论文检索

Datasets and Benchmarks

Cristobal Eyzaguirre, Eric Tang, Shyamal Buch, Adrien Gaidon, Jiajun Wu, Juan Carlos Niebles

Robotics, autonomous driving, augmented reality, and many embodied computer vision applications must quickly react to user-defined events unfolding in real time. We address this setting by proposing a novel task for multimodal video understanding---Streaming Detection of Queried Event Start (SDQES).The goal of SDQES is to identify the beginning of a complex event as described by a natural language query, with high accuracy and low latency. We introduce a new benchmark based on the Ego4D dataset, as well as new task-specific metrics to study streaming multimodal detection of diverse events in an egocentric video setting.Inspired by parameter-efficient fine-tuning methods in NLP and for video tasks, we propose adapter-based baselines that enable image-to-video transfer learning, allowing for efficient online video modeling.We evaluate three vision-language backbones and three adapter architectures on both short-clip and untrimmed video settings.

Datasets and Benchmarks

Shuai Yuan, Guancong Lin, Lixian Zhang, Runmin Dong, Jinxiao Zhang, Shuang Chen, Juepeng Zheng, Jie Wang, Haohuan Fu

Fine urban change segmentation using multi-temporal remote sensing images is essential for understanding human-environment interactions in urban areas. Although there have been advances in high-quality land cover datasets that reveal the physical features of urban landscapes, the lack of fine-grained land use datasets hinders a deeper understanding of how human activities are distributed across landscapes and the impact of these activities on the environment, thus constraining proper technique development. To address this, we introduce FUSU, the first fine-grained land use change segmentation dataset for Fine-grained Urban Semantic Understanding. FUSU features the most detailed land use classification system to date, with 17 classes and 30 billion pixels of annotations. It includes bi-temporal high-resolution satellite images with 0.2-0.5 m ground sample distance and monthly optical and radar satellite time series, covering 847 km^2 across five urban areas in the southern and northern of China with different geographical features. The fine-grained land use pixel-wise annotations and high spatial-temporal resolution data provide a robust foundation for developing proper deep learning models to provide contextual insights on human activities and urbanization. To fully leverage FUSU, we propose a unified time-series architecture for both change detection and segmentation. We benchmark FUSU on various methods for several tasks. Dataset and code are available at: https://github.com/yuanshuai0914/FUSU.

Edward Vendrow, Omiros Pantazis, Alexander Shepard, Gabriel Brostow, Kate Jones, Oisin Mac Aodha, Sara Beery, Grant Van Horn

We introduce INQUIRE, a text-to-image retrieval benchmark designed to challenge multimodal vision-language models on expert-level queries. INQUIRE includes iNaturalist 2024 (iNat24), a new dataset of five million natural world images, along with 250 expert-level retrieval queries. These queries are paired with all relevant images comprehensively labeled within iNat24, comprising 33,000 total matches. Queries span categories such as species identification, context, behavior, and appearance, emphasizing tasks that require nuanced image understanding and domain expertise. Our benchmark evaluates two core retrieval tasks: (1) INQUIRE-Fullrank, a full dataset ranking task, and (2) INQUIRE-Rerank, a reranking task for refining top-100 retrievals. Detailed evaluation of a range of recent multimodal models demonstrates that INQUIRE poses a significant challenge, with the best models failing to achieve an mAP@50 above 50%. In addition, we show that reranking with more powerful multimodal models can enhance retrieval performance, yet there remains a significant margin for improvement. By focusing on scientifically-motivated ecological challenges, INQUIRE aims to bridge the gap between AI capabilities and the needs of real-world scientific inquiry, encouraging the development of retrieval systems that can assist with accelerating ecological and biodiversity research.

