In this paper, we consider the problem of prototype-based vision-language reasoning problem. We observe that existing methods encounter three major challenges: 1) escalating resource demands and prolonging training times, 2) contending with excessive learnable parameters, and 3) fine-tuning based only on a single modality. These challenges will hinder their capability to adapt Vision-Language Models (VLMs) to downstream tasks. Motivated by this critical observation, we propose a novel method called NODE-Adapter, which utilizes Neural Ordinary Differential Equations for better vision-language reasoning. To fully leverage both visual and textual modalities and estimate class prototypes more effectively and accurately, we divide our method into two stages: cross-modal prototype construction and cross-modal prototype optimization using neural ordinary differential equations. Specifically, we exploit VLM to encode hand-crafted prompts into textual features and few-shot support images into visual features. Then, we estimate the textual prototype and visual prototype by averaging the textual features and visual features, respectively, and adaptively combine the textual prototype and visual prototype to construct the cross-modal prototype. To alleviate the prototype bias, we then model the prototype optimization process as an initial value problem with Neural ODEs to estimate the continuous gradient flow. Our extensive experimental results, which cover few-shot classification, domain generalization, and visual reasoning on human-object interaction, demonstrate that the proposed method significantly outperforms existing state-of-the-art approaches.
Although most current large multimodal models (LMMs) can already understand photos of natural scenes and portraits, their understanding of abstract images, e.g., charts, maps, or layouts, and visual reasoning capabilities remains quite rudimentary. They often struggle with simple daily tasks, such as reading time from a clock, understanding a flowchart, or planning a route using a road map. In light of this, we design a multi-modal self-instruct, utilizing large language models and their code capabilities to synthesize massive abstract images and visual reasoning instructions across daily scenarios. Our strategy effortlessly creates a multimodal benchmark with 11,193 instructions for eight visual scenarios: charts, tables, simulated maps, dashboards, flowcharts, relation graphs, floor plans, and visual puzzles. \textbf{This benchmark, constructed with simple lines and geometric elements, exposes the shortcomings of most advanced LMMs} like Claude-3.5-Sonnet and GPT-4o in abstract image understanding, spatial relations reasoning, and visual element induction. Besides, to verify the quality of our synthetic data, we fine-tune an LMM using 62,476 synthetic chart, table and road map instructions. The results demonstrate improved chart understanding and map navigation performance, and also demonstrate potential benefits for other visual reasoning tasks. Our code is available at: \url{https://github.com/zwq2018/Multi-modal-Self-instruct}.
Multimodal Large Language Models (MLLMs) harness comprehensive knowledge spanning text, images, and audio to adeptly tackle complex problems, including zero-shot in-context learning scenarios. This study explores the ability of MLLMs in visually solving the Traveling Salesman Problem (TSP) and Multiple Traveling Salesman Problem (mTSP) using images that portray point distributions on a two-dimensional plane. We introduce a novel approach employing multiple specialized agents within the MLLM framework, each dedicated to optimizing solutions for these combinatorial challenges. Our experimental investigation includes rigorous evaluations across zero-shot settings and introduces innovative multi-agent zero-shot in-context scenarios. The results demonstrated that both multi-agent models. Multi-Agent 1, which includes the Initializer, Critic, and Scorer agents, and Multi-Agent 2, which comprises only the Initializer and Critic agents; significantly improved solution quality for TSP and mTSP problems. Multi-Agent 1 excelled in environments requiring detailed route refinement and evaluation, providing a robust framework for sophisticated optimizations. In contrast, Multi-Agent 2, focusing on iterative refinements by the Initializer and Critic, proved effective for rapid decision-making scenarios. These experiments yield promising outcomes, showcasing the robust visual reasoning capabilities of MLLMs in addressing diverse combinatorial problems. The findings underscore the potential of MLLMs as powerful tools in computational optimization, offering insights that could inspire further advancements in this promising field. Project link: https://github.com/ahmed-abdulhuy/Solving-TSP-and-mTSP-Combinatorial-Challenges-using-Visual-Reasoning-and-Multi-Agent-Approach-MLLMs-.git
Visual mathematical reasoning, as a fundamental visual reasoning ability, has received widespread attention from the Large Multimodal Models (LMMs) community. Existing benchmarks, such as MathVista and MathVerse, focus more on the result-oriented performance but neglect the underlying principles in knowledge acquisition and generalization. Inspired by human-like mathematical reasoning, we introduce WE-MATH, the first benchmark specifically designed to explore the problem-solving principles beyond end-to-end performance. We meticulously collect and categorize 6.5K visual math problems, spanning 67 hierarchical knowledge concepts and five layers of knowledge granularity. We decompose composite problems into sub-problems according to the required knowledge concepts and introduce a novel four-dimensional metric, namely Insufficient Knowledge (IK), Inadequate Generalization (IG), Complete Mastery (CM), and Rote Memorization (RM), to hierarchically assess inherent issues in LMMs' reasoning process. With WE-MATH, we conduct a thorough evaluation of existing LMMs in visual mathematical reasoning and reveal a negative correlation between solving steps and problem-specific performance. We confirm the IK issue of LMMs can be effectively improved via knowledge augmentation strategies. More notably, the primary challenge of GPT-4o has significantly transitioned from IK to IG, establishing it as the first LMM advancing towards the knowledge generalization stage. In contrast, other LMMs exhibit a marked inclination towards Rote Memorization - they correctly solve composite problems involving multiple knowledge concepts yet fail to answer sub-problems. We anticipate that WE-MATH will open new pathways for advancements in visual mathematical reasoning for LMMs. The WE-MATH data and evaluation code are available at https://github.com/We-Math/We-Math.
