paper-with-me

홈 › Papers

xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs

2024-10-21 · Michael S. Ryoo, Honglu Zhou, Shrikant Kendre, Can Qin, Le Xue, Manli Shu, Silvio Savarese, ran Xu, Caiming Xiong, Juan Carlos Niebles

We present xGen-MM-Vid (BLIP-3-Video): a multimodal language model for videos, particularly designed to efficiently capture temporal information over multiple frames. BLIP-3-Video takes advantage of the 'temporal encoder' in addition to the conventional visual tokenizer, which maps a sequence of tokens over multiple frames into a compact set of visual tokens. This enables BLIP3-Video to use much fewer visual tokens than its competing models (e.g., 32 vs. 4608 tokens). We explore different types of temporal encoders, including learnable spatio-temporal pooling as well as sequential models like Token Turing Machines. We experimentally confirm that BLIP-3-Video obtains video question-answering accuracies comparable to much larger state-of-the-art models (e.g., 34B), while being much smaller (i.e., 4B) and more efficient by using fewer visual tokens. The project website is at https://www.salesforceairesearch.com/opensource/xGen-MM-Vid/index.html

📄 PDF Abstract BibTeX arXiv:2410.16267

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingQuestion AnsweringVideo Question Answering

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

xGen-MM (BLIP-3): A Family of Open Large Multimodal Models

2024-08-16 · Le Xue, Manli Shu, Anas Awadalla, Jun Wang 외

This report introduces xGen-MM (also known as BLIP-3), a framework for developing Large Multimodal Models (LMMs). The framework comprises meticulously curated datasets, a training recipe, model architectures, and a resul…

In-Context Learning

xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations

2024-08-22 · Can Qin, Congying Xia, Krithika Ramakrishnan, Michael Ryoo 외

We present xGen-VideoSyn-1, a text-to-video (T2V) generation model capable of producing realistic scenes from textual descriptions. Building on recent advancements, such as OpenAI's Sora, we explore the latent diffusion …

Dense CaptioningMotion EstimationText DetectionVideo Generation

xGen-small Technical Report

2025-05-10 · Erik Nijkamp, Bo Pang, Egor Pakhomov, Akash Gokul 외

We introduce xGen-small, a family of 4B and 9B Transformer decoder models optimized for long-context applications. Our vertically integrated pipeline unites domain-balanced, frequency-aware data curation; multi-stage pre…

DecoderMath

XGen-7B Technical Report

2023-09-07 · Erik Nijkamp, Tian Xie, Hiroaki Hayashi, Bo Pang 외

Large Language Models (LLMs) have become ubiquitous across various domains, transforming the way we interact with information and conduct research. However, most high-performing LLMs remain confined behind proprietary wa…

2k8k

Portable-CELLxGENE: standalone executables of CELLxGENE for easy installation

2024-08-07 · George T. Hall

Biologists who want to analyse their single-cell transcriptomics dataset must install and use specialist software via the command line. This is often impractical for non-bioinformaticians. Whilst the popular CELLxGENE so…