Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
- URL: http://arxiv.org/abs/2308.04152v4
- Date: Sat, 25 May 2024 14:56:21 GMT
- Title: Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
- Authors: Juncheng Li, Kaihang Pan, Zhiqi Ge, Minghe Gao, Wei Ji, Wenqiao Zhang, Tat-Seng Chua, Siliang Tang, Hanwang Zhang, Yueting Zhuang,
- Abstract summary: We introduce a generic and lightweight Visual Prompt Generator Complete module (VPG-C)
VPG-C infers and completes the missing details essential for comprehending demonstrative instructions.
We build DEMON, a comprehensive benchmark for demonstrative instruction understanding.
- Score: 126.3136109870403
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have been utilizing Visual Prompt Generators (VPGs) to convert visual features into tokens that LLMs can recognize. This is achieved by training the VPGs on millions of image-caption pairs, where the VPG-generated tokens of images are fed into a frozen LLM to generate the corresponding captions. However, this image-captioning based training objective inherently biases the VPG to concentrate solely on the primary visual contents sufficient for caption generation, often neglecting other visual details. This shortcoming results in MLLMs' underperformance in comprehending demonstrative instructions consisting of multiple, interleaved, and multimodal instructions that demonstrate the required context to complete a task. To address this issue, we introduce a generic and lightweight Visual Prompt Generator Complete module (VPG-C), which can infer and complete the missing details essential for comprehending demonstrative instructions. Further, we propose a synthetic discriminative training strategy to fine-tune VPG-C, eliminating the need for supervised demonstrative instructions. As for evaluation, we build DEMON, a comprehensive benchmark for demonstrative instruction understanding. Synthetically trained with the proposed strategy, VPG-C achieves significantly stronger zero-shot performance across all tasks of DEMON. Further evaluation on the MME and OwlEval benchmarks also demonstrate the superiority of VPG-C. Our benchmark, code, and pre-trained models are available at https://github.com/DCDmllm/Cheetah.
Related papers
- HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding [91.0552157725366]
This paper presents a novel high-performance monolithic VLM named HoVLE.
It converts visual and textual inputs into a shared space, allowing LLMs to process images in the same way as texts.
Our experiments show that HoVLE achieves performance close to leading compositional models on various benchmarks.
arXiv Detail & Related papers (2024-12-20T18:59:59Z) - Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage [50.84150600032693]
Multimodal large language models (MLLMs) excel at generating highly detailed captions but often produce hallucinations.
We propose a multiagent approach that leverages LLM-MLLM collaboration to correct given captions.
Our proposed method significantly enhances the factual accuracy of captions, even improving those generated by GPT-4V.
arXiv Detail & Related papers (2024-12-20T01:37:22Z) - TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models [52.590072198551944]
Recent advances in multimodal Large Language Models (LLMs) have shown great success in understanding multi-modal contents.
For video understanding tasks, training-based video LLMs are difficult to build due to the scarcity of high-quality, curated video-text paired data.
In this work, we explore the limitations of the existing compression strategies for building a training-free video LLM.
arXiv Detail & Related papers (2024-11-17T13:08:29Z) - PIP-MM: Pre-Integrating Prompt Information into Visual Encoding via Existing MLLM Structures [5.513631883813244]
We propose a framework that textbfPre-textbfIntegratestextbfPrompt information into the visual encoding process using existingmodules of MLLMs.
Our model maintains excellent generation even when half of the visual tokens are reduced.
arXiv Detail & Related papers (2024-10-30T15:05:17Z) - Instruction Tuning-free Visual Token Complement for Multimodal LLMs [51.138806401996696]
multimodal large language models (MLLMs) have promised an elegant bridge between vision and language.
We propose a Visual Token Complement framework (VTC) that helps MLLMs regain the missing visual features.
Our VTC integrates text-to-image generation as a guide to identifying the text-irrelevant features, and a visual selector is then developed to generate complementary visual tokens.
arXiv Detail & Related papers (2024-08-09T12:13:01Z) - Aligned with LLM: a new multi-modal training paradigm for encoding fMRI
activity in visual cortex [4.57590454144072]
Recently, there has been a surge in the popularity of pre trained large language models (LLMs)
This paper proposes a new multi-modal training paradigm, aligning with LLM, encoding fMRI activity in visual cortex.
arXiv Detail & Related papers (2024-01-08T12:30:23Z) - Context-Aware Prompt Tuning for Vision-Language Model with
Dual-Alignment [15.180715595425864]
We introduce a novel method to improve the prompt learning of vision-language models by incorporating pre-trained large language models (LLMs)
With DuAl-PT, we propose to learn more context-aware prompts, benefiting from both explicit and implicit context modeling.
Empirically, DuAl-PT achieves superior performance on 11 downstream datasets on few-shot recognition and base-to-new generalization.
arXiv Detail & Related papers (2023-09-08T06:51:15Z) - Incorporating Structured Representations into Pretrained Vision &
Language Models Using Scene Graphs [79.64891686479213]
We show that it is possible to improve vision and language models (VLMs) when learning from scene graphs (SGs)
For the visual side, we incorporate a special "SG Component" in the image transformer trained to predict SG information, while for the textual side, we utilize SGs to generate fine-grained captions.
Our method improves the performance of several popular VLMs on multiple datasets with only a mild degradation in ZS capabilities.
arXiv Detail & Related papers (2023-05-10T17:52:26Z)
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.