Datasets and Benchmarks

Jian Liu, Jianyu Wu, Hairun Xie, Guoqing zhang, Jing Wang, Liu Wei, Wanli Ouyang, Junjun Jiang, Xianming Liu, SHIXIANG TANG 等

Data-driven generative models have emerged as promising approaches towards achieving efficient mechanical inverse design. However, due to prohibitively high cost in time and money, there is still lack of open-source and large-scale benchmarks in this field. It is mainly the case for airfoil inverse design, which requires to generate and edit diverse geometric-qualified and aerodynamic-qualified airfoils following the multimodal instructions, \emph{i.e.,} dragging points and physical parameters. This paper presents the open-source endeavors in airfoil inverse design, \emph{AFBench}, including a large-scale dataset with 200 thousand airfoils and high-quality aerodynamic and geometric labels, two novel and practical airfoil inverse design tasks, \emph{i.e.,} conditional generation on multimodal physical parameters, controllable editing, and comprehensive metrics to evaluate various existing airfoil inverse design methods. Our aim is to establish \emph{AFBench} as an ecosystem for training and evaluating airfoil inverse design methods, with a specific focus on data-driven controllable inverse design models by multimodal instructions capable of bridging the gap between ideas and execution, the academic research and industrial applications. We have provided baseline models, comprehensive experimental observations, and analysis to accelerate future research. Our baseline model is trained on an RTX 3090 GPU within 16 hours. The codebase, datasets and benchmarks will be available at \url{https://hitcslj.github.io/afbench/}.

Datasets and Benchmarks

Zirui Wang, Mengzhou Xia, Luxi He, Howard Chen, Yitao Liu, Richard Zhu, Kaiqu Liang, Xindi Wu, Haotian Liu, Sadhika Malladi 等

Chart understanding plays a pivotal role when applying Multimodal Large Language Models (MLLMs) to real-world tasks such as analyzing scientific papers or financial reports. However, existing datasets often focus on oversimplified and homogeneous charts with template-based questions, leading to an overly optimistic measure of progress. We demonstrate that although open-source models can appear to outperform strong proprietary models on these benchmarks, a simple stress test with slightly different charts or questions deteriorates performance by up to 34.5%. In this work, we propose CharXiv, a comprehensive evaluation suite involving 2,323 natural, challenging, and diverse charts from scientific papers. CharXiv includes two types of questions: 1) descriptive questions about examining basic chart elements and 2) reasoning questions that require synthesizing information across complex visual elements in the chart. To ensure quality, all charts and questions are handpicked, curated, and verified by human experts. Our results reveal a substantial, previously underestimated gap between the reasoning skills of the strongest proprietary model (i.e., GPT-4o), which achieves 47.1% accuracy, and the strongest open-source model (i.e., InternVL Chat V1.5), which achieves 29.2%. All models lag far behind human performance of 80.5%, underscoring weaknesses in the chart understanding capabilities of existing MLLMs. We hope that CharXiv facilitates future research on MLLM chart understanding by providing a more realistic and faithful measure of progress. Project website: https://charxiv.github.io/

Datasets and Benchmarks

Ge Yang, Changyi He, Jinyang Guo, Jianyu Wu, Yifu Ding, Aishan Liu, Haotong Qin, Pengliang Ji, Xianglong Liu

Although large language models (LLMs) have demonstrated their strong intelligence ability, the high demand for computation and storage hinders their practical application. To this end, many model compression techniques are proposed to increase the efficiency of LLMs. However, current researches only validate their methods on limited models, datasets, metrics, etc, and still lack a comprehensive evaluation under more general scenarios. So it is still a question of which model compression approach we should use under a specific case. To mitigate this gap, we present the Large Language Model Compression Benchmark (LLMCBench), a rigorously designed benchmark with an in-depth analysis for LLM compression algorithms. We first analyze the actual model production requirements and carefully design evaluation tracks and metrics. Then, we conduct extensive experiments and comparison using multiple mainstream LLM compression approaches. Finally, we perform an in-depth analysis based on the evaluation and provide useful insight for LLM compression design. We hope our LLMCBench can contribute insightful suggestions for LLM compression algorithm design and serve as a foundation for future research.

