From Image to Video, what do we need in multimodal LLMs?

• URL: http://arxiv.org/abs/2404.11865v2
• Date: Fri, 16 May 2025 06:50:09 GMT
• Title: From Image to Video, what do we need in multimodal LLMs?
• Authors: Suyuan Huang, Haoxin Zhang, Linqing Zhong, Honggu Chen, Yan Gao, Yao Hu, Zengchang Qin,
• Abstract summary: This paper introduces RED-VILLM, a Resource-Efficient Development pipeline which builds robust Video LLMs.<n>We devise a temporal adaptation plug-and-play structure, endowing the backbone Image LLM with the capability to grasp temporal information.<n>Our approach highlights the potential for a more cost-effective and scalable advancement in multimodal models.
• Score: 17.847011311716077
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Covering from Image LLMs to the more complex Video LLMs, the Multimodal Large Language Models (MLLMs) have demonstrated profound capabilities in comprehending cross-modal information as numerous studies have illustrated. Previous methods delve into designing comprehensive Video LLMs through integrating video foundation models with primitive LLMs. Despite its effectiveness, such paradigm renders Video LLM's structure verbose and typically requires substantial video data for pre-training. Crucially, it neglects leveraging the foundational contributions of ready-made Image LLMs. In this paper, we introduce RED-VILLM, a Resource-Efficient Development pipeline which builds robust Video LLMs through leveraging the prior knowledge of Image LLMs. Specifically, since a video is naturally a combination of images along the temporal dimension, we devise a temporal adaptation plug-and-play structure, endowing the backbone Image LLM with the capability to grasp temporal information. Moreover, through applying this pipeline, we achieve the first Video LLM within the Chinese-speaking community. Extensive experiments demonstrate that Video LLMs developed through our approach surpass conventional Video LLMs, requiring minimal instructional data and training resources. Our approach highlights the potential for a more cost-effective and scalable advancement in multimodal models.

Related papers

• How Important are Videos for Training Video LLMs? [55.965474658745315]
  We present findings indicating Video LLMs are more capable of temporal reasoning after image-only training than one would assume.<n>We introduce a simple finetuning scheme involving sequences of annotated images and questions targeting temporal capabilities.<n>This suggests suboptimal utilization of rich temporal features found in real video by current models.
  arXiv  Detail & Related papers  (2025-06-07T21:32:19Z)
• InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling [56.130911402831906]
  This paper aims to improve the performance of video large language models (LM) via long and rich context (LRC) modeling. We develop a new version of InternVideo2.5 with focus on enhancing the original MLLMs' ability to perceive fine-grained details in videos. Experimental results demonstrate this unique designML LRC greatly improves the results of video MLLM in mainstream understanding benchmarks.
  arXiv  Detail & Related papers  (2025-01-21T18:59:00Z)
• AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning [19.68349294206012]
  We propose a training-free adaptive inference method for multi-modal LLMs. With a minimalist design, our method can be applied to both video and image LLMs. Under a similar computational cost, our method outperforms the state-of-the-art methods in long video understanding.
  arXiv  Detail & Related papers  (2024-12-04T11:47:57Z)
• LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation [60.02145113467427]
  This work introduces a fine-tuning approach that integrates large language models with the pretrained CLIP visual encoder. To address the challenge of LLMs' autoregressive nature, we propose a caption-to-caption contrastive learning framework. Our method achieves substantial performance gains on various downstream tasks.
  arXiv  Detail & Related papers  (2024-11-07T18:59:16Z)
• NoteLLM-2: Multimodal Large Representation Models for Recommendation [60.17448025069594]
  We investigate the potential of Large Language Models to enhance multimodal representation in multimodal item-to-item recommendations. One feasible method is the transfer of Multimodal Large Language Models (MLLMs) for representation tasks. We propose a novel training framework, NoteLLM-2, specifically designed for multimodal representation.
  arXiv  Detail & Related papers  (2024-05-27T03:24:01Z)
• ST-LLM: Large Language Models Are Effective Temporal Learners [58.79456373423189]
  Large Language Models (LLMs) have showcased impressive capabilities in text comprehension and generation. How to effectively encode and understand videos in video-based dialogue systems remains to be solved. We propose ST-LLM, an effective video-LLM baseline with spatial-temporal sequence modeling inside LLM.
  arXiv  Detail & Related papers  (2024-03-30T10:11:26Z)
• Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context Fusion [70.9767518332692]
  Multimodal Large Language Models (MLLMs) that incorporate LLMs with pre-trained vision models have recently demonstrated impressive performance across diverse vision-language tasks. However, they fall short to comprehend context involving multiple images. We propose a two phase paradigm, browse-and-concentrate, to enable in-depth multimodal context fusion.
  arXiv  Detail & Related papers  (2024-02-19T14:59:07Z)
• Video Understanding with Large Language Models: A Survey [97.29126722004949]
  Given the remarkable capabilities of large language models (LLMs) in language and multimodal tasks, this survey provides a detailed overview of recent advancements in video understanding. The emergent capabilities Vid-LLMs are surprisingly advanced, particularly their ability for open-ended multi-granularity reasoning. This survey presents a comprehensive study of the tasks, datasets, benchmarks, and evaluation methodologies for Vid-LLMs.
  arXiv  Detail & Related papers  (2023-12-29T01:56:17Z)
• Towards Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs [72.49064988035126]
  We propose an approach called MKS2, aimed at enhancing multimodal large language models (MLLMs) Specifically, we introduce the Modular Visual Memory, a component integrated into the internal blocks of LLMs, designed to store open-world visual information efficiently. Our experiments demonstrate that MKS2 substantially augments the reasoning capabilities of LLMs in contexts necessitating physical or commonsense knowledge.
  arXiv  Detail & Related papers  (2023-11-27T12:29:20Z)
• VideoLLM: Modeling Video Sequence with Large Language Models [70.32832021713864]
  Existing video understanding models are often task-specific and lack a comprehensive capability of handling diverse tasks. We propose a novel framework called VideoLLM that leverages the sequence reasoning capabilities of pre-trained LLMs. VideoLLM incorporates a carefully designed Modality and Semantic Translator, which convert inputs from various modalities into a unified token sequence.
  arXiv  Detail & Related papers  (2023-05-22T17:51:22Z)

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.