ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding

Structured image understanding, such as interpreting tables and charts, requires strategically refocusing across various structures and texts within an image, forming a reasoning sequence to arrive at the final answer. However, current multimodal large language models (LLMs) lack this multihop selective attention capability. In this work, we introduce ReFocus, a simple yet effective framework that equips multimodal LLMs with the ability to generate "visual thoughts" by performing visual editing on the input image through code, shifting and refining their visual focuses. Specifically, ReFocus enables multimodal LLMs to generate Python codes to call tools and modify the input image, sequentially drawing boxes, highlighting sections, and masking out areas, thereby enhancing the visual reasoning process. We experiment upon a wide range of structured image understanding tasks involving tables and charts. ReFocus largely improves performance on all tasks over GPT-4o without visual editing, yielding an average gain of 11.0% on table tasks and 6.8% on chart tasks. We present an in-depth analysis of the effects of different visual edits, and reasons why ReFocus can improve the performance without introducing additional information. Further, we collect a 14k training set using ReFocus, and prove that such visual chain-of-thought with intermediate information offers a better supervision than standard VQA data, reaching a 8.0% average gain over the same model trained with QA pairs and 2.6% over CoT.

MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design

The discovery of novel mechanical metamaterials, whose properties are dominated by their engineered structures rather than chemical composition, is a knowledge-intensive and resource-demanding process. To accelerate the design of novel metamaterials, we present MetaScientist, a human-in-the-loop system that integrates advanced AI capabilities with expert oversight with two primary phases: (1) hypothesis generation, where the system performs complex reasoning to generate novel and scientifically sound hypotheses, supported with domain-specific foundation models and inductive biases retrieved from existing literature; (2) 3D structure synthesis, where a 3D structure is synthesized with a novel 3D diffusion model based on the textual hypothesis and refined it with a LLM-based refinement model to achieve better structure properties. At each phase, domain experts iteratively validate the system outputs, and provide feedback and supplementary materials to ensure the alignment of the outputs with scientific principles and human preferences. Through extensive evaluation from human scientists, MetaScientist is able to deliver novel and valid mechanical metamaterial designs that have the potential to be highly impactful in the metamaterial field.

Lateralization LoRA: Interleaved Instruction Tuning with Modality-Specialized Adaptations

Recent advancements in Vision-Language Models (VLMs) have led to the development of Vision-Language Generalists (VLGs) capable of understanding and generating interleaved images and text. Despite these advances, VLGs still struggle to follow user instructions for interleaved text and image generation. To address this issue, we introduce LeafInstruct, the first open-sourced interleaved instruction tuning data with over 30,000 high-quality instances across more than 10 domains. Due to the extensive size of existing VLGs, we opt for parameter-efficient tuning. However, we observe that VLGs tuned with a standard LoRA typically exhibit inferior performance in interleaved text-image generation. We attribute this problem to modality interference and the lack of modality-specialized adaptation design. Hence, we propose Lateralization LoRA, a novel modality-specialized adaptation method inspired by the concept of brain lateralization. Lateralization LoRA employs a hybrid approach, combining the traditional linear LoRA and a Convolutional LoRA for generating text and images, enabling the generation of high-quality text and images by leveraging modality-specific structures and parameter sets. We perform instruction tuning of the VLG (i.e., EMU2) using Lateralization LoRA on the LeafInstruct dataset. Extensive experiments demonstrate that EMU2 tuned with Lateralization LoRA achieve state-of-the-art performance, significantly surpassing baseline models in complex interleaved tasks.