Datasets and Benchmarks

Qingyun Sun, Ziying Chen, Beining Yang, Cheng Ji, Xingcheng Fu, Sheng Zhou, Hao Peng, Jianxin Li, Philip S Yu

Graph condensation (GC) has recently garnered considerable attention due to its ability to reduce large-scale graph datasets while preserving their essential properties. The core concept of GC is to create a smaller, more manageable graph that retains the characteristics of the original graph. Despite the proliferation of graph condensation methods developed in recent years, there is no comprehensive evaluation and in-depth analysis, which creates a great obstacle to understanding the progress in this field. To fill this gap, we develop a comprehensive Graph Condensation Benchmark (GC-Bench) to analyze the performance of graph condensation in different scenarios systematically. Specifically, GC-Bench systematically investigates the characteristics of graph condensation in terms of the following dimensions: effectiveness, transferability, and complexity. We comprehensively evaluate 12 state-of-the-art graph condensation algorithms in node-level and graph-level tasks and analyze their performance in 12 diverse graph datasets. Further, we have developed an easy-to-use library for training and evaluating different GC methods to facilitate reproducible research.The GC-Bench library is available at https://github.com/RingBDStack/GC-Bench.

Datasets and Benchmarks

Yanzhi Li, Keqiu Li, LI GUOHUI, zumin wang, Chanqing Ji, Lubo Wang, Die Zuo, Qing Guo, Feng Zhang, Manyu Wang 等

The latest research on wildfire forecast and backtracking has adopted AI models, which require a large amount of data from wildfire scenarios to capture fire spread patterns. This paper explores using cost-effective simulated wildfire scenarios to train AI models and apply them to the analysis of real-world wildfire. This solution requires AI models to minimize the Sim2Real gap, a brand-new topic in the fire spread analysis research community. To investigate the possibility of minimizing the Sim2Real gap, we collect the Sim2Real-Fire dataset that contains 1M simulated scenarios with multi-modal environmental information for training AI models. We prepare 1K real-world wildfire scenarios for testing the AI models. We also propose a deep transformer, S2R-FireTr, which excels in considering the multi-modal environmental information for forecasting and backtracking the wildfire. S2R-FireTr surpasses state-of-the-art methods in real-world wildfire scenarios.

Graph Neural Networks

Julia Gastinger, Shenyang Huang, Michael Galkin, Erfan Loghmani, Ali Parviz, Farimah Poursafaei, Jacob Danovitch, Emanuele Rossi, Ioannis Koutis, Heiner Stuckenschmidt 等

Multi-relational temporal graphs are powerful tools for modeling real-world data, capturing the evolving and interconnected nature of entities over time. Recently, many novel models are proposed for ML on such graphs intensifying the need for robust evaluation and standardized benchmark datasets. However, the availability of such resources remains scarce and evaluation faces added complexity due to reproducibility issues in experimental protocols. To address these challenges, we introduce Temporal Graph Benchmark 2.0 (TGB 2.0), a novel benchmarking framework tailored for evaluating methods for predicting future links on Temporal Knowledge Graphs and Temporal Heterogeneous Graphs with a focus on large-scale datasets, extending the Temporal Graph Benchmark. TGB 2.0 facilitates comprehensive evaluations by presenting eight novel datasets spanning five domains with up to 53 million edges. TGB 2.0 datasets are significantly largerthan existing datasets in terms of number of nodes, edges, or timestamps. In addition, TGB 2.0 provides a reproducible and realistic evaluation pipeline for multi-relational temporal graphs. Through extensive experimentation, we observe that 1) leveraging edge-type information is crucial to obtain high performance, 2) simple heuristic baselines are often competitive with more complex methods, 3) most methods fail to run on our largest datasets, highlighting the need for research on more scalable methods.

Datasets and Benchmarks

Peng Xia, Ze Chen, Juanxi Tian, Yangrui Gong, Ruibo Hou, Yue Xu, Zhenbang Wu, Zhiyuan Fan, Yiyang Zhou, Kangyu Zhu 等

Artificial intelligence has significantly impacted medical applications, particularly with the advent of Medical Large Vision Language Models (Med-LVLMs), sparking optimism for the future of automated and personalized healthcare. However, the trustworthiness of Med-LVLMs remains unverified, posing significant risks for future model deployment. In this paper, we introduce CARES and aim to comprehensively evaluate the Trustworthiness of Med-LVLMs across the medical domain. We assess the trustworthiness of Med-LVLMs across five dimensions, including trustfulness, fairness, safety, privacy, and robustness. CARES comprises about 41K question-answer pairs in both closed and open-ended formats, covering 16 medical image modalities and 27 anatomical regions. Our analysis reveals that the models consistently exhibit concerns regarding trustworthiness, often displaying factual inaccuracies and failing to maintain fairness across different demographic groups. Furthermore, they are vulnerable to attacks and demonstrate a lack of privacy awareness. We publicly release our benchmark and code in https://github.com/richard-peng-xia/CARES.

