Search

Recent advances in microscopy have enabled the rapid generation of terabytes of image data in cell biology and biomedical research. Vision-language models (VLMs) offer a promising solution for large-scale biological image analysis, enhancing researchers' efficiency, identifying new image biomarkers, and accelerating hypothesis generation and scientific discovery. However, there is a lack of standardized, diverse, and large-scale vision-language benchmarks to evaluate VLMs' perception and cognition capabilities in biological image understanding. To address this gap, we introduce {\mu}-Bench, an expert-curated benchmark encompassing 22 biomedical tasks across various scientific disciplines (biology, pathology), microscopy modalities (electron, fluorescence, light), scales (subcellular, cellular, tissue), and organisms in both normal and abnormal states. We evaluate state-of-the-art biomedical, pathology, and general VLMs on {\mu}-Bench and find that: i) current models struggle on all categories, even for basic tasks such as distinguishing microscopy modalities; ii) current specialist models fine-tuned on biomedical data often perform worse than generalist models; iii) fine-tuning in specific microscopy domains can cause catastrophic forgetting, eroding prior biomedical knowledge encoded in their base model. iv) weight interpolation between fine-tuned and pre-trained models offers one solution to forgetting and improves general performance across biomedical tasks. We release {\mu}-Bench under a permissive license to accelerate the research and development of microscopy foundation models.

Image classification is one of the most fundamental capabilities of machine vision intelligence. In this work, we revisit the image classification task using visually-grounded language models (VLMs) such as GPT-4V and LLaVA. We find that existing proprietary and public VLMs, despite often using CLIP as a vision encoder and having many more parameters, significantly underperform CLIP on standard image classification benchmarks like ImageNet. To understand the reason, we explore several hypotheses concerning the inference algorithms, training objectives, and data processing in VLMs. Our analysis reveals that the primary cause is data-related: critical information for image classification is encoded in the VLM's latent space but can only be effectively decoded with enough training data. Specifically, there is a strong correlation between the frequency of class exposure during VLM training and instruction-tuning and the VLM's performance in those classes; when trained with sufficient data, VLMs can match the accuracy of state-of-the-art classification models. Based on these findings, we enhance a VLM by integrating classification-focused datasets into its training, and demonstrate that the enhanced classification performance of the VLM transfers to its general capabilities, resulting in an improvement of 11.8% on the newly collected ImageWikiQA dataset.

Federated Split Learning (FSL) is a promising distributed learning paradigm in practice, which gathers the strengths of both Federated Learning (FL) and Split Learning (SL) paradigms, to ensure model privacy while diminishing the resource overhead of each client, especially on large transformer models in a resource-constrained environment, e.g., Internet of Things (IoT). However, almost all works merely investigate the performance with simple neural network models in FSL. Despite the minor efforts focusing on incorporating Vision Transformers (ViT) as model architectures, they train ViT from scratch, thereby leading to enormous training overhead in each device with limited resources. Therefore, in this paper, we harness Pre-trained Image Transformers (PITs) as the initial model, coined FedV, to accelerate the training process and improve model robustness. Furthermore, we propose FedVZ to hinder the gradient inversion attack, especially having the capability compatible with black-box scenarios, where the gradient information is unavailable. Concretely, FedVZ approximates the server gradient by utilizing a zeroth-order (ZO) optimization, which replaces the backward propagation with just one forward process. Empirically, we are the first to provide a systematic evaluation of FSL methods with PITs in real-world datasets, different partial device participations, and heterogeneous data splits. Our experiments verify the effectiveness of our algorithms.

Long-form video understanding represents a significant challenge within computer vision, demanding a model capable of reasoning over long multi-modal sequences. Motivated by the human cognitive process for long-form video understanding, we emphasize interactive reasoning and planning over the ability to process lengthy visual inputs. We introduce a novel agent-based system, VideoAgent, that employs a large language model as a central agent to iteratively identify and compile crucial information to answer a question, with vision-language foundation models serving as tools to translate and retrieve visual information. Evaluated on the challenging EgoSchema and NExT-QA benchmarks, VideoAgent achieves 54.1% and 71.3% zero-shot accuracy with only 8.4 and 8.2 frames used on average. These results demonstrate superior effectiveness and efficiency of our method over the current state-of-the-art methods, highlighting the potential of agent-based approaches in advancing long-form video understanding.

