Unleashing the Potential of SAM2 for Biomedical Images and Videos: A Survey

The unprecedented developments in segmentation foundational models have become a dominant force in the field of computer vision, introducing a multitude of previously unexplored capabilities in a wide range of natural images and videos. Specifically, the Segment Anything Model (SAM) signifies a noteworthy expansion of the prompt-driven paradigm into the domain of image segmentation. The recent introduction of SAM2 effectively extends the original SAM to a streaming fashion and demonstrates strong performance in video segmentation. However, due to the substantial distinctions between natural and medical images, the effectiveness of these models on biomedical images and videos is still under exploration. This paper presents an overview of recent efforts in applying and adapting SAM2 to biomedical images and videos. The findings indicate that while SAM2 shows promise in reducing annotation burdens and enabling zero-shot segmentation, its performance varies across different datasets and tasks. Addressing the domain gap between natural and medical images through adaptation and fine-tuning is essential to fully unleash SAM2's potential in clinical applications. To support ongoing research endeavors, we maintain an active repository that contains up-to-date SAM & SAM2-related papers and projects at https://github.com/YichiZhang98/SAM4MIS.

Prompt Your Brain: Scaffold Prompt Tuning for Efficient Adaptation of fMRI Pre-trained Model

We introduce Scaffold Prompt Tuning (ScaPT), a novel prompt-based framework for adapting large-scale functional magnetic resonance imaging (fMRI) pre-trained models to downstream tasks, with high parameter efficiency and improved performance compared to fine-tuning and baselines for prompt tuning. The full fine-tuning updates all pre-trained parameters, which may distort the learned feature space and lead to overfitting with limited training data which is common in fMRI fields. In contrast, we design a hierarchical prompt structure that transfers the knowledge learned from high-resource tasks to low-resource ones. This structure, equipped with a Deeply-conditioned Input-Prompt (DIP) mapping module, allows for efficient adaptation by updating only 2% of the trainable parameters. The framework enhances semantic interpretability through attention mechanisms between inputs and prompts, and it clusters prompts in the latent space in alignment with prior knowledge. Experiments on public resting state fMRI datasets reveal ScaPT outperforms fine-tuning and multitask-based prompt tuning in neurodegenerative diseases diagnosis/prognosis and personality trait prediction, even with fewer than 20 participants. It highlights ScaPT's efficiency in adapting pre-trained fMRI models to low-resource tasks.

Timeliness-Fidelity Tradeoff in 3D Scene Representations

Real-time three-dimensional (3D) scene representations serve as one of the building blocks that bolster various innovative applications, e.g., digital manufacturing, Virtual/Augmented/Extended/Mixed Reality (VR/AR/XR/MR), and the metaverse. Despite substantial efforts that have been made to real-time communications and computing, real-time 3D scene representations remain a challenging task. This paper investigates the tradeoff between timeliness and fidelity in real-time 3D scene representations. Specifically, we establish a framework to evaluate the impact of communication delay on the tradeoff, where the real-world scenario is monitored by multiple cameras that communicate with an edge server. To improve fidelity for 3D scene representations, we propose to use a single-step Proximal Policy Optimization (PPO) method that leverages the Age of Information (AoI) to decide if the received image needs to be involved in 3D scene representations and rendering. We test our framework and the proposed approach with different well-known 3D scene representation methods. Simulation results reveal that real-time 3D scene representation can be sensitively affected by communication delay, and our proposed method can achieve optimal 3D scene representation results.