Holistic Evaluation for Interleaved Text-and-Image Generation

Interleaved text-and-image generation has been an intriguing research direction, where the models are required to generate both images and text pieces in an arbitrary order. Despite the emerging advancements in interleaved generation, the progress in its evaluation still significantly lags behind. Existing evaluation benchmarks do not support arbitrarily interleaved images and text for both inputs and outputs, and they only cover a limited number of domains and use cases. Also, current works predominantly use similarity-based metrics which fall short in assessing the quality in open-ended scenarios. To this end, we introduce InterleavedBench, the first benchmark carefully curated for the evaluation of interleaved text-and-image generation. InterleavedBench features a rich array of tasks to cover diverse real-world use cases. In addition, we present InterleavedEval, a strong reference-free metric powered by GPT-4o to deliver accurate and explainable evaluation. We carefully define five essential evaluation aspects for InterleavedEval, including text quality, perceptual quality, image coherence, text-image coherence, and helpfulness, to ensure a comprehensive and fine-grained assessment. Through extensive experiments and rigorous human evaluation, we show that our benchmark and metric can effectively evaluate the existing models with a strong correlation with human judgments surpassing previous reference-based metrics. We also provide substantial findings and insights to foster future research in interleaved generation and its evaluation.

X-Eval: Generalizable Multi-aspect Text Evaluation via Augmented Instruction Tuning with Auxiliary Evaluation Aspects

Natural Language Generation (NLG) typically involves evaluating the generated text in various aspects (e.g., consistency and naturalness) to obtain a comprehensive assessment. However, multi-aspect evaluation remains challenging as it may require the evaluator to generalize to any given evaluation aspect even if it's absent during training. In this paper, we introduce X-Eval, a two-stage instruction tuning framework to evaluate the text in both seen and unseen aspects customized by end users. X-Eval consists of two learning stages: the vanilla instruction tuning stage that improves the model's ability to follow evaluation instructions, and an enhanced instruction tuning stage that exploits the connections between fine-grained evaluation aspects to better assess text quality. To support the training of X-Eval, we collect AspectInstruct, the first instruction tuning dataset tailored for multi-aspect NLG evaluation spanning 27 diverse evaluation aspects with 65 tasks. To enhance task diversity, we devise an augmentation strategy that converts human rating annotations into diverse forms of NLG evaluation tasks, including scoring, comparison, ranking, and Boolean question answering. Extensive experiments across three essential categories of NLG tasks: dialogue generation, summarization, and data-to-text coupled with 21 aspects in meta-evaluation, demonstrate that our X-Eval enables even a lightweight language model to achieve a comparable if not higher correlation with human judgments compared to the state-of-the-art NLG evaluators, such as GPT-4.

MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks

Automatically generating scripts (i.e. sequences of key steps described in text) from video demonstrations and reasoning about the subsequent steps are crucial to the modern AI virtual assistants to guide humans to complete everyday tasks, especially unfamiliar ones. However, current methods for generative script learning rely heavily on well-structured preceding steps described in text and/or images or are limited to a certain domain, resulting in a disparity with real-world user scenarios. To address these limitations, we present a new benchmark challenge -- MultiScript, with two new tasks on task-oriented multimodal script learning: (1) multimodal script generation, and (2) subsequent step prediction. For both tasks, the input consists of a target task name and a video illustrating what has been done to complete the target task, and the expected output is (1) a sequence of structured step descriptions in text based on the demonstration video, and (2) a single text description for the subsequent step, respectively. Built from WikiHow, MultiScript covers multimodal scripts in videos and text descriptions for over 6,655 human everyday tasks across 19 diverse domains. To establish baseline performance on MultiScript, we propose two knowledge-guided multimodal generative frameworks that incorporate the task-related knowledge prompted from large language models such as Vicuna. Experimental results show that our proposed approaches significantly improve over the competitive baselines.

