Related papers: OTT-Vid: Optimal Transport Temporal Token Compress…
Token-based video representation has emerged as a promising approach for enabling large language models (LLMs) to interpret video content. However, existing token reduction techniques, such as pruning and merging, often disrupt essential…
Video Temporal Grounding (VTG) localizes the temporal boundaries of a query-relevant moment in long, untrimmed videos, making video-language-model (VLM) pipelines prohibitively expensive. While recent training-free visual token pruning has…
Video tokenizers are essential for latent video diffusion models, converting raw video data into spatiotemporally compressed latent spaces for efficient training. However, extending state-of-the-art video tokenizers to achieve a temporal…
Variational Autoencoder (VAE), compressing videos into latent representations, is a crucial preceding component of Latent Video Diffusion Models (LVDMs). With the same reconstruction quality, the more sufficient the VAE's compression for…
Multimodal large language models (MLLMs) have made remarkable strides, largely driven by their ability to process increasingly long and complex contexts, such as high-resolution images, extended video sequences, and lengthy audio input.…
Video-based multimodal large language models (Video-LLMs) possess significant potential for video understanding tasks. However, most Video-LLMs treat videos as a sequential set of individual frames, which results in insufficient…
Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction methods mitigate this issue, they mainly target single-turn…
Video large language models (Video-LLMs) have demonstrated strong capabilities in video understanding tasks. However, their practical deployment is still hindered by the inefficiency introduced by processing massive amounts of visual…
Video temporal grounding aims to identify video segments within untrimmed videos that are most relevant to a given natural language query. Existing video temporal localization models rely on specific datasets for training and have high data…
Vision-language models (VLMs) have transformed multimodal reasoning, but feeding hundreds of visual patch tokens into LLMs incurs quadratic computational costs, straining memory and context windows. Traditional approaches face a trade-off:…
Video large multimodal models increasingly face a scalability bottleneck: long videos produce excessively long visual-token sequences, which sharply increase memory and latency during inference. While existing compression methods are…
Visual text compression (VTC) promises efficient long-context processing by rendering text into an image and re-encoding it with a vision-language model, often producing $3$--$20\times$ fewer decoder tokens than subword tokenization. Yet…
The rapid progress of large language models (LLMs) has laid the foundation for multimodal models. However, visual language models (VLMs) still face heavy computational costs when extended from images to videos due to high frame rates and…
Omni-modal large language models (om-LLMs) achieve unified audio-visual understanding by encoding video and audio into temporally aligned token sequences interleaved at the window level. However, processing these dense non-textual tokens…
In this work, we present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. Current VLMs, while proficient in tasks like image captioning and visual…
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 Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically…
Omni-modal Large Language Models (Omni-LLMs) have demonstrated strong capabilities in audio-video understanding tasks. However, their reliance on long multimodal token sequences leads to substantial computational overhead. Despite this…
Vision language models (VLMs) demonstrate strong capabilities in jointly processing visual and textual data. However, they often incur substantial computational overhead due to redundant visual information, particularly in long-form video…
Vision-language models (VLMs) have achieved remarkable multimodal understanding and reasoning capabilities, yet remain computationally expensive due to dense visual tokenization. Existing efficiency approaches either merge redundant visual…