Computer Vision · Video Generation

Shenghai Yuan, Jinfa Huang, Yongqi Xu, YaoYang Liu, Shaofeng Zhang, Yujun Shi, Rui-Jie Zhu, Xinhua Cheng, Jiebo Luo, Li Yuan

We propose a novel text-to-video (T2V) generation benchmark, *ChronoMagic-Bench*, to evaluate the temporal and metamorphic knowledge skills in time-lapse video generation of the T2V models (e.g. Sora and Lumiere). Compared to existing benchmarks that focus on visual quality and text relevance of generated videos, *ChronoMagic-Bench* focuses on the models’ ability to generate time-lapse videos with significant metamorphic amplitude and temporal coherence. The benchmark probes T2V models for their physics, biology, and chemistry capabilities, in a free-form text control. For these purposes, *ChronoMagic-Bench* introduces **1,649** prompts and real-world videos as references, categorized into four major types of time-lapse videos: biological, human creation, meteorological, and physical phenomena, which are further divided into 75 subcategories. This categorization ensures a comprehensive evaluation of the models’ capacity to handle diverse and complex transformations. To accurately align human preference on the benchmark, we introduce two new automatic metrics, MTScore and CHScore, to evaluate the videos' metamorphic attributes and temporal coherence. MTScore measures the metamorphic amplitude, reflecting the degree of change over time, while CHScore assesses the temporal coherence, ensuring the generated videos maintain logical progression and continuity. Based on the *ChronoMagic-Bench*, we conduct comprehensive manual evaluations of eighteen representative T2V models, revealing their strengths and weaknesses across different categories of prompts, providing a thorough evaluation framework that addresses current gaps in video generation research. More encouragingly, we create a large-scale *ChronoMagic-Pro* dataset, containing **460k** high-quality pairs of 720p time-lapse videos and detailed captions. Each caption ensures high physical content and large metamorphic amplitude, which have a far-reaching impact on the video generation community. The source data and code are publicly available on [https://pku-yuangroup.github.io/ChronoMagic-Bench](https://pku-yuangroup.github.io/ChronoMagic-Bench).

Computer Vision · Segmentation

sagi eppel, Jolina Li, Manuel Drehwald, Alan Aspuru-Guzik

Visual recognition of materials and their states is essential for understanding the physical world, from identifying wet regions on surfaces or stains on fabrics to detecting infected areas or minerals in rocks. Collecting data that captures this vast variability is complex due to the scattered and gradual nature of material states. Manually annotating real-world images is constrained by cost and precision, while synthetic data, although accurate and inexpensive, lacks real-world diversity. This work aims to bridge this gap by infusing patterns automatically extracted from real-world images into synthetic data. Hence, patterns collected from natural images are used to generate and map materials into synthetic scenes. This unsupervised approach captures the complexity of the real world while maintaining the precision and scalability of synthetic data. We also present the first comprehensive benchmark for zero-shot material state segmentation, utilizing real-world images across a diverse range of domains, including food, soils, construction, plants, liquids, and more, each appears in various states such as wet, dry, infected, cooked, burned, and many others. The annotation includes partial similarity between regions with similar but not identical materials and hard segmentation of only identical material states. This benchmark eluded top foundation models, exposing the limitations of existing data collection methods. Meanwhile, nets trained on the infused data performed significantly better on this and related tasks. The dataset, code, and trained model are publicly available. We also share 300,000 extracted textures and SVBRDF/PBR materials to facilitate future datasets generation.

