LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

• URL: http://arxiv.org/abs/2311.17043v1
• Date: Tue, 28 Nov 2023 18:53:43 GMT
• Title: LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models
• Authors: Yanwei Li, Chengyao Wang, Jiaya Jia
• Abstract summary: We present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. LLaMA-VID addresses this issue by representing each frame with two distinct tokens, namely context token and content token. This dual-token strategy significantly reduces the overload of long videos while preserving critical information.
• Score: 66.40252169137447
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 question answering, face computational burdens when processing long videos due to the excessive visual tokens. LLaMA-VID addresses this issue by representing each frame with two distinct tokens, namely context token and content token. The context token encodes the overall image context based on user input, whereas the content token encapsulates visual cues in each frame. This dual-token strategy significantly reduces the overload of long videos while preserving critical information. Generally, LLaMA-VID empowers existing frameworks to support hour-long videos and pushes their upper limit with an extra context token. It is proved to surpass previous methods on most of video- or image-based benchmarks. Code is available https://github.com/dvlab-research/LLaMA-VID}{https://github.com/dvlab-research/LLaMA-VID

Related papers

• Long Context Transfer from Language to Vision [74.78422371545716]
  Video sequences offer valuable temporal information, but existing large multimodal models (LMMs) fall short in understanding extremely long videos. In this paper, we approach this problem from the perspective of the language model. By simply extrapolating the context length of the language backbone, we enable LMMs to comprehend orders of magnitude more visual tokens without any video training.
  arXiv  Detail & Related papers  (2024-06-24T17:58:06Z)
• Auto-Encoding Morph-Tokens for Multimodal LLM [151.2618346912529]
  We propose encoding images into morph-tokens to serve a dual purpose: for comprehension, they act as visual prompts instructing MLLM to generate texts. Experiments show that morph-tokens can achieve a new SOTA for multimodal comprehension and generation simultaneously.
  arXiv  Detail & Related papers  (2024-05-03T08:43:06Z)
• Vista-LLaMA: Reliable Video Narrator via Equal Distance to Visual Tokens [70.80127538938093]
  Vista-LLaMA is a novel framework that maintains the consistent distance between all visual tokens and any language tokens. We present a sequential visual projector that projects the current video frame into tokens of language space with the assistance of the previous frame.
  arXiv  Detail & Related papers  (2023-12-12T09:47:59Z)
• Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation [122.63617171522316]
  Large Language Models (LLMs) are the dominant models for generative tasks in language. We introduce MAGVIT-v2, a video tokenizer designed to generate concise and expressive tokens for both videos and images.
  arXiv  Detail & Related papers  (2023-10-09T14:10:29Z)
• Leveraging per Image-Token Consistency for Vision-Language Pre-training [52.825150269820696]
  Cross-modal masked language modeling (CMLM) is insufficient for vision-language pre-training. We propose EPIC (lEveraging Per Image-Token Consistency for vision-language pre-training) The proposed EPIC method is easily combined with pre-training methods.
  arXiv  Detail & Related papers  (2022-11-20T12:10:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.