Teamwork Is Not Always Good: An Empirical Study of Classifier Drift in Class-incremental Information Extraction

Class-incremental learning (CIL) aims to develop a learning system that can continually learn new classes from a data stream without forgetting previously learned classes. When learning classes incrementally, the classifier must be constantly updated to incorporate new classes, and the drift in decision boundary may lead to severe forgetting. This fundamental challenge, however, has not yet been studied extensively, especially in the setting where no samples from old classes are stored for rehearsal. In this paper, we take a closer look at how the drift in the classifier leads to forgetting, and accordingly, design four simple yet (super-) effective solutions to alleviate the classifier drift: an Individual Classifiers with Frozen Feature Extractor (ICE) framework where we individually train a classifier for each learning session, and its three variants ICE-PL, ICE-O, and ICE-PL&O which further take the logits of previously learned classes from old sessions or a constant logit of an Other class as a constraint to the learning of new classifiers. Extensive experiments and analysis on 6 class-incremental information extraction tasks demonstrate that our solutions, especially ICE-O, consistently show significant improvement over the previous state-of-the-art approaches with up to 44.7% absolute F-score gain, providing a strong baseline and insights for future research on class-incremental learning.

Iteratively Improving Biomedical Entity Linking and Event Extraction via Hard Expectation-Maximization

Biomedical entity linking and event extraction are two crucial tasks to support text understanding and retrieval in the biomedical domain. These two tasks intrinsically benefit each other: entity linking disambiguates the biomedical concepts by referring to external knowledge bases and the domain knowledge further provides additional clues to understand and extract the biological processes, while event extraction identifies a key trigger and entities involved to describe each biological process which also captures the structural context to better disambiguate the biomedical entities. However, previous research typically solves these two tasks separately or in a pipeline, leading to error propagation. What's more, it's even more challenging to solve these two tasks together as there is no existing dataset that contains annotations for both tasks. To solve these challenges, we propose joint biomedical entity linking and event extraction by regarding the event structures and entity references in knowledge bases as latent variables and updating the two task-specific models in a hard Expectation-Maximization (EM) fashion: (1) predicting the missing variables for each partially annotated dataset based on the current two task-specific models, and (2) updating the parameters of each model on the corresponding pseudo completed dataset. Experimental results on two benchmark datasets: Genia 2011 for event extraction and BC4GO for entity linking, show that our joint framework significantly improves the model for each individual task and outperforms the strong baselines for both tasks. We will make the code and model checkpoints publicly available once the paper is accepted.

AMELI: Enhancing Multimodal Entity Linking with Fine-Grained Attributes

We propose attribute-aware multimodal entity linking, where the input is a mention described with a text and image, and the goal is to predict the corresponding target entity from a multimodal knowledge base (KB) where each entity is also described with a text description, a visual image and a set of attributes and values. To support this research, we construct AMELI, a large-scale dataset consisting of 18,472 reviews and 35,598 products. To establish baseline performance on AMELI, we experiment with the current state-of-the-art multimodal entity linking approaches and our enhanced attribute-aware model and demonstrate the importance of incorporating the attribute information into the entity linking process. To be best of our knowledge, we are the first to build benchmark dataset and solutions for the attribute-aware multimodal entity linking task. Datasets and codes will be made publicly available.

The Art of SOCRATIC QUESTIONING: Zero-shot Multimodal Reasoning with Recursive Thinking and Self-Questioning

Chain-of-Thought prompting (CoT) enables large-scale language models to solve complex reasoning problems by decomposing the problem and tackling it step-by-step. However, Chain-of-Thought is a greedy thinking process that requires the language model to come up with a starting point and generate the next step solely based on previous steps. This thinking process is different from how humans approach a complex problem e.g., we proactively raise sub-problems related to the original problem and recursively answer them. In this work, we propose Socratic Questioning, a divide-and-conquer fashion algorithm that simulates the self-questioning and recursive thinking process. Socratic Questioning is driven by a Self-Questioning module that employs a large-scale language model to propose sub-problems related to the original problem as intermediate steps and Socratic Questioning recursively backtracks and answers the sub-problems until reaches the original problem. We apply our proposed algorithm to the visual question-answering task as a case study and by evaluating it on three public benchmark datasets, we observe a significant performance improvement over all baselines on (almost) all datasets. In addition, the qualitative analysis clearly demonstrates the intermediate thinking steps elicited by Socratic Questioning are similar to the human's recursively thinking process of a complex reasoning problem.