MR-MLLM: Mutual Reinforcement of Multimodal Comprehension and Vision Perception

In recent years, multimodal large language models (MLLMs) have shown remarkable capabilities in tasks like visual question answering and common sense reasoning, while visual perception models have made significant strides in perception tasks, such as detection and segmentation. However, MLLMs mainly focus on high-level image-text interpretations and struggle with fine-grained visual understanding, and vision perception models usually suffer from open-world distribution shifts due to their limited model capacity. To overcome these challenges, we propose the Mutually Reinforced Multimodal Large Language Model (MR-MLLM), a novel framework that synergistically enhances visual perception and multimodal comprehension. First, a shared query fusion mechanism is proposed to harmonize detailed visual inputs from vision models with the linguistic depth of language models, enhancing multimodal comprehension and vision perception synergistically. Second, we propose the perception-enhanced cross-modal integration method, incorporating novel modalities from vision perception outputs, like object detection bounding boxes, to capture subtle visual elements, thus enriching the understanding of both visual and textual data. In addition, an innovative perception-embedded prompt generation mechanism is proposed to embed perceptual information into the language model's prompts, aligning the responses contextually and perceptually for a more accurate multimodal interpretation. Extensive experiments demonstrate MR-MLLM's superior performance in various multimodal comprehension and vision perception tasks, particularly those requiring corner case vision perception and fine-grained language comprehension.

On Efficient Neural Network Architectures for Image Compression

Recent advances in learning-based image compression typically come at the cost of high complexity. Designing computationally efficient architectures remains an open challenge. In this paper, we empirically investigate the impact of different network designs in terms of rate-distortion performance and computational complexity. Our experiments involve testing various transforms, including convolutional neural networks and transformers, as well as various context models, including hierarchical, channel-wise, and space-channel context models. Based on the results, we present a series of efficient models, the final model of which has comparable performance to recent best-performing methods but with significantly lower complexity. Extensive experiments provide insights into the design of architectures for learned image compression and potential direction for future research. The code is available at \url{https://gitlab.com/viper-purdue/efficient-compression}.

Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study

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/.

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

In this study, we investigate whether attention-based information flow inside large language models (LLMs) is aggregated through noticeable patterns for long context processing. Our observations reveal that LLMs aggregate information through Pyramidal Information Funneling where attention is scattering widely in lower layers, progressively consolidating within specific contexts, and ultimately focusin on critical tokens (a.k.a massive activation or attention sink) in higher layers. Motivated by these insights, we developed PyramidKV, a novel and effective KV cache compression method. This approach dynamically adjusts the KV cache size across different layers, allocating more cache in lower layers and less in higher ones, diverging from traditional methods that maintain a uniform KV cache size. Our experimental evaluations, utilizing the LongBench benchmark, show that PyramidKV matches the performance of models with a full KV cache while retaining only 12% of the KV cache, thus significantly reducing memory usage. In scenarios emphasizing memory efficiency, where only 0.7% of the KV cache is maintained, PyramidKV surpasses other KV cache compression techniques achieving up to a 20.5 absolute accuracy improvement on TREC.

Eliciting Informative Text Evaluations with Large Language Models

Peer prediction mechanisms motivate high-quality feedback with provable guarantees. However, current methods only apply to rather simple reports, like multiple-choice or scalar numbers. We aim to broaden these techniques to the larger domain of text-based reports, drawing on the recent developments in large language models. This vastly increases the applicability of peer prediction mechanisms as textual feedback is the norm in a large variety of feedback channels: peer reviews, e-commerce customer reviews, and comments on social media. We introduce two mechanisms, the Generative Peer Prediction Mechanism (GPPM) and the Generative Synopsis Peer Prediction Mechanism (GSPPM). These mechanisms utilize LLMs as predictors, mapping from one agent's report to a prediction of her peer's report. Theoretically, we show that when the LLM prediction is sufficiently accurate, our mechanisms can incentivize high effort and truth-telling as an (approximate) Bayesian Nash equilibrium. Empirically, we confirm the efficacy of our mechanisms through experiments conducted on two real datasets: the Yelp review dataset and the ICLR OpenReview dataset. We highlight the results that on the ICLR dataset, our mechanisms can differentiate three quality levels -- human-written reviews, GPT-4-generated reviews, and GPT-3.5-generated reviews in terms of expected scores. Additionally, GSPPM penalizes LLM-generated reviews more effectively than GPPM.

Mixture of Modality Knowledge Experts for Robust Multi-modal Knowledge Graph Completion

Multi-modal knowledge graph completion (MMKGC) aims to automatically discover new knowledge triples in the given multi-modal knowledge graphs (MMKGs), which is achieved by collaborative modeling the structural information concealed in massive triples and the multi-modal features of the entities. Existing methods tend to focus on crafting elegant entity-wise multi-modal fusion strategies, yet they overlook the utilization of multi-perspective features concealed within the modalities under diverse relational contexts. To address this issue, we introduce a novel MMKGC framework with Mixture of Modality Knowledge experts (MoMoK for short) to learn adaptive multi-modal embedding under intricate relational contexts. We design relation-guided modality knowledge experts to acquire relation-aware modality embeddings and integrate the predictions from multi-modalities to achieve comprehensive decisions. Additionally, we disentangle the experts by minimizing their mutual information. Experiments on four public MMKG benchmarks demonstrate the outstanding performance of MoMoK under complex scenarios.

