Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model

To develop high-performing Visual Language Models (VLMs), it is essential to prepare multimodal resources, such as image-text pairs, interleaved data, and instruction data. While multimodal resources for English are abundant, there is a significant lack of corresponding resources for non-English languages, such as Japanese. To address this problem, we take Japanese as a non-English language and propose a method for rapidly creating Japanese multimodal datasets from scratch. We collect Japanese image-text pairs and interleaved data from web archives and generate Japanese instruction data directly from images using an existing VLM. Our experimental results show that a VLM trained on these native datasets outperforms those relying on machine-translated content.

AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering

Visual question answering aims to provide responses to natural language questions given visual input. Recently, visual programmatic models (VPMs), which generate executable programs to answer questions through large language models (LLMs), have attracted research interest. However, they often require long input prompts to provide the LLM with sufficient API usage details to generate relevant code. To address this limitation, we propose AdaCoder, an adaptive prompt compression framework for VPMs. AdaCoder operates in two phases: a compression phase and an inference phase. In the compression phase, given a preprompt that describes all API definitions in the Python language with example snippets of code, a set of compressed preprompts is generated, each depending on a specific question type. In the inference phase, given an input question, AdaCoder predicts the question type and chooses the appropriate corresponding compressed preprompt to generate code to answer the question. Notably, AdaCoder employs a single frozen LLM and pre-defined prompts, negating the necessity of additional training and maintaining adaptability across different powerful black-box LLMs such as GPT and Claude. In experiments, we apply AdaCoder to ViperGPT and demonstrate that it reduces token length by 71.1%, while maintaining or even improving the performance of visual question answering.

Answerability Fields: Answerable Location Estimation via Diffusion Models

In an era characterized by advancements in artificial intelligence and robotics, enabling machines to interact with and understand their environment is a critical research endeavor. In this paper, we propose Answerability Fields, a novel approach to predicting answerability within complex indoor environments. Leveraging a 3D question answering dataset, we construct a comprehensive Answerability Fields dataset, encompassing diverse scenes and questions from ScanNet. Using a diffusion model, we successfully infer and evaluate these Answerability Fields, demonstrating the importance of objects and their locations in answering questions within a scene. Our results showcase the efficacy of Answerability Fields in guiding scene-understanding tasks, laying the foundation for their application in enhancing interactions between intelligent agents and their environments.

LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs

This paper introduces LLM-jp, a cross-organizational project for the research and development of Japanese large language models (LLMs). LLM-jp aims to develop open-source and strong Japanese LLMs, and as of this writing, more than 1,500 participants from academia and industry are working together for this purpose. This paper presents the background of the establishment of LLM-jp, summaries of its activities, and technical reports on the LLMs developed by LLM-jp. For the latest activities, visit https://llm-jp.nii.ac.jp/en/.

CityNav: Language-Goal Aerial Navigation Dataset with Geographic Information

Vision-and-language navigation (VLN) aims to guide autonomous agents through real-world environments by integrating visual and linguistic cues. While substantial progress has been made in understanding these interactive modalities in ground-level navigation, aerial navigation remains largely underexplored. This is primarily due to the scarcity of resources suitable for real-world, city-scale aerial navigation studies. To bridge this gap, we introduce CityNav, a new dataset for language-goal aerial navigation using a 3D point cloud representation from real-world cities. CityNav includes 32,637 natural language descriptions paired with human demonstration trajectories, collected from participants via a new web-based 3D simulator developed for this research. Each description specifies a navigation goal, leveraging the names and locations of landmarks within real-world cities. We also provide baseline models of navigation agents that incorporate an internal 2D spatial map representing landmarks referenced in the descriptions. We benchmark the latest aerial navigation baselines and our proposed model on the CityNav dataset. The results using this dataset reveal the following key findings: (i) Our aerial agent models trained on human demonstration trajectories outperform those trained on shortest path trajectories, highlighting the importance of human-driven navigation strategies; (ii) The integration of a 2D spatial map significantly enhances navigation efficiency at city scale. Our dataset and code are available at https://water-cookie.github.io/city-nav-proj/

