We introduce a full-stack framework that scales up reasoning in vision-language models (VLMs) to long videos, leveraging reinforcement learning. We address the unique challenges of long video reasoning by integrating three critical…

We present Recurrent Video Masked-Autoencoders (RVM): a novel approach to video representation learning that leverages recurrent computation to model the temporal structure of video data. RVM couples an asymmetric masking objective with a…

Accurately estimating task progress is critical for embodied agents to plan and execute long-horizon, multi-step tasks. Despite promising advances, existing Vision-Language Models (VLMs) based methods primarily leverage their video…

We explore how reconciling several foundation models (large language models and vision-language models) with a novel unified memory mechanism could tackle the challenging video understanding problem, especially capturing the long-term…

The rapid growth of video content demands efficient and precise retrieval systems. While vision-language models (VLMs) excel in representation learning, they often struggle with adaptive, time-sensitive video retrieval. This paper…

Multi-modal Large language models (MLLMs) show remarkable ability in video understanding. Nevertheless, understanding long videos remains challenging as the models can only process a finite number of frames in a single inference,…

The challenge of long video understanding lies in its high computational complexity and prohibitive memory cost, since the memory and computation required by transformer-based LLMs scale quadratically with input sequence length. We propose…

Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual…

Long video understanding requires more than large context windows. It also needs a memory mechanism that decides what visual evidence to retain, keeps it searchable over long horizons, and grounds later reasoning in recoverable observations…

In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a…

While multimodal large language models (MLLMs) have shown remarkable success across a wide range of tasks, long-form video understanding remains a significant challenge. In this study, we focus on video understanding by MLLMs. This task is…