How do two sets of images differ? Discerning set-level differences is crucial for understanding model behaviors and analyzing datasets, yet manually sifting through thousands of images is impractical. To aid in this discovery process, we explore the task of automatically describing the differences between two $\textbf{sets}$ of images, which we term Set Difference Captioning. This task takes in image sets $D_A$ and $D_B$, and outputs a description that is more often true on $D_A$ than $D_B$. We outline a two-stage approach that first proposes candidate difference descriptions from image sets and then re-ranks the candidates by checking how well they can differentiate the two sets. We introduce VisDiff, which first captions the images and prompts a language model to propose candidate descriptions, then re-ranks these descriptions using CLIP. To evaluate VisDiff, we collect VisDiffBench, a dataset with 187 paired image sets with ground truth difference descriptions. We apply VisDiff to various domains, such as comparing datasets (e.g., ImageNet vs. ImageNetV2), comparing classification models (e.g., zero-shot CLIP vs. supervised ResNet), summarizing model failure modes (supervised ResNet), characterizing differences between generative models (e.g., StableDiffusionV1 and V2), and discovering what makes images memorable. Using VisDiff, we are able to find interesting and previously unknown differences in datasets and models, demonstrating its utility in revealing nuanced insights., Comment: CVPR 2024 Oral

Human commonsense understanding of the physical and social world is organized around intuitive theories. These theories support making causal and moral judgments. When something bad happens, we naturally ask: who did what, and why? A rich literature in cognitive science has studied people's causal and moral intuitions. This work has revealed a number of factors that systematically influence people's judgments, such as the violation of norms and whether the harm is avoidable or inevitable. We collected a dataset of stories from 24 cognitive science papers and developed a system to annotate each story with the factors they investigated. Using this dataset, we test whether large language models (LLMs) make causal and moral judgments about text-based scenarios that align with those of human participants. On the aggregate level, alignment has improved with more recent LLMs. However, using statistical analyses, we find that LLMs weigh the different factors quite differently from human participants. These results show how curated, challenge datasets combined with insights from cognitive science can help us go beyond comparisons based merely on aggregate metrics: we uncover LLMs implicit tendencies and show to what extent these align with human intuitions., Comment: 34 pages, 7 figures. NeurIPS 2023

Expert feedback lays the foundation of rigorous research. However, the rapid growth of scholarly production and intricate knowledge specialization challenge the conventional scientific feedback mechanisms. High-quality peer reviews are increasingly difficult to obtain. Researchers who are more junior or from under-resourced settings have especially hard times getting timely feedback. With the breakthrough of large language models (LLM) such as GPT-4, there is growing interest in using LLMs to generate scientific feedback on research manuscripts. However, the utility of LLM-generated feedback has not been systematically studied. To address this gap, we created an automated pipeline using GPT-4 to provide comments on the full PDFs of scientific papers. We evaluated the quality of GPT-4's feedback through two large-scale studies. We first quantitatively compared GPT-4's generated feedback with human peer reviewer feedback in 15 Nature family journals (3,096 papers in total) and the ICLR machine learning conference (1,709 papers). The overlap in the points raised by GPT-4 and by human reviewers (average overlap 30.85% for Nature journals, 39.23% for ICLR) is comparable to the overlap between two human reviewers (average overlap 28.58% for Nature journals, 35.25% for ICLR). The overlap between GPT-4 and human reviewers is larger for the weaker papers. We then conducted a prospective user study with 308 researchers from 110 US institutions in the field of AI and computational biology to understand how researchers perceive feedback generated by our GPT-4 system on their own papers. Overall, more than half (57.4%) of the users found GPT-4 generated feedback helpful/very helpful and 82.4% found it more beneficial than feedback from at least some human reviewers. While our findings show that LLM-generated feedback can help researchers, we also identify several limitations.