The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to preserve all visual contexts via one-to-one transformation. However, the visual tokens are redundant and can be considerably increased when dealing with high-resolution images, impairing the efficiency of MLLMs significantly. Some recent works have introduced resampler or abstractor to reduce the number of resulting visual tokens. Unfortunately, they fail to capture finer details and undermine the visual reasoning capabilities of MLLMs. In this work, we propose a novel visual projector, which adopts a coarse-to-fine scheme to inject the enriched characteristics to generate the condensed visual tokens. In specific, we first interpolate the visual features as a low-resolution point query, providing the overall visual representation as the foundation. Then, we introduce a region-to-point injection module that utilizes high-resolution, multi-level region-based cues as fine-grained reference keys and values, allowing them to be fully absorbed within the corresponding local context region. This step effectively updates the coarse point query, transforming it into an enriched one for the subsequent LLM reasoning. Extensive experiments demonstrate that our approach compresses the visual tokens by 75%~89%, while achieves comparable or even better performance across diverse benchmarks with significantly higher efficiency. The source codes can be found at https://github.com/CircleRadon/TokenPacker.
It is fundamentally challenging for robots to serve as useful assistants in human environments because this requires addressing a spectrum of sub-problems across robotics, including perception, language understanding, reasoning, and planning. The recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated their exceptional abilities in solving complex mathematical problems, mastering commonsense and abstract reasoning. This has led to the recent utilization of MLLMs as the brain in robotic systems, enabling these models to conduct high-level planning prior to triggering low-level control actions for task execution. However, it remains uncertain whether existing MLLMs are reliable in serving the brain role of robots. In this study, we introduce the first benchmark for evaluating Multimodal LLM for Robotic (MMRo) benchmark, which tests the capability of MLLMs for robot applications. Specifically, we identify four essential capabilities perception, task planning, visual reasoning, and safety measurement that MLLMs must possess to qualify as the robot's central processing unit. We have developed several scenarios for each capability, resulting in a total of 14 metrics for evaluation. We present experimental results for various MLLMs, including both commercial and open-source models, to assess the performance of existing systems. Our findings indicate that no single model excels in all areas, suggesting that current MLLMs are not yet trustworthy enough to serve as the cognitive core for robots. Our data can be found in https://mm-robobench.github.io/.
We explore multi-step reasoning in vision-language models (VLMs). The problem is challenging, as reasoning data consisting of multiple steps of visual and language processing are barely available. To overcome the challenge, we first introduce a least-to-most visual reasoning paradigm, which interleaves steps of decomposing a question into sub-questions and invoking external tools for resolving sub-questions. Based on the paradigm, we further propose a novel data synthesis approach that can automatically create questions and multi-step reasoning paths for an image in a bottom-up manner. Our approach divides the complex synthesis task into a few simple sub-tasks, and (almost entirely) relies on open-sourced models to accomplish the sub-tasks. Therefore, the entire synthesis process is reproducible and cost-efficient, and the synthesized data is quality guaranteed. With the approach, we construct $50$k visual reasoning examples. Then, we develop a visual reasoner through supervised fine-tuning, which is capable of generally enhancing the reasoning abilities of a wide range of existing VLMs in a plug-and-play fashion. Extensive experiments indicate that the visual reasoner can consistently and significantly improve four VLMs on four VQA benchmarks. Our code and dataset are available at https://github.com/steven-ccq/VisualReasoner.