Generative Models · Reasoning

Niki M Foteinopoulou, Enjie Ghorbel, Djamila Aouada

Explainability in artificial intelligence is crucial for restoring trust, particularly in areas like face forgery detection, where viewers often struggle to distinguish between real and fabricated content. Vision and Large Language Models (VLLM) bridge computer vision and natural language, offering numerous applications driven by strong common-sense reasoning. Despite their success in various tasks, the potential of vision and language remains underexplored in face forgery detection, where they hold promise for enhancing explainability by leveraging the intrinsic reasoning capabilities of language to analyse fine-grained manipulation areas. For that reason, few works have recently started to frame the problem of deepfake detection as a Visual Question Answering (VQA) task, nevertheless omitting the realistic and informative open-ended multi-label setting. With the rapid advances in the field of VLLM, an exponential rise of investigations in that direction is expected. As such, there is a need for a clear experimental methodology that converts face forgery detection to a Visual Question Answering (VQA) task to systematically and fairly evaluate different VLLM architectures. Previous evaluation studies in deepfake detection have mostly focused on the simpler binary task, overlooking evaluation protocols for multi-label fine-grained detection and text-generative models. We propose a multi-staged approach that diverges from the traditional binary evaluation protocol and conducts a comprehensive evaluation study to compare the capabilities of several VLLMs in this context. In the first stage, we assess the models' performance on the binary task and their sensitivity to given instructions using several prompts. In the second stage, we delve deeper into fine-grained detection by identifying areas of manipulation in a multiple-choice VQA setting. In the third stage, we convert the fine-grained detection to an open-ended question and compare several matching strategies for the multi-label classification task. Finally, we qualitatively evaluate the fine-grained responses of the VLLMs included in the benchmark. We apply our benchmark to several popular models, providing a detailed comparison of binary, multiple-choice, and open-ended VQA evaluation across seven datasets. \url{https://nickyfot.github.io/hitchhickersguide.github.io/}

Datasets and Benchmarks

Arian Prabowo, Xiachong LIN, Imran Razzak, Hao Xue, Emily Yap, Matthew Amos, Flora Salim

Buildings play a crucial role in human well-being, influencing occupant comfort, health, and safety.Additionally, they contribute significantly to global energy consumption, accounting for one-third of total energy usage, and carbon emissions.Optimizing building performance presents a vital opportunity to combat climate change and promote human flourishing.However, research in building analytics has been hampered by the lack of accessible, available, and comprehensive real-world datasets on multiple building operations.In this paper, we introduce the Building TimeSeries (BTS) dataset.Our dataset covers three buildings over a three-year period, comprising more than ten thousand timeseries data points with hundreds of unique ontologies.Moreover, the metadata is standardized using the Brick schema.To demonstrate the utility of this dataset, we performed benchmarks on two tasks: timeseries ontology classification and zero-shot forecasting.These tasks represent an essential initial step in addressing challenges related to interoperability in building analytics.Access to the dataset and the code used for benchmarking are available here: https://github.com/cruiseresearchgroup/DIEF\_BTS

Generative Models

Xindi Wu, Dingli Yu, Yangsibo Huang, Olga Russakovsky, Sanjeev Arora

Compositionality is a critical capability in Text-to-Image (T2I) models, as it reflects their ability to understand and combine multiple concepts from text descriptions. Existing evaluations of compositional capability rely heavily on human-designed text prompts or fixed templates, limiting their diversity and complexity, and yielding low discriminative power. We propose ConceptMix, a scalable, controllable, and customizable benchmark which automatically evaluates compositional generation ability of T2I models. This is done in two stages. First, ConceptMix generates the text prompts: concretely, using categories of visual concepts (e.g., objects, colors, shapes, spatial relationships), it randomly samples an object and k-tuples of visual concepts, then uses GPT-4o to generate text prompts for image generation based on these sampled concepts. Second, ConceptMix evaluates the images generated in response to these prompts: concretely, it checks how many of the k concepts actually appeared in the image by generating one question per visual concept and using a strong VLM to answer them. Through administering ConceptMix to a diverse set of T2I models (proprietary as well as open ones) using increasing values of k, we show that our ConceptMix has higher discrimination power than earlier benchmarks. Specifically, ConceptMix reveals that the performance of several models, especially open models, drops dramatically with increased k. Importantly, it also provides insight into the lack of prompt diversity in widely-used training datasets. Additionally, we conduct extensive human studies to validate the design of ConceptMix and compare our automatic grading with human judgement. We hope it will guide future T2I model development.