While RNA technologies hold immense therapeutic potential in a range of applications from vaccination to gene editing, the broad implementation of these technologies is hindered by the challenge of delivering these agents effectively. Lipid nanoparticles have emerged as one of the most widely used delivery agents, but their design optimization relies on laborious and costly experimental methods. We propose to in silico optimize LNP design with machine learning models. On a curated dataset of 622 LNPs from published studies, we demonstrate the effectiveness of our model in predicting the transfection efficiency of unseen LNPs, with the multilayer perceptron achieving a classification accuracy of 98% on the test set. Our work represents a pioneering effort in combining ML and LNP design, offering significant potential for improving screening efficiency by computationally prioritizing LNP candidates for experimental validation and accelerating the development of effective mRNA delivery systems., Comment: The 2023 ICML Workshop on Computational Biology

Work on scaling laws has found that large language models (LMs) show predictable improvements to overall loss with increased scale (model size, training data, and compute). Here, we present evidence for the claim that LMs may show inverse scaling, or worse task performance with increased scale, e.g., due to flaws in the training objective and data. We present empirical evidence of inverse scaling on 11 datasets collected by running a public contest, the Inverse Scaling Prize, with a substantial prize pool. Through analysis of the datasets, along with other examples found in the literature, we identify four potential causes of inverse scaling: (i) preference to repeat memorized sequences over following in-context instructions, (ii) imitation of undesirable patterns in the training data, (iii) tasks containing an easy distractor task which LMs could focus on, rather than the harder real task, and (iv) correct but misleading few-shot demonstrations of the task. We release the winning datasets at https://inversescaling.com/data to allow for further investigation of inverse scaling. Our tasks have helped drive the discovery of U-shaped and inverted-U scaling trends, where an initial trend reverses, suggesting that scaling trends are less reliable at predicting the behavior of larger-scale models than previously understood. Overall, our results suggest that there are tasks for which increased model scale alone may not lead to progress, and that more careful thought needs to go into the data and objectives for training language models., Comment: Published in TMLR (2023), 39 pages

This paper introduces FedSecurity, an end-to-end benchmark that serves as a supplementary component of the FedML library for simulating adversarial attacks and corresponding defense mechanisms in Federated Learning (FL). FedSecurity eliminates the need for implementing the fundamental FL procedures, e.g., FL training and data loading, from scratch, thus enables users to focus on developing their own attack and defense strategies. It contains two key components, including FedAttacker that conducts a variety of attacks during FL training, and FedDefender that implements defensive mechanisms to counteract these attacks. FedSecurity has the following features: i) It offers extensive customization options to accommodate a broad range of machine learning models (e.g., Logistic Regression, ResNet, and GAN) and FL optimizers (e.g., FedAVG, FedOPT, and FedNOVA); ii) it enables exploring the effectiveness of attacks and defenses across different datasets and models; and iii) it supports flexible configuration and customization through a configuration file and some APIs. We further demonstrate FedSecurity's utility and adaptability through federated training of Large Language Models (LLMs) to showcase its potential on a wide range of complex applications.

Language models have been shown to exhibit positive scaling, where performance improves as models are scaled up in terms of size, compute, or data. In this work, we introduce NeQA, a dataset consisting of questions with negation in which language models do not exhibit straightforward positive scaling. We show that this task can exhibit inverse scaling, U-shaped scaling, or positive scaling, and the three scaling trends shift in this order as we use more powerful prompting methods or model families. We hypothesize that solving NeQA depends on two subtasks: question answering (task 1) and negation understanding (task 2). We find that task 1 has linear scaling, while task 2 has sigmoid-shaped scaling with an emergent transition point, and composing these two scaling trends yields the final scaling trend of NeQA. Our work reveals and provides a way to analyze the complex scaling trends of language models., Comment: Published at ACL 2023 Findings

Representation learning has been increasing its impact on the research and practice of machine learning, since it enables to learn representations that can apply to various downstream tasks efficiently. However, recent works pay little attention to the fact that real-world datasets used during the stage of representation learning are commonly contaminated by noise, which can degrade the quality of learned representations. This paper tackles the problem to learn robust representations against noise in a raw dataset. To this end, inspired by recent works on denoising and the success of the cosine-similarity-based objective functions in representation learning, we propose the denoising Cosine-Similarity (dCS) loss. The dCS loss is a modified cosine-similarity loss and incorporates a denoising property, which is supported by both our theoretical and empirical findings. To make the dCS loss implementable, we also construct the estimators of the dCS loss with statistical guarantees. Finally, we empirically show the efficiency of the dCS loss over the baseline objective functions in vision and speech domains.

