Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models

The recent advancement of Multimodal Large Language Models (MLLMs) has significantly improved their fine-grained perception of single images and general comprehension across multiple images. However, existing MLLMs still face challenges in achieving precise grounding in complex multi-image scenarios. To address this, we first explore a Chain-of-Thought (CoT) framework that integrates single-image grounding with multi-image comprehension. While partially effective, it remains unstable and struggles to capture abstract visual information due to its non-end-to-end nature. Therefore, we introduce Migician, the first multi-image grounding model capable of performing free-form and accurate grounding across multiple images. To support this, we present the MGrounding-630k dataset, which comprises data for several multi-image grounding tasks derived from existing datasets, along with newly generated free-form grounding instruction-following data. Furthermore, we propose MIG-Bench, a comprehensive benchmark specifically designed for evaluating multi-image grounding capabilities. Experimental results demonstrate that our model achieves significantly superior multi-image grounding capabilities, outperforming the best existing MLLMs by 21.61% and even surpassing much larger 70B models. Our code, model, dataset, and benchmark are fully open-sourced at https://migician-vg.github.io/.

ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in chart understanding tasks. However, interpreting charts with textual descriptions often leads to information loss, as it fails to fully capture the dense information embedded in charts. In contrast, parsing charts into code provides lossless representations that can effectively contain all critical details. Although existing open-source MLLMs have achieved success in chart understanding tasks, they still face two major challenges when applied to chart-to-code tasks.: (1) Low executability and poor restoration of chart details in the generated code and (2) Lack of large-scale and diverse training data. To address these challenges, we propose \textbf{ChartCoder}, the first dedicated chart-to-code MLLM, which leverages Code LLMs as the language backbone to enhance the executability of the generated code. Furthermore, we introduce \textbf{Chart2Code-160k}, the first large-scale and diverse dataset for chart-to-code generation, and propose the \textbf{Snippet-of-Thought (SoT)} method, which transforms direct chart-to-code generation data into step-by-step generation. Experiments demonstrate that ChartCoder, with only 7B parameters, surpasses existing open-source MLLMs on chart-to-code benchmarks, achieving superior chart restoration and code excitability. Our code will be available at https://github.com/thunlp/ChartCoder.

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency

Multimodal Large Language Models (MLLMs) have achieved impressive performance and have been put into practical use in commercial applications, but they still have potential safety mechanism vulnerabilities. Jailbreak attacks are red teaming methods that aim to bypass safety mechanisms and discover MLLMs' potential risks. Existing MLLMs' jailbreak methods often bypass the model's safety mechanism through complex optimization methods or carefully designed image and text prompts. Despite achieving some progress, they have a low attack success rate on commercial closed-source MLLMs. Unlike previous research, we empirically find that there exists a Shuffle Inconsistency between MLLMs' comprehension ability and safety ability for the shuffled harmful instruction. That is, from the perspective of comprehension ability, MLLMs can understand the shuffled harmful text-image instructions well. However, they can be easily bypassed by the shuffled harmful instructions from the perspective of safety ability, leading to harmful responses. Then we innovatively propose a text-image jailbreak attack named SI-Attack. Specifically, to fully utilize the Shuffle Inconsistency and overcome the shuffle randomness, we apply a query-based black-box optimization method to select the most harmful shuffled inputs based on the feedback of the toxic judge model. A series of experiments show that SI-Attack can improve the attack's performance on three benchmarks. In particular, SI-Attack can obviously improve the attack success rate for commercial MLLMs such as GPT-4o or Claude-3.5-Sonnet.