Datasets and Benchmarks

Bowen Li, Zhaoyu Li, Qiwei Du, Jinqi Luo, Wenshan Wang, Yaqi Xie, Simon Stepputtis, Chen Wang, Katia Sycara, Pradeep Ravikumar 等

Recent years have witnessed the rapid development of Neuro-Symbolic (NeSy) AI systems, which integrate symbolic reasoning into deep neural networks.However, most of the existing benchmarks for NeSy AI fail to provide long-horizon reasoning tasks with complex multi-agent interactions.Furthermore, they are usually constrained by fixed and simplistic logical rules over limited entities, making them far from real-world complexities.To address these crucial gaps, we introduce LogiCity, the first simulator based on customizable first-order logic (FOL) for an urban-like environment with multiple dynamic agents.LogiCity models diverse urban elements using semantic and spatial concepts, such as $\texttt{IsAmbulance}(\texttt{X})$ and $\texttt{IsClose}(\texttt{X}, \texttt{Y})$. These concepts are used to define FOL rules that govern the behavior of various agents. Since the concepts and rules are abstractions, they can be universally applied to cities with any agent compositions, facilitating the instantiation of diverse scenarios.Besides, a key feature of LogiCity is its support for user-configurable abstractions, enabling customizable simulation complexities for logical reasoning.To explore various aspects of NeSy AI, LogiCity introduces two tasks, one features long-horizon sequential decision-making, and the other focuses on one-step visual reasoning, varying in difficulty and agent behaviors.Our extensive evaluation reveals the advantage of NeSy frameworks in abstract reasoning. Moreover, we highlight the significant challenges of handling more complex abstractions in long-horizon multi-agent scenarios or under high-dimensional, imbalanced data.With its flexible design, various features, and newly raised challenges, we believe LogiCity represents a pivotal step forward in advancing the next generation of NeSy AI.All the code and data are open-sourced at our website.

Datasets and Benchmarks

Biao Gong, Shuai Tan, Yutong Feng, Xiaoying Xie, Yuyuan Li, Chaochao Chen, Kecheng Zheng, Yujun Shen, Deli Zhao

This work presents a unified knowledge protocol, called UKnow, which facilitates knowledge-based studies from the perspective of data. Particularly focusing on visual and linguistic modalities, we categorize data knowledge into five unit types, namely, in-image, in-text, cross-image, cross-text, and image-text, and set up an efficient pipeline to help construct the multimodal knowledge graph from any data collection. Thanks to the logical information naturally contained in knowledge graph, organizing datasets under UKnow format opens up more possibilities of data usage compared to the commonly used image-text pairs. Following UKnow protocol, we collect, from public international news, a large-scale multimodal knowledge graph dataset that consists of 1,388,568 nodes (with 571,791 vision-related ones) and 3,673,817 triplets. The dataset is also annotated with rich event tags, including 11 coarse labels and 9,185 fine labels. Experiments on four benchmarks demonstrate the potential of UKnow in supporting common-sense reasoning and boosting vision-language pre-training with a single dataset, benefiting from its unified form of knowledge organization. Code, dataset, and models will be made publicly available. See Appendix to download the dataset.

Datasets and Benchmarks

Patrick Tser Jern Kon, Jiachen Liu, Yiming Qiu, Weijun Fan, Ting He, Lei Lin, Haoran Zhang, Owen Park, George Elengikal, Yuxin Kang 等