MAVIS: Mathematical Visual Instruction Tuning

Multi-modal Large Language Models (MLLMs) have recently emerged as a significant focus in academia and industry. Despite their proficiency in general multi-modal scenarios, the mathematical problem-solving capabilities in visual contexts remain insufficiently explored. We identify three key areas within MLLMs that need to be improved: visual encoding of math diagrams, diagram-language alignment, and mathematical reasoning skills. This draws forth an urgent demand for large-scale, high-quality data and training pipelines in visual mathematics. In this paper, we propose MAVIS, the first MAthematical VISual instruction tuning paradigm for MLLMs, involving a series of mathematical visual datasets and specialized MLLMs. Targeting the three issues, MAVIS contains three progressive training stages from scratch. First, we curate MAVIS-Caption, consisting of 558K diagram-caption pairs, to fine-tune a math-specific vision encoder (CLIP-Math) through contrastive learning, tailored for improved diagram visual encoding. Second, we utilize MAVIS-Caption to align the CLIP-Math with a large language model (LLM) by a projection layer, enhancing vision-language alignment in mathematical domains. Third, we introduce MAVIS-Instruct, including 900K meticulously collected and annotated visual math problems, which is adopted to finally instruct-tune the MLLM for robust mathematical reasoning skills. In MAVIS-Instruct, we incorporate complete chain-of-thought (CoT) rationales for each problem, and minimize textual redundancy, thereby concentrating the model towards the visual elements. Data and Models are released at https://github.com/ZrrSkywalker/MAVIS

MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation

Large Multimodal Models (LMMs) exhibit impressive cross-modal understanding and reasoning abilities, often assessed through multiple-choice questions (MCQs) that include an image, a question, and several options. However, many benchmarks used for such evaluations suffer from systematic biases. Remarkably, Large Language Models (LLMs) without any visual perception capabilities achieve non-trivial performance, undermining the credibility of these evaluations. To address this issue while maintaining the efficiency of MCQ evaluations, we propose MMEvalPro, a benchmark designed to avoid Type-I errors through a trilogy evaluation pipeline and more rigorous metrics. For each original question from existing benchmarks, human annotators augment it by creating one perception question and one knowledge anchor question through a meticulous annotation process. MMEvalPro comprises $2,138$ question triplets, totaling $6,414$ distinct questions. Two-thirds of these questions are manually labeled by human experts, while the rest are sourced from existing benchmarks (MMMU, ScienceQA, and MathVista). Compared with the existing benchmarks, our experiments with the latest LLMs and LMMs demonstrate that MMEvalPro is more challenging (the best LMM lags behind human performance by $31.73\%$, compared to an average gap of $8.03\%$ in previous benchmarks) and more trustworthy (the best LLM trails the best LMM by $23.09\%$, whereas the gap for previous benchmarks is just $14.64\%$). Our in-depth analysis explains the reason for the large performance gap and justifies the trustworthiness of evaluation, underscoring its significant potential for advancing future research.

Accelerating Clinical Evidence Synthesis with Large Language Models

Automatic medical discovery by AI is a dream of many. One step toward that goal is to create an AI model to understand clinical studies and synthesize clinical evidence from the literature. Clinical evidence synthesis currently relies on systematic reviews of clinical trials and retrospective analyses from medical literature. However, the rapid expansion of publications presents challenges in efficiently identifying, summarizing, and updating evidence. We introduce TrialMind, a generative AI-based pipeline for conducting medical systematic reviews, encompassing study search, screening, and data extraction phases. We utilize large language models (LLMs) to drive each pipeline component while incorporating human expert oversight to minimize errors. To facilitate evaluation, we also create a benchmark dataset TrialReviewBench, a custom dataset with 870 annotated clinical studies from 25 meta-analysis papers across various medical treatments. Our results demonstrate that TrialMind significantly improves the literature review process, achieving high recall rates (0.897-1.000) in study searching from over 20 million PubMed studies and outperforming traditional language model embeddings-based methods in screening (Recall@20 of 0.227-0.246 vs. 0.000-0.102). Furthermore, our approach surpasses direct GPT-4 performance in result extraction, with accuracy ranging from 0.65 to 0.84. We also support clinical evidence synthesis in forest plots, as validated by eight human annotators who preferred TrialMind over the GPT-4 baseline with a winning rate of 62.5%-100% across the involved reviews. Our findings suggest that an LLM-based clinical evidence synthesis approach, such as TrialMind, can enable reliable and high-quality clinical evidence synthesis to improve clinical research efficiency.

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.