Map-based Modular Approach for Zero-shot Embodied Question Answering

Building robots capable of interacting with humans through natural language in the visual world presents a significant challenge in the field of robotics. To overcome this challenge, Embodied Question Answering (EQA) has been proposed as a benchmark task to measure the ability to identify an object navigating through a previously unseen environment in response to human-posed questions. Although some methods have been proposed, their evaluations have been limited to simulations, without experiments in real-world scenarios. Furthermore, all of these methods are constrained by a limited vocabulary for question-and-answer interactions, making them unsuitable for practical applications. In this work, we propose a map-based modular EQA method that enables real robots to navigate unknown environments through frontier-based map creation and address unknown QA pairs using foundation models that support open vocabulary. Unlike the questions of the previous EQA dataset on Matterport 3D (MP3D), questions in our real-world experiments contain various question formats and vocabularies not included in the training data. We conduct comprehensive experiments on virtual environments (MP3D-EQA) and two real-world house environments and demonstrate that our method can perform EQA even in the real world.

Text-driven Affordance Learning from Egocentric Vision

Visual affordance learning is a key component for robots to understand how to interact with objects. Conventional approaches in this field rely on pre-defined objects and actions, falling short of capturing diverse interactions in realworld scenarios. The key idea of our approach is employing textual instruction, targeting various affordances for a wide range of objects. This approach covers both hand-object and tool-object interactions. We introduce text-driven affordance learning, aiming to learn contact points and manipulation trajectories from an egocentric view following textual instruction. In our task, contact points are represented as heatmaps, and the manipulation trajectory as sequences of coordinates that incorporate both linear and rotational movements for various manipulations. However, when we gather data for this task, manual annotations of these diverse interactions are costly. To this end, we propose a pseudo dataset creation pipeline and build a large pseudo-training dataset: TextAFF80K, consisting of over 80K instances of the contact points, trajectories, images, and text tuples. We extend existing referring expression comprehension models for our task, and experimental results show that our approach robustly handles multiple affordances, serving as a new standard for affordance learning in real-world scenarios.

JDocQA: Japanese Document Question Answering Dataset for Generative Language Models

Document question answering is a task of question answering on given documents such as reports, slides, pamphlets, and websites, and it is a truly demanding task as paper and electronic forms of documents are so common in our society. This is known as a quite challenging task because it requires not only text understanding but also understanding of figures and tables, and hence visual question answering (VQA) methods are often examined in addition to textual approaches. We introduce Japanese Document Question Answering (JDocQA), a large-scale document-based QA dataset, essentially requiring both visual and textual information to answer questions, which comprises 5,504 documents in PDF format and annotated 11,600 question-and-answer instances in Japanese. Each QA instance includes references to the document pages and bounding boxes for the answer clues. We incorporate multiple categories of questions and unanswerable questions from the document for realistic question-answering applications. We empirically evaluate the effectiveness of our dataset with text-based large language models (LLMs) and multimodal models. Incorporating unanswerable questions in finetuning may contribute to harnessing the so-called hallucination generation.

Vision Language Model-based Caption Evaluation Method Leveraging Visual Context Extraction

Given the accelerating progress of vision and language modeling, accurate evaluation of machine-generated image captions remains critical. In order to evaluate captions more closely to human preferences, metrics need to discriminate between captions of varying quality and content. However, conventional metrics fail short of comparing beyond superficial matches of words or embedding similarities; thus, they still need improvement. This paper presents VisCE$^2$, a vision language model-based caption evaluation method. Our method focuses on visual context, which refers to the detailed content of images, including objects, attributes, and relationships. By extracting and organizing them into a structured format, we replace the human-written references with visual contexts and help VLMs better understand the image, enhancing evaluation performance. Through meta-evaluation on multiple datasets, we validated that VisCE$^2$ outperforms the conventional pre-trained metrics in capturing caption quality and demonstrates superior consistency with human judgment.

SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition

Audio-visual speech recognition (AVSR) is a multimodal extension of automatic speech recognition (ASR), using video as a complement to audio. In AVSR, considerable efforts have been directed at datasets for facial features such as lip-readings, while they often fall short in evaluating the image comprehension capabilities in broader contexts. In this paper, we construct SlideAVSR, an AVSR dataset using scientific paper explanation videos. SlideAVSR provides a new benchmark where models transcribe speech utterances with texts on the slides on the presentation recordings. As technical terminologies that are frequent in paper explanations are notoriously challenging to transcribe without reference texts, our SlideAVSR dataset spotlights a new aspect of AVSR problems. As a simple yet effective baseline, we propose DocWhisper, an AVSR model that can refer to textual information from slides, and confirm its effectiveness on SlideAVSR.