Visual instruction tuning has become the predominant technology in eliciting the multimodal task-solving capabilities of large vision-language models (LVLMs). Despite the success, as visual instructions require images as the input, it would leave the gap in inheriting the task-solving capabilities from the backbone LLMs, and make it costly to collect a large-scale dataset. To address it, we propose ViFT, a visual instruction-free fine-tuning framework for LVLMs. In ViFT, we only require the text-only instructions and image caption data during training, to separately learn the task-solving and visual perception abilities. During inference, we extract and combine the representations of the text and image inputs, for fusing the two abilities to fulfill multimodal tasks. Experimental results demonstrate that ViFT can achieve state-of-the-art performance on several visual reasoning and visual instruction following benchmarks, with rather less training data. Our code and data will be publicly released.
Large Multimodal Models (LMMs) have made significant breakthroughs with the advancement of instruction tuning. However, while existing models can understand images and videos at a holistic level, they still struggle with instance-level understanding that requires a more nuanced comprehension and alignment. Instance-level understanding is crucial, as it focuses on the specific elements that we are most interested in. Excitingly, existing works find that the state-of-the-art LMMs exhibit strong instance understanding capabilities when provided with explicit visual cues. Motivated by this, we introduce an automated annotation pipeline assisted by GPT-4o to extract instance-level information from images and videos through explicit visual prompting for instance guidance. Building upon this pipeline, we proposed Inst-IT, a solution to enhance LMMs in Instance understanding via explicit visual prompt Instruction Tuning. Inst-IT consists of a benchmark to diagnose multimodal instance-level understanding, a large-scale instruction-tuning dataset, and a continuous instruction-tuning training paradigm to effectively enhance spatial-temporal instance understanding capabilities of existing LMMs. Experimental results show that, with the boost of Inst-IT, our models not only achieve outstanding performance on Inst-IT Bench but also demonstrate significant improvements across various generic image and video understanding benchmarks. This highlights that our dataset not only boosts instance-level understanding but also strengthens the overall capabilities of generic image and video comprehension.
Remote sensing (RS) visual grounding aims to use natural language expression to locate specific objects (in the form of the bounding box or segmentation mask) in RS images, enhancing human interaction with intelligent RS interpretation systems. Early research in this area was primarily based on horizontal bounding boxes (HBBs), but as more diverse RS datasets have become available, tasks involving oriented bounding boxes (OBBs) and segmentation masks have emerged. In practical applications, different targets require different grounding types: HBB can localize an object's position, OBB provides its orientation, and mask depicts its shape. However, existing specialized methods are typically tailored to a single type of RS visual grounding task and are hard to generalize across tasks. In contrast, large vision-language models (VLMs) exhibit powerful multi-task learning capabilities but struggle to handle dense prediction tasks like segmentation. This paper proposes GeoGround, a novel framework that unifies support for HBB, OBB, and mask RS visual grounding tasks, allowing flexible output selection. Rather than customizing the architecture of VLM, our work aims to elegantly support pixel-level visual grounding output through the Text-Mask technique. We define prompt-assisted and geometry-guided learning to enhance consistency across different signals. Experimental results show that GeoGround demonstrates strong performance across four RS visual grounding tasks, matching the performance of specialized methods on multiple benchmarks. Code available at https://github.com/zytx121/GeoGround
In the aftermath of the COVID-19 pandemic and amid accelerating climate change, emerging infectious diseases, particularly those arising from zoonotic spillover, remain a global threat. Mpox (caused by the monkeypox virus) is a notable example of a zoonotic infection that often goes undiagnosed, especially as its rash progresses through stages, complicating detection across diverse populations with different presentations. In August 2024, the WHO Director-General declared the mpox outbreak a public health emergency of international concern for a second time. Despite the deployment of deep learning techniques for detecting diseases from skin lesion images, a robust and publicly accessible foundation model for mpox diagnosis is still lacking due to the unavailability of open-source mpox skin lesion images, multimodal clinical data, and specialized training pipelines. To address this gap, we propose MpoxVLM, a vision-language model (VLM) designed to detect mpox by analyzing both skin lesion images and patient clinical information. MpoxVLM integrates the CLIP visual encoder, an enhanced Vision Transformer (ViT) classifier for skin lesions, and LLaMA-2-7B models, pre-trained and fine-tuned on visual instruction-following question-answer pairs from our newly released mpox skin lesion dataset. Our work achieves 90.38% accuracy for mpox detection, offering a promising pathway to improve early diagnostic accuracy in combating mpox.