Contrastive learning is an efficient approach to self-supervised representation learning. Although recent studies have made progress in the theoretical understanding of contrastive learning, the investigation of how to characterize the clusters of the learned representations is still limited. In this paper, we aim to elucidate the characterization from theoretical perspectives. To this end, we consider a kernel-based contrastive learning framework termed Kernel Contrastive Learning (KCL), where kernel functions play an important role when applying our theoretical results to other frameworks. We introduce a formulation of the similarity structure of learned representations by utilizing a statistical dependency viewpoint. We investigate the theoretical properties of the kernel-based contrastive loss via this formulation. We first prove that the formulation characterizes the structure of representations learned with the kernel-based contrastive learning framework. We show a new upper bound of the classification error of a downstream task, which explains that our theory is consistent with the empirical success of contrastive learning. We also establish a generalization error bound of KCL. Finally, we show a guarantee for the generalization ability of KCL to the downstream classification task via a surrogate bound.

We consider the scenario of deep clustering, in which the available prior knowledge is limited. In this scenario, few existing state-of-the-art deep clustering methods can perform well for both non-complex topology and complex topology datasets. To address the problem, we propose a constraint utilizing symmetric InfoNCE, which helps an objective of deep clustering method in the scenario train the model so as to be efficient for not only non-complex topology but also complex topology datasets. Additionally, we provide several theoretical explanations of the reason why the constraint can enhances performance of deep clustering methods. To confirm the effectiveness of the proposed constraint, we introduce a deep clustering method named MIST, which is a combination of an existing deep clustering method and our constraint. Our numerical experiments via MIST demonstrate that the constraint is effective. In addition, MIST outperforms other state-of-the-art deep clustering methods for most of the commonly used ten benchmark datasets., Comment: 48 pages, 6 figures

We show that a periodic multi-grated-gate structure can be applied to THz plasmonic FETs (TeraFETs) to improve the THz detection sensitivity. The introduction of spatial non-uniformity by separated gate sections creates regions with distinct carrier concentrations and velocities, giving rise to harmonic behaviors. The resulting frequency spectrum of DC voltage response is composed of enhanced and suppressed regions. In the enhanced region, the amplitude of response voltage can be enlarged up to 100% compared to that in a uniform channel device. The distribution pattern of those regions is directly related to the number of gate sections (Ns). A mapping of response amplitude in an Ns-frequency scale is created, which helps distinguish enhanced/suppressed regions and locate optimal operating parameters., Comment: 6 pages, 6 figures

The inevitable feature deviation of synthetic aperture radar (SAR) image due to the special imaging principle (depression angle variation) leads to poor recognition accuracy, especially in few-shot learning (FSL). To deal with this problem, we propose a dense graph prototype network (DGP-Net) to eliminate the feature deviation by learning potential features, and classify by learning feature distribution. The role of the prototype in this model is to solve the problem of large distance between congeneric samples taken due to the contingency of single sampling in FSL, and enhance the robustness of the model. Experimental results on the MSTAR dataset show that the DGP-Net has good classification results for SAR images with different depression angles and the recognition accuracy of it is higher than typical FSL methods.

Given the prevalence of 3D medical imaging technologies such as MRI and CT that are widely used in diagnosing and treating diverse diseases, 3D segmentation is one of the fundamental tasks of medical image analysis. Recently, Transformer-based models have started to achieve state-of-the-art performances across many vision tasks, through pre-training on large-scale natural image benchmark datasets. While works on medical image analysis have also begun to explore Transformer-based models, there is currently no optimal strategy to effectively leverage pre-trained Transformers, primarily due to the difference in dimensionality between 2D natural images and 3D medical images. Existing solutions either split 3D images into 2D slices and predict each slice independently, thereby losing crucial depth-wise information, or modify the Transformer architecture to support 3D inputs without leveraging pre-trained weights. In this work, we use a simple yet effective weight inflation strategy to adapt pre-trained Transformers from 2D to 3D, retaining the benefit of both transfer learning and depth information. We further investigate the effectiveness of transfer from different pre-training sources and objectives. Our approach achieves state-of-the-art performances across a broad range of 3D medical image datasets, and can become a standard strategy easily utilized by all work on Transformer-based models for 3D medical images, to maximize performance., Comment: Published at ML4H 2022