Multi-domain Knowledge Graph Collaborative Pre-training and Prompt Tuning for Diverse Downstream Tasks

Knowledge graphs (KGs) provide reliable external knowledge for a wide variety of AI tasks in the form of structured triples. Knowledge graph pre-training (KGP) aims to pre-train neural networks on large-scale KGs and provide unified interfaces to enhance different downstream tasks, which is a key direction for KG management, maintenance, and applications. Existing works often focus on purely research questions in open domains, or they are not open source due to data security and privacy in real scenarios. Meanwhile, existing studies have not explored the training efficiency and transferability of KGP models in depth. To address these problems, We propose a framework MuDoK to achieve multi-domain collaborative pre-training and efficient prefix prompt tuning to serve diverse downstream tasks like recommendation and text understanding. Our design is a plug-and-play prompt learning approach that can be flexibly adapted to different downstream task backbones. In response to the lack of open-source benchmarks, we constructed a new multi-domain KGP benchmark called KPI with two large-scale KGs and six different sub-domain tasks to evaluate our method and open-sourced it for subsequent research. We evaluated our approach based on constructed KPI benchmarks using diverse backbone models in heterogeneous downstream tasks. The experimental results show that our framework brings significant performance gains, along with its generality, efficiency, and transferability.

Surveying Attitudinal Alignment Between Large Language Models Vs. Humans Towards 17 Sustainable Development Goals

Large Language Models (LLMs) have emerged as potent tools for advancing the United Nations' Sustainable Development Goals (SDGs). However, the attitudinal disparities between LLMs and humans towards these goals can pose significant challenges. This study conducts a comprehensive review and analysis of the existing literature on the attitudes of LLMs towards the 17 SDGs, emphasizing the comparison between their attitudes and support for each goal and those of humans. We examine the potential disparities, primarily focusing on aspects such as understanding and emotions, cultural and regional differences, task objective variations, and factors considered in the decision-making process. These disparities arise from the underrepresentation and imbalance in LLM training data, historical biases, quality issues, lack of contextual understanding, and skewed ethical values reflected. The study also investigates the risks and harms that may arise from neglecting the attitudes of LLMs towards the SDGs, including the exacerbation of social inequalities, racial discrimination, environmental destruction, and resource wastage. To address these challenges, we propose strategies and recommendations to guide and regulate the application of LLMs, ensuring their alignment with the principles and goals of the SDGs, and therefore creating a more just, inclusive, and sustainable future.

Beyond Pixel-Wise Supervision for Medical Image Segmentation: From Traditional Models to Foundation Models

Medical image segmentation plays an important role in many image-guided clinical approaches. However, existing segmentation algorithms mostly rely on the availability of fully annotated images with pixel-wise annotations for training, which can be both labor-intensive and expertise-demanding, especially in the medical imaging domain where only experts can provide reliable and accurate annotations. To alleviate this challenge, there has been a growing focus on developing segmentation methods that can train deep models with weak annotations, such as image-level, bounding boxes, scribbles, and points. The emergence of vision foundation models, notably the Segment Anything Model (SAM), has introduced innovative capabilities for segmentation tasks using weak annotations for promptable segmentation enabled by large-scale pre-training. Adopting foundation models together with traditional learning methods has increasingly gained recent interest research community and shown potential for real-world applications. In this paper, we present a comprehensive survey of recent progress on annotation-efficient learning for medical image segmentation utilizing weak annotations before and in the era of foundation models. Furthermore, we analyze and discuss several challenges of existing approaches, which we believe will provide valuable guidance for shaping the trajectory of foundational models to further advance the field of medical image segmentation.

Exploring the Transferability of Visual Prompting for Multimodal Large Language Models

Although Multimodal Large Language Models (MLLMs) have demonstrated promising versatile capabilities, their performance is still inferior to specialized models on downstream tasks, which makes adaptation necessary to enhance their utility. However, fine-tuning methods require independent training for every model, leading to huge computation and memory overheads. In this paper, we propose a novel setting where we aim to improve the performance of diverse MLLMs with a group of shared parameters optimized for a downstream task. To achieve this, we propose Transferable Visual Prompting (TVP), a simple and effective approach to generate visual prompts that can transfer to different models and improve their performance on downstream tasks after trained on only one model. We introduce two strategies to address the issue of cross-model feature corruption of existing visual prompting methods and enhance the transferability of the learned prompts, including 1) Feature Consistency Alignment: which imposes constraints to the prompted feature changes to maintain task-agnostic knowledge; 2) Task Semantics Enrichment: which encourages the prompted images to contain richer task-specific semantics with language guidance. We validate the effectiveness of TVP through extensive experiments with 6 modern MLLMs on a wide variety of tasks ranging from object recognition and counting to multimodal reasoning and hallucination correction.