The rapid evolution of artificial intelligence, especially in large language models (LLMs), has significantly impacted various domains, including healthcare. In chest X-ray (CXR) analysis, previous studies have employed LLMs, but with limitations: either underutilizing the multi-tasking capabilities of LLMs or lacking clinical accuracy. This paper presents M4CXR, a multi-modal LLM designed to enhance CXR interpretation. The model is trained on a visual instruction-following dataset that integrates various task-specific datasets in a conversational format. As a result, the model supports multiple tasks such as medical report generation (MRG), visual grounding, and visual question answering (VQA). M4CXR achieves state-of-the-art clinical accuracy in MRG by employing a chain-of-thought prompting strategy, in which it identifies findings in CXR images and subsequently generates corresponding reports. The model is adaptable to various MRG scenarios depending on the available inputs, such as single-image, multi-image, and multi-study contexts. In addition to MRG, M4CXR performs visual grounding at a level comparable to specialized models and also demonstrates outstanding performance in VQA. Both quantitative and qualitative assessments reveal M4CXR's versatility in MRG, visual grounding, and VQA, while consistently maintaining clinical accuracy.
Foundation Models (FMs), e.g., large language models, possess attributes of intelligence which offer promise to endow a robot with the contextual understanding necessary to navigate complex, unstructured tasks in the wild. We see three core challenges in the future of space robotics that motivate building an FM for the space robotics community: 1) Scalability of ground-in-the-loop operations; 2) Generalizing prior knowledge to novel environments; and 3) Multi-modality in tasks and sensor data. As a first-step towards a space foundation model, we programmatically augment three extraterrestrial databases with fine-grained language annotations inspired by the sensory reasoning necessary to e.g., identify a site of scientific interest on Mars, building a synthetic dataset of visual-question-answer and visual instruction-following tuples. We fine-tune a pre-trained LLaVA 13B checkpoint on our augmented dataset to adapt a Vision-Language Model (VLM) to the visual semantic features in an extraterrestrial environment, demonstrating FMs as a tool for specialization and enhancing a VLM's zero-shot performance on unseen task types in comparison to state-of-the-art VLMs. Ablation studies show that fine-tuning the language backbone and vision-language adapter in concert is key to facilitate adaption while a small percentage, e.g., 20%, of the pre-training data can be used to safeguard against catastrophic forgetting.
Visual place recognition (VPR) remains challenging due to significant viewpoint changes and appearance variations. Mainstream works tackle these challenges by developing various feature aggregation methods to transform deep features into robust and compact global representations. Unfortunately, satisfactory results cannot be achieved under challenging conditions. We start from a new perspective and attempt to build a discriminative global representations by fusing image data and text descriptions of the the visual scene. The motivation is twofold: (1) Current Large Vision-Language Models (LVLMs) demonstrate extraordinary emergent capability in visual instruction following, and thus provide an efficient and flexible manner in generating text descriptions of images; (2) The text descriptions, which provide high-level scene understanding, show strong robustness against environment variations. Although promising, leveraging LVLMs to build multi-modal VPR solutions remains challenging in efficient multi-modal fusion. Furthermore, LVLMs will inevitably produces some inaccurate descriptions, making it even harder. To tackle these challenges, we propose a novel multi-modal VPR solution. It first adapts pre-trained visual and language foundation models to VPR for extracting image and text features, which are then fed into the feature combiner to enhance each other. As the main component, the feature combiner first propose a token-wise attention block to adaptively recalibrate text tokens according to their relevance to the image data, and then develop an efficient cross-attention fusion module to propagate information across different modalities. The enhanced multi-modal features are compressed into the feature descriptor for performing retrieval. Experimental results show that our method outperforms state-of-the-art methods by a large margin with significantly smaller image descriptor dimension.