Recent multi-modal contrastive learning models have demonstrated the ability to learn an embedding space suitable for building strong vision classifiers, by leveraging the rich information in large-scale image-caption datasets. Our work highlights a distinct advantage of this multi-modal embedding space: the ability to diagnose vision classifiers through natural language. The traditional process of diagnosing model behaviors in deployment settings involves labor-intensive data acquisition and annotation. Our proposed method can discover high-error data slices, identify influential attributes and further rectify undesirable model behaviors, without requiring any visual data. Through a combination of theoretical explanation and empirical verification, we present conditions under which classifiers trained on embeddings from one modality can be equivalently applied to embeddings from another modality. On a range of image datasets with known error slices, we demonstrate that our method can effectively identify the error slices and influential attributes, and can further use language to rectify failure modes of the classifier., Comment: Published at ICLR 2023

Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models. First, we taxonomize the vast space of potential scenarios (i.e. use cases) and metrics (i.e. desiderata) that are of interest for LMs. Then we select a broad subset based on coverage and feasibility, noting what's missing or underrepresented (e.g. question answering for neglected English dialects, metrics for trustworthiness). Second, we adopt a multi-metric approach: We measure 7 metrics (accuracy, calibration, robustness, fairness, bias, toxicity, and efficiency) for each of 16 core scenarios when possible (87.5% of the time). This ensures metrics beyond accuracy don't fall to the wayside, and that trade-offs are clearly exposed. We also perform 7 targeted evaluations, based on 26 targeted scenarios, to analyze specific aspects (e.g. reasoning, disinformation). Third, we conduct a large-scale evaluation of 30 prominent language models (spanning open, limited-access, and closed models) on all 42 scenarios, 21 of which were not previously used in mainstream LM evaluation. Prior to HELM, models on average were evaluated on just 17.9% of the core HELM scenarios, with some prominent models not sharing a single scenario in common. We improve this to 96.0%: now all 30 models have been densely benchmarked on the same core scenarios and metrics under standardized conditions. Our evaluation surfaces 25 top-level findings. For full transparency, we release all raw model prompts and completions publicly for further analysis, as well as a general modular toolkit. We intend for HELM to be a living benchmark for the community, continuously updated with new scenarios, metrics, and models., Comment: Authored by the Center for Research on Foundation Models (CRFM) at the Stanford Institute for Human-Centered Artificial Intelligence (HAI). Project page: https://crfm.stanford.edu/helm/v1.0

We report on the numerical and theoretical results of sub-THz and THz detection by a current-driven InGaAs/GaAs plasmonic Field-Effect Transistor (TeraFET). New equations are developed to account for the channel length dependence of the drain voltage and saturation current. Numerical simulation results demonstrate that the effect of drain bias current on the source-to-drain response voltage (dU) varies with the device channel length. In a long-channel TeraFET where plasmonic oscillations cannot reach the drain, dU is always positive and rises rapidly with increasing drain current. For a short device in which plasmonic oscillations reach the drain, the current-induced nonuniform electric field leads to a negative response, agreeing with previous observations. At negative dU, the amplitude of the small-signal voltage at the drain side becomes larger than that at the source side. Thus, the device effectively serves as a THz amplifier in this condition. Under the resonant mode, the negative response can be further amplified near the resonant peaks. A new expression of dU is proposed to account for this resonant effect. Based on those expressions, a current-driven TeraFET spectrometer is proposed. The ease of implementation and simplified calibration procedures make it competitive or superior compared with other TeraFET-based spectrometers., Comment: 23 pages, 11 figures, 1 table

We present modality gap, an intriguing geometric phenomenon of the representation space of multi-modal models. Specifically, we show that different data modalities (e.g. images and text) are embedded at arm's length in their shared representation in multi-modal models such as CLIP. Our systematic analysis demonstrates that this gap is caused by a combination of model initialization and contrastive learning optimization. In model initialization, we show empirically and theoretically that the representation of a common deep neural network is restricted to a narrow cone. As a consequence, in a multi-modal model with two encoders, the representations of the two modalities are clearly apart when the model is initialized. During optimization, contrastive learning keeps the different modalities separate by a certain distance, which is influenced by the temperature parameter in the loss function. Our experiments further demonstrate that varying the modality gap distance has a significant impact in improving the model's downstream zero-shot classification performance and fairness. Our code and data are available at https://modalitygap.readthedocs.io/, Comment: Published at NeurIPS 2022. Code and data are available at https://modalitygap.readthedocs.io/