Visual arguments, often used in advertising or social causes, rely on images to persuade viewers to do or believe something. Understanding these arguments requires selective vision: only specific visual stimuli within an image are relevant to the argument, and relevance can only be understood within the context of a broader argumentative structure. While visual arguments are readily appreciated by human audiences, we ask: are today's AI capable of similar understanding? We present VisArgs, a dataset of 1,611 images annotated with 5,112 visual premises (with regions), 5,574 commonsense premises, and reasoning trees connecting them into structured arguments. We propose three tasks for evaluating visual argument understanding: premise localization, premise identification, and conclusion deduction. Experiments show that 1) machines struggle to capture visual cues: GPT-4-O achieved 78.5% accuracy, while humans reached 98.0%. Models also performed 19.5% worse when distinguishing between irrelevant objects within the image compared to external objects. 2) Providing relevant visual premises improved model performance significantly.
Despite significant advancements in robotic systems and surgical data science, ensuring safe and optimal execution in robot-assisted minimally invasive surgery (RMIS) remains a complex challenge. Current surgical error detection methods involve two parts: identifying surgical gestures and then detecting errors within each gesture clip. These methods seldom consider the rich contextual and semantic information inherent in surgical videos, limiting their performance due to reliance on accurate gesture identification. Motivated by the chain-of-thought prompting in natural language processing, this letter presents a novel and real-time end-to-end error detection framework, Chain-of-Thought (COG) prompting, leveraging contextual information from surgical videos. This encompasses two reasoning modules designed to mimic the decision-making processes of expert surgeons. Concretely, we first design a Gestural-Visual Reasoning module, which utilizes transformer and attention architectures for gesture prompting, while the second, a Multi-Scale Temporal Reasoning module, employs a multi-stage temporal convolutional network with both slow and fast paths for temporal information extraction. We extensively validate our method on the public benchmark RMIS dataset JIGSAWS. Our method encapsulates the reasoning processes inherent to surgical activities enabling it to outperform the state-of-the-art by 4.6% in F1 score, 4.6% in Accuracy, and 5.9% in Jaccard index while processing each frame in 6.69 milliseconds on average, demonstrating the great potential of our approach in enhancing the safety and efficacy of RMIS procedures and surgical education. The code will be available.
We study the Knowledge-Based visual question-answering problem, for which given a question, the models need to ground it into the visual modality to find the answer. Although many recent works use question-dependent captioners to verbalize the given image and use Large Language Models to solve the VQA problem, the research results show they are not reasonably performing for multi-hop questions. Our study shows that replacing a complex question with several simpler questions helps to extract more relevant information from the image and provide a stronger comprehension of it. Moreover, we analyze the decomposed questions to find out the modality of the information that is required to answer them and use a captioner for the visual questions and LLMs as a general knowledge source for the non-visual KB-based questions. Our results demonstrate the positive impact of using simple questions before retrieving visual or non-visual information. We have provided results and analysis on three well-known VQA datasets including OKVQA, A-OKVQA, and KRVQA, and achieved up to 2% improvement in accuracy.
To create culturally inclusive vision-language models (VLMs), developing a benchmark that tests their ability to address culturally relevant questions is essential. Existing approaches typically rely on human annotators, making the process labor-intensive and creating a cognitive burden in generating diverse questions. To address this, we propose a semi-automated framework for constructing cultural VLM benchmarks, specifically targeting multiple-choice QA. This framework combines human-VLM collaboration, where VLMs generate questions based on guidelines, a small set of annotated examples, and relevant knowledge, followed by a verification process by native speakers. We demonstrate the effectiveness of this framework through the creation of K-Viscuit, a dataset focused on Korean culture. Our experiments on this dataset reveal that open-source models lag behind proprietary ones in understanding Korean culture, highlighting key areas for improvement. We also present a series of further analyses, including human evaluation, augmenting VLMs with external knowledge, and the evaluation beyond multiple-choice QA. Our dataset is available at https://huggingface.co/datasets/ddehun/k-viscuit.
Though vision transformers (ViTs) have achieved state-of-the-art performance in a variety of settings, they exhibit surprising failures when performing tasks involving visual relations. This begs the question: how do ViTs attempt to perform tasks that require computing visual relations between objects? Prior efforts to interpret ViTs tend to focus on characterizing relevant low-level visual features. In contrast, we adopt methods from mechanistic interpretability to study the higher-level visual algorithms that ViTs use to perform abstract visual reasoning. We present a case study of a fundamental, yet surprisingly difficult, relational reasoning task: judging whether two visual entities are the same or different. We find that pretrained ViTs fine-tuned on this task often exhibit two qualitatively different stages of processing despite having no obvious inductive biases to do so: 1) a perceptual stage wherein local object features are extracted and stored in a disentangled representation, and 2) a relational stage wherein object representations are compared. In the second stage, we find evidence that ViTs can learn to represent somewhat abstract visual relations, a capability that has long been considered out of reach for artificial neural networks. Finally, we demonstrate that failures at either stage can prevent a model from learning a generalizable solution to our fairly simple tasks. By understanding ViTs in terms of discrete processing stages, one can more precisely diagnose and rectify shortcomings of existing and future models.