The rapid development of Multimodal Large Language Models (MLLMs) is making AI-driven scientific assistants increasingly feasible, with interpreting scientific figures being a crucial task. However, existing datasets and benchmarks focus mainly on basic charts and limited science subjects, lacking comprehensive evaluations. To address this, we curated a multimodal, multidisciplinary dataset from peer-reviewed, open-access Nature Communications articles, spanning 72 scientific disciplines. This dataset includes figures such as schematic diagrams, simulated images, macroscopic/microscopic photos, and experimental visualizations (e.g., western blots), which often require graduate-level, discipline-specific expertise to interpret. We developed benchmarks for scientific figure captioning and multiple-choice questions, evaluating six proprietary and over ten open-source models across varied settings. The results highlight the high difficulty of these tasks and the significant performance gap among models. While many open-source models performed at chance level on the multiple-choice task, some matched the performance of proprietary models. However, the gap was more pronounced in the captioning task. Our dataset also provide valuable resource for training. Fine-tuning the Qwen2-VL-2B model with our task-specific multimodal training data improved its multiple-choice accuracy to a level comparable to GPT-4o, though captioning remains challenging. Continuous pre-training of MLLMs using our interleaved article and figure data enhanced their material generation capabilities, demonstrating potential for integrating scientific knowledge. The dataset and benchmarks will be released to support further research.
Large Visual Language Models (LVLMs) struggle with hallucinations in visual instruction following task(s), limiting their trustworthiness and real-world applicability. We propose Pelican -- a novel framework designed to detect and mitigate hallucinations through claim verification. Pelican first decomposes the visual claim into a chain of sub-claims based on first-order predicates. These sub-claims consist of (predicate, question) pairs and can be conceptualized as nodes of a computational graph. We then use Program-of-Thought prompting to generate Python code for answering these questions through flexible composition of external tools. Pelican improves over prior work by introducing (1) intermediate variables for precise grounding of object instances, and (2) shared computation for answering the sub-question to enable adaptive corrections and inconsistency identification. We finally use reasoning abilities of LLMs to verify the correctness of the claim by considering the consistency and confidence of the (question, answer) pairs from each sub-claim. Our experiments reveal a drop in hallucination rate by ~ 8% - 32% across various baseline LVLMs and a 27% drop compared to approaches proposed for hallucination mitigation on MMHal-Bench. Results on two other benchmarks further corroborate our results.
Despite recent advances in the general visual instruction-following ability of Multimodal Large Language Models (MLLMs), they still struggle with critical problems when required to provide a precise and detailed response to a visual instruction: (1) failure to identify novel objects or entities, (2) mention of non-existent objects, and (3) neglect of object's attributed details. Intuitive solutions include improving the size and quality of data or using larger foundation models. They show effectiveness in mitigating these issues, but at an expensive cost of collecting a vast amount of new data and introducing a significantly larger model. Standing at the intersection of these approaches, we examine the three object-oriented problems from the perspective of the image-to-text mapping process by the multimodal connector. In this paper, we first identify the limitations of multimodal connectors stemming from insufficient training data. Driven by this, we propose to enhance the mapping with retrieval-augmented tag tokens, which contain rich object-aware information such as object names and attributes. With our Tag-grounded visual instruction tuning with retrieval Augmentation (TUNA), we outperform baselines that share the same language model and training data on 12 benchmarks. Furthermore, we show the zero-shot capability of TUNA when provided with specific datastores.
Efficient finetuning of large language models (LLMs) aims to adapt the LLMs with reduced computational and memory cost. Previous LoRA-based approaches initialize the low-rank matrices with Gaussian distribution and zero values while keeping the original weight matrices frozen. However, the trainable model parameters optimized in an unguided subspace might interfere with the well-learned subspace of the pretrained weight matrices. In this paper, we propose MiLoRA, a simple yet effective LLM finetuning approach that only updates the minor singular components of the weight matrix while keeping the principal singular components frozen. It is observed that the minor matrix corresponds to the noisy or long-tail information, while the principal matrix contains important knowledge. The MiLoRA initializes the low-rank matrices within a subspace that is orthogonal to the principal matrix, thus the pretrained knowledge is expected to be well preserved. During finetuning, MiLoRA makes the most use of the less-optimized subspace for learning the labeled dataset. Extensive experiments on commonsense reasoning, math reasoning, instruction following and visual instruction following benchmarks present the superior performance of our method.