Infrastructure-as-Code (IaC), an important component of cloud computing, allows the definition of cloud infrastructure in high-level programs. However, developing IaC programs is challenging, complicated by factors that include the burgeoning complexity of the cloud ecosystem (e.g., diversity of cloud services and workloads), and the relative scarcity of IaC-specific code examples and public repositories. While large language models (LLMs) have shown promise in general code generation and could potentially aid in IaC development, no benchmarks currently exist for evaluating their ability to generate IaC code. We present IaC-Eval, a first step in this research direction. IaC-Eval's dataset includes 458 human-curated scenarios covering a wide range of popular AWS services, at varying difficulty levels. Each scenario mainly comprises a natural language IaC problem description and an infrastructure intent specification. The former is fed as user input to the LLM, while the latter is a general notion used to verify if the generated IaC program conforms to the user's intent; by making explicit the problem's requirements that can encompass various cloud services, resources and internal infrastructure details. Our in-depth evaluation shows that contemporary LLMs perform poorly on IaC-Eval, with the top-performing model, GPT-4, obtaining a pass@1 accuracy of 19.36%. In contrast, it scores 86.6% on EvalPlus, a popular Python code generation benchmark, highlighting a need for advancements in this domain. We open-source the IaC-Eval dataset and evaluation framework at https://github.com/autoiac-project/iac-eval to enable future research on LLM-based IaC code generation.

Trustworthy Machine Learning

Yichi Zhang, Yao Huang, Yitong Sun, Chang Liu, Zhe Zhao, Zhengwei Fang, Yifan Wang, Huanran Chen, Xiao Yang, Xingxing Wei 等

Despite the superior capabilities of Multimodal Large Language Models (MLLMs) across diverse tasks, they still face significant trustworthiness challenges. Yet, current literature on the assessment of trustworthy MLLMs remains limited, lacking a holistic evaluation to offer thorough insights into future improvements. In this work, we establish **MultiTrust**, the first comprehensive and unified benchmark on the trustworthiness of MLLMs across five primary aspects: *truthfulness*, *safety*, *robustness*, *fairness*, and *privacy*. Our benchmark employs a rigorous evaluation strategy that addresses both multimodal risks and cross-modal impacts, encompassing 32 diverse tasks with self-curated datasets. Extensive experiments with 21 modern MLLMs reveal some previously unexplored trustworthiness issues and risks, highlighting the complexities introduced by the multimodality and underscoring the necessity for advanced methodologies to enhance their reliability. For instance, typical proprietary models still struggle with the perception of visually confusing images and are vulnerable to multimodal jailbreaking and adversarial attacks; MLLMs are more inclined to disclose privacy in text and reveal ideological and cultural biases even when paired with irrelevant images in inference, indicating that the multimodality amplifies the internal risks from base LLMs. Additionally, we release a scalable toolbox for standardized trustworthiness research, aiming to facilitate future advancements in this important field. Code and resources are publicly available at: [https://multi-trust.github.io/](https://multi-trust.github.io/).

Datasets and Benchmarks

Junlin Xie, Ruifei Zhang, Zhihong Chen, Xiang Wan, Guanbin Li

Recently, large language models (LLMs) have achieved superior performance, empowering the development of large multimodal agents (LMAs). An LMA is anticipated to execute practical tasks requires various capabilities including multimodal perception, interaction, reasoning, and decision making. However, existing benchmarks are limited in assessing compositional skills and actions demanded by practical scenarios, where they primarily focused on single tasks and static scenarios. To bridge this gap, we introduce WhodunitBench, a benchmark rooted from murder mystery games, where players are required to utilize the aforementioned skills to achieve their objective (i.e., identifying the `murderer' or hiding themselves), providing a simulated dynamic environment for evaluating LMAs. Specifically, WhodunitBench includes two evaluation modes. The first mode, the arena-style evaluation, is constructed from 50 meticulously curated scripts featuring clear reasoning clues and distinct murderers; The second mode, the chain of evaluation, consists of over 3000 curated multiple-choice questions and open-ended questions, aiming to assess every facet of the murder mystery games for LMAs. Experiments show that although current LMAs show acceptable performance in basic perceptual tasks, they are insufficiently equipped for complex multi-agent collaboration and multi-step reasoning tasks. Furthermore, the full application of the theory of mind to complete games in a manner akin to human behavior remains a significant challenge. We hope this work can illuminate the path forward, providing a solid foundation for the future development of LMAs. Our WhodunitBench is open-source and accessible at: https://github.com/jun0wanan/WhodunitBench-Murder_Mystery_Games