Visual programs are executable code generated by large language models to address visual reasoning problems. They decompose complex questions into multiple reasoning steps and invoke specialized models for each step to solve the problems. However, these programs are prone to logic errors, with our preliminary evaluation showing that 58% of the total errors are caused by program logic errors. Debugging complex visual programs remains a major bottleneck for visual reasoning. To address this, we introduce VDebugger, a novel critic-refiner framework trained to localize and debug visual programs by tracking execution step by step. VDebugger identifies and corrects program errors leveraging detailed execution feedback, improving interpretability and accuracy. The training data is generated through an automated pipeline that injects errors into correct visual programs using a novel mask-best decoding technique. Evaluations on six datasets demonstrate VDebugger's effectiveness, showing performance improvements of up to 3.2% in downstream task accuracy. Further studies show VDebugger's ability to generalize to unseen tasks, bringing a notable improvement of 2.3% on the unseen COVR task. Code, data and models are made publicly available at https://github.com/shirley-wu/vdebugger/
The ability to understand and reason about spatial relationships between objects in images is an important component of visual reasoning. This skill rests on the ability to recognize and localize objects of interest and determine their spatial relation. Early vision and language models (VLMs) have been shown to struggle to recognize spatial relations. We extend the previously released What'sUp dataset and propose a novel comprehensive evaluation for spatial relationship understanding that highlights the strengths and weaknesses of 27 different models. In addition to the VLMs evaluated in What'sUp, our extensive evaluation encompasses 3 classes of Multimodal LLMs (MLLMs) that vary in their parameter sizes (ranging from 7B to 110B), training/instruction-tuning methods, and visual resolution to benchmark their performances and scrutinize the scaling laws in this task.
When presented with questions involving visual thinking, humans naturally switch reasoning modalities, often forming mental images or drawing visual aids. Large language models have shown promising results in arithmetic and symbolic reasoning by expressing intermediate reasoning in text as a chain of thought, yet struggle to extend this capability to answer text queries that are easily solved by visual reasoning, even with extensive multimodal pretraining. We introduce a simple method, whiteboard-of-thought prompting, to unlock the visual reasoning capabilities of multimodal large language models across modalities. Whiteboard-of-thought prompting provides multimodal large language models with a metaphorical `whiteboard' to draw out reasoning steps as images, then returns these images back to the model for further processing. We find this can be accomplished with no demonstrations or specialized modules, instead leveraging models' existing ability to write code with libraries such as Matplotlib and Turtle. This simple approach shows state-of-the-art results on four difficult natural language tasks that involve visual and spatial reasoning. We identify multiple settings where GPT-4o using chain-of-thought fails dramatically, including more than one where it achieves $0\%$ accuracy, while whiteboard-of-thought enables up to $92\%$ accuracy in these same settings. We present a detailed exploration of where the technique succeeds as well as its sources of error.