We introduce FaceGPT, a self-supervised learning framework for Large Vision-Language Models (VLMs) to reason about 3D human faces from images and text. Typical 3D face reconstruction methods are specialized algorithms that lack semantic reasoning capabilities. FaceGPT overcomes this limitation by embedding the parameters of a 3D morphable face model (3DMM) into the token space of a VLM, enabling the generation of 3D faces from both textual and visual inputs. FaceGPT is trained in a self-supervised manner as a model-based autoencoder from in-the-wild images. In particular, the hidden state of LLM is projected into 3DMM parameters and subsequently rendered as 2D face image to guide the self-supervised learning process via image-based reconstruction. Without relying on expensive 3D annotations of human faces, FaceGPT obtains a detailed understanding about 3D human faces, while preserving the capacity to understand general user instructions. Our experiments demonstrate that FaceGPT not only achieves high-quality 3D face reconstructions but also retains the ability for general-purpose visual instruction following. Furthermore, FaceGPT learns fully self-supervised to generate 3D faces based on complex textual inputs, which opens a new direction in human face analysis.
Large Language Models (LLMs) have achieved impressive performance in text understanding and have become an essential tool for building smart assistants. Originally focusing on text, they have been enhanced with multimodal capabilities in recent works that successfully built visual instruction following assistants. As far as the graph modality goes, however, no such assistants have yet been developed. Graph structures are complex in that they represent relation between different features and are permutation invariant. Moreover, representing them in purely textual form does not always lead to good LLM performance even for finetuned models. As a result, there is a need to develop a new method to integrate graphs in LLMs for general graph understanding. This work explores the integration of the graph modality in LLM for general graph instruction following tasks. It aims at producing a deep learning model that enhances an underlying LLM with graph embeddings and trains it to understand them and to produce, given an instruction, an answer grounded in the graph representation. The approach performs significantly better than a graph to text approach and remains consistent even for larger graphs.
Robot manipulation policies have shown unsatisfactory action performance when confronted with novel task or object instances. Hence, the capability to automatically detect and self-correct failure action is essential for a practical robotic system. Recently, Multimodal Large Language Models (MLLMs) have shown promise in visual instruction following and demonstrated strong reasoning abilities in various tasks. To unleash general MLLMs as an end-to-end robotic agent, we introduce a Self-Corrected (SC)-MLLM, equipping our model not only to predict end-effector poses but also to autonomously recognize and correct failure actions. Specifically, we first conduct parameter-efficient fine-tuning to empower MLLM with pose prediction ability, which is reframed as a language modeling problem. When facing execution failures, our model learns to identify low-level action error causes (i.e., position and rotation errors) and adaptively seeks prompt feedback from experts. Based on the feedback, SC-MLLM rethinks the current failure scene and generates the corrected actions. Furthermore, we design a continuous policy learning method for successfully corrected samples, enhancing the model's adaptability to the current scene configuration and reducing the frequency of expert intervention. To evaluate our SC-MLLM, we conduct extensive experiments in both simulation and real-world settings. SC-MLLM agent significantly improve manipulation accuracy compared to previous state-of-the-art robotic MLLM (ManipLLM), increasing from 57\% to 79\% on seen object categories and from 47\% to 69\% on unseen novel categories.
Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios. However, this fine-tuning paradigm may not be able to efficiently learn optimal decision-making agents in multi-step goal-directed tasks from interactive environments. To address this challenge, we propose an algorithmic framework that fine-tunes VLMs with reinforcement learning (RL). Specifically, our framework provides a task description and then prompts the VLM to generate chain-of-thought (CoT) reasoning, enabling the VLM to efficiently explore intermediate reasoning steps that lead to the final text-based action. Next, the open-ended text output is parsed into an executable action to interact with the environment to obtain goal-directed task rewards. Finally, our framework uses these task rewards to fine-tune the entire VLM with RL. Empirically, we demonstrate that our proposed framework enhances the decision-making capabilities of VLM agents across various tasks, enabling 7b models to outperform commercial models such as GPT4-V or Gemini. Furthermore, we find that CoT reasoning is a crucial component for performance improvement, as removing the CoT reasoning results in a significant decrease in the overall performance of our method.
Recent advancements in Multimodal Large Language Models (LLMs) have focused primarily on scaling by increasing text-image pair data and enhancing LLMs to improve performance on multimodal tasks. However, these scaling approaches are computationally expensive and overlook the significance of improving model capabilities from the vision side. Inspired by the successful applications of Mixture-of-Experts (MoE) in LLMs, which improves model scalability during training while keeping inference costs similar to those of smaller models, we propose CuMo. CuMo incorporates Co-upcycled Top-K sparsely-gated Mixture-of-experts blocks into both the vision encoder and the MLP connector, thereby enhancing the multimodal LLMs with minimal additional activated parameters during inference. CuMo first pre-trains the MLP blocks and then initializes each expert in the MoE block from the pre-trained MLP block during the visual instruction tuning stage. Auxiliary losses are used to ensure a balanced loading of experts. CuMo outperforms state-of-the-art multimodal LLMs across various VQA and visual-instruction-following benchmarks using models within each model size group, all while training exclusively on open-sourced datasets. The code and model weights for CuMo are open-sourced at https://github.com/SHI-Labs/CuMo.