LLaVA-UHD v2: an MLLM Integrating High-Resolution Feature Pyramid via Hierarchical Window Transformer

In multimodal large language models (MLLMs), vision transformers (ViTs) are widely employed for visual encoding. However, their performance in solving universal MLLM tasks is not satisfactory. We attribute it to a lack of information from diverse visual levels, impeding alignment with the various semantic granularity required for language generation. To address this issue, we present LLaVA-UHD v2, an advanced MLLM centered around a Hierarchical window transformer that enables capturing diverse visual granularity by constructing and integrating a high-resolution feature pyramid. As a vision-language projector, Hiwin transformer comprises two primary modules: (i) an inverse feature pyramid, constructed by a ViT-derived feature up-sampling process utilizing high-frequency details from an image pyramid, and (ii) hierarchical window attention, focusing on a set of key sampling features within cross-scale windows to condense multi-level feature maps. Extensive experiments demonstrate that LLaVA-UHD v2 achieves superior performance over existing MLLMs on popular benchmarks. Notably, our design brings an average boost of 3.7% across 14 benchmarks compared with the baseline method, 9.3% on DocVQA for instance. We make all the data, model checkpoint, and code publicly available to facilitate future research.

StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding

The rapid development of Multimodal Large Language Models (MLLMs) has expanded their capabilities from image comprehension to video understanding. However, most of these MLLMs focus primarily on offline video comprehension, necessitating extensive processing of all video frames before any queries can be made. This presents a significant gap compared to the human ability to watch, listen, think, and respond to streaming inputs in real time, highlighting the limitations of current MLLMs. In this paper, we introduce StreamingBench, the first comprehensive benchmark designed to evaluate the streaming video understanding capabilities of MLLMs. StreamingBench assesses three core aspects of streaming video understanding: (1) real-time visual understanding, (2) omni-source understanding, and (3) contextual understanding. The benchmark consists of 18 tasks, featuring 900 videos and 4,500 human-curated QA pairs. Each video features five questions presented at different time points to simulate a continuous streaming scenario. We conduct experiments on StreamingBench with 13 open-source and proprietary MLLMs and find that even the most advanced proprietary MLLMs like Gemini 1.5 Pro and GPT-4o perform significantly below human-level streaming video understanding capabilities. We hope our work can facilitate further advancements for MLLMs, empowering them to approach human-level video comprehension and interaction in more realistic scenarios.

PlaneSAM: Multimodal Plane Instance Segmentation Using the Segment Anything Model

Plane instance segmentation from RGB-D data is a crucial research topic for many downstream tasks. However, most existing deep-learning-based methods utilize only information within the RGB bands, neglecting the important role of the depth band in plane instance segmentation. Based on EfficientSAM, a fast version of SAM, we propose a plane instance segmentation network called PlaneSAM, which can fully integrate the information of the RGB bands (spectral bands) and the D band (geometric band), thereby improving the effectiveness of plane instance segmentation in a multimodal manner. Specifically, we use a dual-complexity backbone, with primarily the simpler branch learning D-band features and primarily the more complex branch learning RGB-band features. Consequently, the backbone can effectively learn D-band feature representations even when D-band training data is limited in scale, retain the powerful RGB-band feature representations of EfficientSAM, and allow the original backbone branch to be fine-tuned for the current task. To enhance the adaptability of our PlaneSAM to the RGB-D domain, we pretrain our dual-complexity backbone using the segment anything task on large-scale RGB-D data through a self-supervised pretraining strategy based on imperfect pseudo-labels. To support the segmentation of large planes, we optimize the loss function combination ratio of EfficientSAM. In addition, Faster R-CNN is used as a plane detector, and its predicted bounding boxes are fed into our dual-complexity network as prompts, thereby enabling fully automatic plane instance segmentation. Experimental results show that the proposed PlaneSAM sets a new SOTA performance on the ScanNet dataset, and outperforms previous SOTA approaches in zero-shot transfer on the 2D-3D-S, Matterport3D, and ICL-NUIM RGB-D datasets, while only incurring a 10% increase in computational overhead compared to EfficientSAM.

ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models

Active perception, a crucial human capability, involves setting a goal based on the current understanding of the environment and performing actions to achieve that goal. Despite significant efforts in evaluating Multimodal Large Language Models (MLLMs), active perception has been largely overlooked. To address this gap, we propose a novel benchmark named ActiView to evaluate active perception in MLLMs. Since comprehensively assessing active perception is challenging, we focus on a specialized form of Visual Question Answering (VQA) that eases the evaluation yet challenging for existing MLLMs. Given an image, we restrict the perceptual field of a model, requiring it to actively zoom or shift its perceptual field based on reasoning to answer the question successfully. We conduct extensive evaluation over 27 models, including proprietary and open-source models, and observe that the ability to read and comprehend multiple images simultaneously plays a significant role in enabling active perception. Results reveal a significant gap in the active perception capability of MLLMs, indicating that this area deserves more attention. We hope that our benchmark could help develop methods for MLLMs to understand multimodal inputs in more natural and holistic ways.

Co-Fix3D: Enhancing 3D Object Detection with Collaborative Refinement

In the realm of autonomous driving,accurately detecting occluded or distant objects,referred to as weak positive sample ,presents significant challenges. These challenges predominantly arise during query initialization, where an over-reliance on heatmap confidence often results in a high rate of false positives, consequently masking weaker detections and impairing system performance. To alleviate this issue, we propose a novel approach, Co-Fix3D, which employs a collaborative hybrid multi-stage parallel query generation mechanism for BEV representations. Our method incorporates the Local-Global Feature Enhancement (LGE) module, which refines BEV features to more effectively highlight weak positive samples. It uniquely leverages the Discrete Wavelet Transform (DWT) for accurate noise reduction and features refinement in localized areas, and incorporates an attention mechanism to more comprehensively optimize global BEV features. Moreover, our method increases the volume of BEV queries through a multi-stage parallel processing of the LGE, significantly enhancing the probability of selecting weak positive samples. This enhancement not only improves training efficiency within the decoder framework but also boosts overall system performance. Notably, Co-Fix3D achieves superior results on the stringent nuScenes benchmark, outperforming all previous models with a 69.1% mAP and 72.9% NDS on the LiDAR-based benchmark, and 72.3% mAP and 74.1% NDS on the multi-modality benchmark, without relying on test-time augmentation or additional datasets. The source code will be made publicly available upon acceptance.

PagPassGPT: Pattern Guided Password Guessing via Generative Pretrained Transformer

Amidst the surge in deep learning-based password guessing models, challenges of generating high-quality passwords and reducing duplicate passwords persist. To address these challenges, we present PagPassGPT, a password guessing model constructed on Generative Pretrained Transformer (GPT). It can perform pattern guided guessing by incorporating pattern structure information as background knowledge, resulting in a significant increase in the hit rate. Furthermore, we propose D&C-GEN to reduce the repeat rate of generated passwords, which adopts the concept of a divide-and-conquer approach. The primary task of guessing passwords is recursively divided into non-overlapping subtasks. Each subtask inherits the knowledge from the parent task and predicts succeeding tokens. In comparison to the state-of-the-art model, our proposed scheme exhibits the capability to correctly guess 12% more passwords while producing 25% fewer duplicates.

Goldfish: An Efficient Federated Unlearning Framework

With recent legislation on the right to be forgotten, machine unlearning has emerged as a crucial research area. It facilitates the removal of a user's data from federated trained machine learning models without the necessity for retraining from scratch. However, current machine unlearning algorithms are confronted with challenges of efficiency and validity.To address the above issues, we propose a new framework, named Goldfish. It comprises four modules: basic model, loss function, optimization, and extension. To address the challenge of low validity in existing machine unlearning algorithms, we propose a novel loss function. It takes into account the loss arising from the discrepancy between predictions and actual labels in the remaining dataset. Simultaneously, it takes into consideration the bias of predicted results on the removed dataset. Moreover, it accounts for the confidence level of predicted results. Additionally, to enhance efficiency, we adopt knowledge distillation technique in basic model and introduce an optimization module that encompasses the early termination mechanism guided by empirical risk and the data partition mechanism. Furthermore, to bolster the robustness of the aggregated model, we propose an extension module that incorporates a mechanism using adaptive distillation temperature to address the heterogeneity of user local data and a mechanism using adaptive weight to handle the variety in the quality of uploaded models. Finally, we conduct comprehensive experiments to illustrate the effectiveness of proposed approach.