Recent State Space Models (SSMs) such as S4, S5, and Mamba have shown remarkable computational benefits in long-range temporal dependency modeling. However, in many sequence modeling problems, the underlying process is inherently modular and it is of interest to have inductive biases that mimic this modular structure. In this paper, we introduce SlotSSMs, a novel framework for incorporating independent mechanisms into SSMs to preserve or encourage separation of information. Unlike conventional SSMs that maintain a monolithic state vector, SlotSSMs maintains the state as a collection of multiple vectors called slots. Crucially, the state transitions are performed independently per slot with sparse interactions across slots implemented via the bottleneck of self-attention. In experiments, we evaluate our model in object-centric learning, 3D visual reasoning, and long-context video understanding tasks, which involve modeling multiple objects and their long-range temporal dependencies. We find that our proposed design offers substantial performance gains over existing sequence modeling methods. Project page is available at https://slotssms.github.io/
The Privacy-sensitive Object Identification (POI) task allocates bounding boxes for privacy-sensitive objects in a scene. The key to POI is settling an object's privacy class (privacy-sensitive or non-privacy-sensitive). In contrast to conventional object classes which are determined by the visual appearance of an object, one object's privacy class is derived from the scene contexts and is subject to various implicit factors beyond its visual appearance. That is, visually similar objects may be totally opposite in their privacy classes. To explicitly derive the objects' privacy class from the scene contexts, in this paper, we interpret the POI task as a visual reasoning task aimed at the privacy of each object in the scene. Following this interpretation, we propose the PrivacyGuard framework for POI. PrivacyGuard contains three stages. i) Structuring: an unstructured image is first converted into a structured, heterogeneous scene graph that embeds rich scene contexts. ii) Data Augmentation: a contextual perturbation oversampling strategy is proposed to create slightly perturbed privacy-sensitive objects in a scene graph, thereby balancing the skewed distribution of privacy classes. iii) Hybrid Graph Generation & Reasoning: the balanced, heterogeneous scene graph is then transformed into a hybrid graph by endowing it with extra "node-node" and "edge-edge" homogeneous paths. These homogeneous paths allow direct message passing between nodes or edges, thereby accelerating reasoning and facilitating the capturing of subtle context changes. Based on this hybrid graph... **For the full abstract, see the original paper.**
The remote sensing image intelligence understanding model is undergoing a new profound paradigm shift which has been promoted by multi-modal large language model (MLLM), i.e. from the paradigm learning a domain model (LaDM) shifts to paradigm learning a pre-trained general foundation model followed by an adaptive domain model (LaGD). Under the new LaGD paradigm, the old datasets, which have led to advances in RSI intelligence understanding in the last decade, are no longer suitable for fire-new tasks. We argued that a new dataset must be designed to lighten tasks with the following features: 1) Generalization: training model to learn shared knowledge among tasks and to adapt to different tasks; 2) Understanding complex scenes: training model to understand the fine-grained attribute of the objects of interest, and to be able to describe the scene with natural language; 3) Reasoning: training model to be able to realize high-level visual reasoning. In this paper, we designed a high-quality, diversified, and unified multimodal instruction-following dataset for RSI understanding produced by GPT-4V and existing datasets, which we called RS-GPT4V. To achieve generalization, we used a (Question, Answer) which was deduced from GPT-4V via instruction-following to unify the tasks such as captioning and localization; To achieve complex scene, we proposed a hierarchical instruction description with local strategy in which the fine-grained attributes of the objects and their spatial relationships are described and global strategy in which all the local information are integrated to yield detailed instruction descript; To achieve reasoning, we designed multiple-turn QA pair to provide the reasoning ability for a model. The empirical results show that the fine-tuned MLLMs by RS-GPT4V can describe fine-grained information. The dataset is available at: https://github.com/GeoX-Lab/RS-GPT4V.
Aligning vision and language concepts at a finer level remains an essential topic of multimodal large language models (MLLMs), particularly for tasks such as referring and grounding. Existing methods, such as proxy encoding and geometry encoding, incorporate additional syntax to encode spatial information, imposing extra burdens when communicating between language and vision modules. In this study, we propose ClawMachine, offering a new methodology that explicitly notates each entity using token collectives groups of visual tokens that collaboratively represent higher level semantics. A hybrid perception mechanism is also explored to perceive and understand scenes from both discrete and continuous spaces. Our method unifies the prompt and answer of visual referential tasks without using additional syntax. By leveraging a joint vision-language vocabulary, ClawMachine further integrates referring and grounding in an auto-regressive manner, demonstrating great potential with scaled-up pre-training data. Experiments show that ClawMachine achieves superior performance on scene-level and referential understanding tasks with higher efficiency. It also exhibits the potential to integrate multi-source information for complex visual reasoning, which is beyond the capability of many MLLMs. Our code is available at github.com/martian422/ClawMachine.
Recently, Multimodal Large Language Models (MLLMs) have shown great promise in language-guided perceptual tasks such as recognition, segmentation, and object detection. However, their effectiveness in addressing visual cognition problems that require high-level reasoning is not well-established. One such challenge is abstract visual reasoning (AVR) -- the cognitive ability to discern relationships among patterns in a set of images and extrapolate to predict subsequent patterns. This skill is crucial during the early neurodevelopmental stages of children. Inspired by the AVR tasks in Raven's Progressive Matrices (RPM) and Wechsler Intelligence Scale for Children (WISC), we propose a new dataset MaRs-VQA and a new benchmark VCog-Bench containing three datasets to evaluate the zero-shot AVR capability of MLLMs and compare their performance with existing human intelligent investigation. Our comparative experiments with different open-source and closed-source MLLMs on the VCog-Bench revealed a gap between MLLMs and human intelligence, highlighting the visual cognitive limitations of current MLLMs. We believe that the public release of VCog-Bench, consisting of MaRs-VQA, and the inference pipeline will drive progress toward the next generation of MLLMs with human-like visual cognition abilities.