In the realm of vision-language understanding, the proficiency of models in interpreting and reasoning over visual content has become a cornerstone for numerous applications. However, it is challenging for the visual encoder in Large Vision-Language Models (LVLMs) to extract useful features tailored to questions that aid the language model's response. Furthermore, a common practice among existing LVLMs is to utilize lower-resolution images, which restricts the ability for visual recognition. Our work introduces the Chain-of-Spot (CoS) method, which we describe as Interactive Reasoning, a novel approach that enhances feature extraction by focusing on key regions of interest (ROI) within the image, corresponding to the posed questions or instructions. This technique allows LVLMs to access more detailed visual information without altering the original image resolution, thereby offering multi-granularity image features. By integrating Chain-of-Spot with instruct-following LLaVA-1.5 models, the process of image reasoning consistently improves performance across a wide range of multimodal datasets and benchmarks without bells and whistles and achieves new state-of-the-art results. Our empirical findings demonstrate a significant improvement in LVLMs' ability to understand and reason about visual content, paving the way for more sophisticated visual instruction-following applications. Code and models are available at https://github.com/dongyh20/Chain-of-Spot
Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks, but the idea is less explored in the multimodal field. In this paper, we present the first attempt to use language-only GPT-4 to generate multimodal language-image instruction-following data. By instruction tuning on such generated data, we introduce LLaVA: Large Language and Vision Assistant, an end-to-end trained large multimodal model that connects a vision encoder and LLM for general-purpose visual and language understanding.Our early experiments show that LLaVA demonstrates impressive multimodel chat abilities, sometimes exhibiting the behaviors of multimodal GPT-4 on unseen images/instructions, and yields a 85.1% relative score compared with GPT-4 on a synthetic multimodal instruction-following dataset. When fine-tuned on Science QA, the synergy of LLaVA and GPT-4 achieves a new state-of-the-art accuracy of 92.53%. We make GPT-4 generated visual instruction tuning data, our model and code base publicly available.
Large-scale pre-training and instruction tuning have been successful at creating general-purpose language models with broad competence. However, building general-purpose vision-language models is challenging due to the rich input distributions and task diversity resulting from the additional visual input. Although vision-language pretraining has been widely studied, vision-language instruction tuning remains under-explored. In this paper, we conduct a systematic and comprehensive study on vision-language instruction tuning based on the pretrained BLIP-2 models. We gather 26 publicly available datasets, covering a wide variety of tasks and capabilities, and transform them into instruction tuning format. Additionally, we introduce an instruction-aware Query Transformer, which extracts informative features tailored to the given instruction. Trained on 13 held-in datasets, InstructBLIP attains state-of-the-art zero-shot performance across all 13 held-out datasets, substantially outperforming BLIP-2 and larger Flamingo models. Our models also lead to state-of-the-art performance when finetuned on individual downstream tasks (e.g., 90.7% accuracy on ScienceQA questions with image contexts). Furthermore, we qualitatively demonstrate the advantages of InstructBLIP over concurrent multimodal models. All InstructBLIP models are open-sourced at https://github.com/salesforce/LAVIS/tree/main/projects/instructblip.
Recent multimodal large language models (MLLMs) have shown promising instruction following capabilities on vision-language tasks. In this work, we introduce VISUAL MODALITY INSTRUCTION (VIM), and investigate how well multimodal models can understand textual instructions provided in pixels, despite not being explicitly trained on such data during pretraining or fine-tuning. We adapt VIM to eight benchmarks, including OKVQA, MM-Vet, MathVista, MMMU, and probe diverse MLLMs in both the text-modality instruction (TEM) setting and VIM setting. Notably, we observe a significant performance disparity between the original TEM and VIM settings for open-source MLLMs, indicating that open-source MLLMs face greater challenges when text instruction is presented solely in image form. To address this issue, we train v-MLLM, a generalizable model that is capable to conduct robust instruction following in both text-modality and visual-modality instructions.